CN109948979B - Inventory detection method, equipment and storage medium - Google Patents
Inventory detection method, equipment and storage medium Download PDFInfo
- Publication number
- CN109948979B CN109948979B CN201910192769.0A CN201910192769A CN109948979B CN 109948979 B CN109948979 B CN 109948979B CN 201910192769 A CN201910192769 A CN 201910192769A CN 109948979 B CN109948979 B CN 109948979B
- Authority
- CN
- China
- Prior art keywords
- inventory
- clustering
- points
- point
- item
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000013507 mapping Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Abstract
The invention discloses a warehouse detection method, equipment and a computer readable storage medium, and belongs to the technical field of warehouse management. The method is suitable for the inventory detection equipment, and comprises the steps of searching in a warehouse and scanning found articles; identifying a plurality of articles including inventory items as an inventory item stack when the found articles are judged to be new inventory items through map matching operation; mapping all articles in the stock article stack, and analyzing the data obtained by mapping; and obtaining the quantity of the inventory items according to the analysis result. By adopting the invention, whether the user knows the type and the placing mode of the newly added stock articles in the warehouse in advance or not, the newly added stock articles can be quickly and accurately counted.
Description
Technical Field
The invention relates to the technical field of warehouse management, in particular to a warehouse inventory detection method, equipment and a storage medium.
Background
Inventory management is an important process step in a warehousing system, and the existing inventory quantity needs to be checked frequently in daily inventory management work to ensure the accuracy of inventory.
Existing inventory management techniques typically count products in a pre-set area, and the products in the warehouse are typically placed in a particular manner. Also, the products are typically of a particular type, such as vials, food items, and the like.
However, as people have increasingly abundant living needs, warehouses of many manufacturers and retailers have a great variety of goods to store, and the warehouses are often randomly placed for time and labor saving. The existing inventory management technology can not solve the problem of counting the inventory goods in the warehouse aiming at the unstructured environment which can not know the type and the placing mode of the goods in advance.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and a storage medium for inventory detection, so as to solve the problem that the prior art can only count inventory goods of a specific type and a fixed placement manner.
The technical scheme adopted by the invention for solving the technical problems is as follows:
according to a first aspect of the present invention, there is provided a method of inventory detection, adapted for use with an inventory detection device, the method comprising the steps of:
searching in a warehouse, and scanning the articles when the articles are found;
judging whether the found article is a new stock article or not through map matching operation;
identifying a plurality of items including the inventory item as a stack of inventory items when the found item is judged to be a new inventory item;
mapping all inventory items in the inventory item stack, and analyzing the data obtained by mapping;
and obtaining the quantity of the inventory items in the inventory item stack according to the analysis result.
According to a second aspect of the present invention, there is provided an inventory detection apparatus, the apparatus comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program realizing the steps according to the first aspect when executed by the processor.
According to a third aspect of the present invention, there is provided a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the inventory detection method according to the first or second aspect.
The inventory detection method, the equipment and the storage medium provided by the embodiment of the invention can quickly and accurately count the newly added inventory items no matter whether the types and the placing modes of the newly added inventory items in the warehouse are known in advance, thereby improving the convenience and the timeliness of warehouse management.
Drawings
Fig. 1 is a flowchart of an inventory detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another inventory detection method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an inventory detecting device according to a third embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, if suffixes such as "module", "part", or "unit" used to indicate elements are used only for the convenience of description of the present invention, they have no specific meaning by themselves. Thus, "module", "component" or "unit" may be used mixedly.
The embodiment of the invention provides an inventory detection method. The inventory detection of the present embodiment is applicable to an inventory detection apparatus. Referring to fig. 1, the method flow includes:
s101, searching in a warehouse, and scanning the articles when the articles are found;
step S102, judging whether the found article is a new stock article or not through map matching operation;
step S103, when the found article is judged to be a new inventory article, identifying a plurality of articles containing the inventory article as an inventory article stack;
step S104, mapping all inventory items in the inventory item stack, and analyzing the data obtained by mapping;
and step S105, obtaining the quantity of the inventory items in the inventory item stack according to the analysis result.
In one possible scenario, step S101, searching in a warehouse, and when an item is found, scanning the item from different directions includes:
exploring the warehouse environment by adopting a semi-random strategy, and exploring forward straight line running;
when an item is found within a distance less than a predetermined threshold, the item is scanned from different directions and at different angles.
A laser radar (LIDAR), a short term laser Detection and Ranging system, is a radar system that emits a laser beam to detect characteristic quantities such as a position and a velocity of a target. The working principle is to emit a detection signal (laser beam) to the target, then compare the received signal reflected from the target with the emitted signal, and after appropriate processing, obtain the information about the detected target.
In practical application, besides laser radar scanning, other detection devices such as a common microwave radar and a three-dimensional scanner can be adopted to scan to obtain one or more parameter combination information such as distance, direction, size, shape and color of an object.
In one possible solution, the step S102 of determining whether the found item is a new inventory item through a map matching operation includes:
converting the scanned data into coordinates of each point on the map;
clustering the points on all the maps obtained by conversion to generate clustering points of different categories;
and matching the clustering points with points in the pre-stored map data, and judging whether the clustering points are matched with the pre-stored map data.
The stock detection apparatus stores stock raw data of the warehouse in advance and stores it in the form of map data. In practical applications, the Map may be a grid Map (Grip Map), and the spatial information of the inventory goods in the warehouse may be stored and represented in a grid form. Dividing the object into grid units according to a plane coordinate system, and recording and storing various object elements for each grid unit. The pre-stored map data may also record the area, volume, and various environmental parameters of the warehouse, among others.
In a feasible scheme, clustering is performed on all the points on the map obtained by conversion to generate clustering points of different categories, and the specific method is as follows:
presetting a clustering threshold value, and setting a first point obtained by conversion as a first clustering point;
and when the distance between a second point adjacent to the first point and the first point is greater than a clustering threshold value, setting the second clustering point as a second clustering point, and when the distance between a third point adjacent to the second clustering point is greater than the clustering threshold value, setting the third clustering point as a third clustering point, and sequentially comparing until the distance between the nth point adjacent to the n-1 clustering point is greater than the clustering threshold value, and generating an nth clustering point.
In practical application, two adjacent points are judged, and whether the two points are in the same category is judged, which is called clustering. The distance limit value between two adjacent points can be preset, the distance limit value is a clustering threshold value, when the distance between two adjacent points is smaller than the clustering threshold value, the two points are points with the same attribute, and when the distance between two adjacent points is larger than the clustering threshold value, the two points are clustering points of different categories.
The cluster points of different classes are stored in the memory of the device in the form of a list.
In one possible scheme, matching the clustering point with a point in pre-stored map data, and determining whether the clustering point is a point in the pre-stored map data includes:
sampling the clustering points for the first time, presetting an inspection window, and judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than a preset window percentage threshold value, wherein the window percentage threshold value is used for identifying whether the sampled clustering points are matched with data stored in a pre-stored map;
if yes, outputting the clustering point to be matched with data stored in a pre-stored map;
if not, increasing the preset clustering threshold value so as to increase the number of the sampled clustering points, performing secondary sampling on the clustering points, judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than the preset window percentage threshold value or not, and judging that the clustering points are not matched with the points in the pre-stored map data until the clustering threshold value is greater than the preset mismatching count threshold value.
In practical application, the inspection window is within the space range of the grid map where the searched article is located. Presetting an inspection window, that is, presetting the size of the inspection window, generally means dividing a certain number of grid cells on a map so as to determine whether sampled cluster points are matched with data on the map within a certain range.
In one possible solution, step S104 maps all the inventory items in the stack of inventory items, and analyzes the data obtained by mapping, including:
moving to the vicinity of a new inventory item, recording the position as a mapping starting position, and mapping the new inventory item;
mapping all inventory items in sequence around the stack of inventory items starting from the starting location until returning to the starting location;
and carrying out merging operation on the information of all the inventory items obtained by mapping to obtain the whole volume of the inventory item stack.
The specific mode of sequentially mapping all inventory items around the inventory item stack is as follows:
the information of images, colors, sizes and the like of the inventory items is recorded at regular intervals around the inventory item stack, and the data recorded each time are stored in the map data as point clouds. I.e. mapping information of all inventory items one-to-one in the map data stored by the device.
In practical application, after the quantity of the inventory items in the inventory item stack and the information of other items are detected, the map data stored in advance are updated and stored.
In one possible solution, the step S105 of obtaining the quantity of the inventory item in the inventory item stack according to the analysis result includes:
obtaining the volume of the stock item stack and the volume of the single stock item according to the analysis result;
dividing the volume of the stack of inventory items by the volume of the individual inventory item to yield the number of inventory items in the stack of inventory items.
According to the inventory detection method, the found articles are scanned in the warehouse, the scanning information and the pre-stored inventory data are subjected to map matching operation, whether the stacks are newly added inventory articles or not is identified, the whole volume of the inventory article stacks and the volume of a single inventory article are obtained through mapping of the inventory article stacks, and therefore the number of the inventory articles in the newly added inventory article stacks is calculated, the number of the newly added inventory articles can be accurately detected whether the size and the placement position of the inventory articles in the warehouse are known in advance or not, and convenience and timeliness of warehouse management are improved.
On the basis of the foregoing embodiment, a second embodiment of the present invention provides another inventory detection method, which is suitable for an inventory detection device. Referring to fig. 2, the method includes the following steps:
step S201, the inventory detection equipment runs in a warehouse in a straight line, a semi-random strategy is adopted to explore the warehouse environment, and when an article is found within a distance smaller than a preset threshold value, a laser radar is called to scan the article from different directions and different angles;
the scan direction is randomly selected from a range equation as follows:
Newheading＝currentheading+randow([0.6pi,1.4pi])
in this embodiment, the items in the warehouse refer to Stock Keeping Units (SKUs), and the item stack (SKU Pile) refers to a collection of items of the same size and variety placed together. In this embodiment, the inventory detection device is a robot, and may be other intelligent devices.
The scanning device called by the inventory detection device can be a laser radar, a common microwave radar or a three-dimensional scanner or other detection devices which can scan and obtain information such as distance, direction, size, shape, color and the like of an article. In the present embodiment, a laser radar is taken as an example for description.
The specific scanning mode is that the laser radar emits signals outwards according to a certain angle and receives the signals reflected by the object, so that the position information of the object detected by the laser radar at each angle is obtained.
Step S202, converting data information detected by the laser radar into coordinate points on a map;
this conversion is done by using a conversion from map frames to lidar frames. Each coordinate point corresponds to a coordinate (x, y) of the object detected by the lidar in the map. These coordinate points may be stored in the form of a list.
Step S203, presetting a clustering threshold, setting a first point obtained by conversion as a first clustering point, setting the first point as a second clustering point when the distance between a second point adjacent to the first point and the first point is greater than the clustering threshold, setting the first point as a third clustering point when the distance between a third point adjacent to the second clustering point is greater than the clustering threshold, and sequentially comparing until the distance between the nth point adjacent to the n-1 clustering point is greater than the clustering threshold, so as to generate an nth clustering point;
the clustering points of different categories may also be stored in the form of a list. Since the information of the size and the position of the added inventory item is unknown, in the unknown pattern recognition, the correlation between the data is usually found from a stack of data without tags, so as to find the similarity between the data. For example: by detecting the object through the laser radar, various spatial information data of the object on the map can be obtained, wherein some spatial information data relate to the length of the object, some spatial information data relate to the height of the object, and some spatial information data relate to the width of the object. In order to be able to subsequently compare these data with pre-stored map data one by one, the data points of different classes are clustered first.
In general, the more similar two points are, the greater the similarity S is, and the smaller the distance D between the two points is; conversely, the less the two points are, the smaller the similarity S, the greater the distance D between the two points. Therefore, a clustering threshold value can be preset. The clustering threshold can be set by the user. Therefore, clustering can be performed by comparing the distance between two adjacent points with a clustering threshold.
There are many specific Clustering algorithms, such as an Exclusive Clustering algorithm (explicit Clustering), an Overlapping Clustering algorithm (Overlapping Clustering), a Hierarchical Clustering algorithm (Hierarchical Clustering), a Probabilistic Clustering algorithm (Probabilistic Clustering), and so on, which are not described herein again.
Step S204, matching the clustering points with points in prestored map data, and judging whether the clustering points are matched with the points in the prestored map data;
the equipment for inventory check stores inventory data of the warehouse in advance and stores it in the form of map data. In this embodiment, the map is a grid map, and the spatial information of the inventory goods in the warehouse can be stored and represented in a grid form. Dividing the object into grid units according to a plane coordinate system, and recording and storing elements of various objects for each grid unit.
Judging whether the clustering points are matched with points in the prestored map data or not, wherein the specific mode is as follows:
calling a grid map stored in advance, and sampling the clustering points for the first time;
presetting an inspection window, and judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than a preset window percentage threshold value, wherein the window percentage threshold value is used for identifying whether the sampled clustering points are matched with data stored in a pre-stored map;
if yes, outputting the clustering point to be matched with data stored in a pre-stored map;
if not, increasing the clustering threshold value so as to increase the number of the sampled clustering points, sampling the clustering points again, judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than a preset window percentage threshold value or not, and judging that the clustering points are not matched with the points in the pre-stored map data until the clustering threshold value is greater than a preset mismatching count threshold value.
For example, the number of cluster points for one item is 100, and 20 cluster points are sampled in order to reduce the amount of calculation. The preset window percentage threshold value is 0.8, if 18 of the 20 sampled points are in the inspection window, the ratio of the number of the clustering points in the window to the number of the sampled clustering points is 0.9 and is greater than the preset window percentage threshold value of 0.8, and therefore the clustering points are judged to be matched with the points in the pre-stored map data. On the contrary, if the ratio of the number of the clustering points in the window to the number of the sampled clustering points is smaller than the preset window percentage threshold value, the preset clustering threshold value between two adjacent points is possibly smaller, at this time, the number of the clustering points is increased by 200 by increasing the clustering threshold value, the 40 points are sampled again, and whether the 40 points are matched with the points on the map is judged; if the number of the cluster points is not matched, the cluster threshold value is increased again, namely the number of the cluster points is increased by 400, 80 points are sampled, at this time, the number of the cluster points exceeds the unmatched count threshold value (the unmatched count threshold value can be set by a user in a self-defined mode), the cluster points are judged to be unmatched with the points in the map data, and the object is a newly added inventory item. And the middle point in the cluster points is considered as the position of the item.
Step S205, when the clustering point is not matched with the point in the prestored map data, identifying the found article as a newly added stock article;
step S206, identifying a plurality of articles containing the newly added stock articles as stock article stacks;
step S207, moving to the position near the new inventory item, recording the position as a mapping initial position, and mapping the new inventory item;
step S208, starting from the starting position, sequentially mapping all inventory items around the inventory item stack until the inventory items return to the starting position;
information such as images, colors, sizes, etc. of the inventory items is recorded at regular intervals around the stack of inventory items, and the data recorded each time is stored as dots in the map data.
Since the inventory detection device does not know in advance the size and shape of the stack of inventory items, it uses LIDAR viewing to maintain a distance away from the stack of items as it moves. The inventory detection equipment surrounds the inventory item stack, stops and measures images every time the inventory detection equipment runs for a certain distance, and an instrument for measuring the images can be an onboard Kinect sensor or other image recording equipment; the data for each measurement is saved as a point in a file and saved along the location where the inventory detection device is traveling. When the inventory detection device is within a certain distance from its initial location where it begins to circle around the stack of inventory items, it recognizes that a complete cycle has been completed, stops and continues a new round of exploration for warehouse items in the other direction.
Step S209, merging and calculating the information of all the inventory items obtained by mapping to obtain the whole volume of the inventory item stack and the volume of a single inventory item;
we use a point cloud merging algorithm to combine all measurements made during the run, resulting in the overall volume of the stack of inventory items.
Step S210, dividing the volume of the stock item stack by the volume of a single stock item to obtain the number of the stock items in the stock item stack;
and step S211, updating and saving the map data stored in advance.
According to the inventory detection method, the found articles are scanned in the warehouse, the scanning information and the pre-stored inventory data are subjected to map matching operation, whether the stacks are newly added inventory articles or not is identified, the whole volume of the inventory article stacks and the volume of a single inventory article are obtained through mapping of the inventory article stacks, and therefore the number of the inventory articles in the newly added inventory article stacks is calculated, the number of the newly added inventory articles can be accurately detected whether the size and the placement position of the inventory articles in the warehouse are known in advance or not, and convenience and timeliness of warehouse management are improved.
On the basis of the foregoing embodiment, a third embodiment of the present invention provides yet another inventory detecting device.
Referring to fig. 3, the inventory detection apparatus includes: a memory 301, a processor 302 and a computer program 303 stored on said memory 301 and executable on said processor 302, said computer program 303, when executed by said processor 302, implementing the steps of inventory detection as in the first or second embodiment.
The inventory detection equipment of the embodiment scans found articles in the warehouse, performs map matching operation on the scanning information and the pre-stored inventory data, identifies whether the stacks are newly added inventory articles, and obtains the whole volume of the stacks and the volume of a single inventory article through mapping the stacks, thereby calculating the number of the inventory articles in the newly added inventory article stacks.
On the basis of the foregoing embodiments, an embodiment four of the present invention provides a computer-readable storage medium, which is characterized in that the computer-readable storage medium stores thereon a computer program, and the computer program, when executed by a processor, implements the steps of inventory detection as in the first embodiment or the second embodiment.
The computer-readable storage medium of the embodiment scans the found articles in the warehouse, performs map matching operation on the scanning information and the pre-stored inventory data, identifies whether the stack is a newly-added inventory article stack, and obtains the whole volume of the inventory article stack and the volume of a single inventory article by mapping the inventory article stack, thereby calculating the number of inventory articles in the newly-added inventory article stack.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. An inventory detection method, which is suitable for an inventory detection device, and comprises the following steps:
searching in a warehouse, and scanning the articles when the articles are found;
through map matching operation, whether the found article is a new inventory article is judged, and the method specifically comprises the following steps:
converting the scanned data into coordinates of each point on the map,
clustering the points on all the maps obtained by conversion to generate clustering points of different categories,
matching the clustering points with points in prestored map data, and judging whether the clustering points are matched with the prestored map data;
identifying a plurality of items including the inventory item as a stack of inventory items when the found item is judged to be a new inventory item;
mapping all inventory items in the inventory item stack, and analyzing the data obtained by mapping, specifically comprising: moving to the vicinity of a new inventory item, recording the position near the new inventory item as a mapping initial position, mapping the new inventory item, sequentially mapping all inventory items around the inventory item stack from the initial position until the initial position is reached, and merging and calculating the information of all the inventory items obtained by mapping to obtain the whole volume of the inventory item stack;
and obtaining the quantity of the inventory items in the inventory item stack according to the analysis result.
2. The inventory detection method as recited in claim 1, wherein deriving the quantity of inventory items in the stack of inventory items based on the analysis comprises:
obtaining the volume of the stock item stack and the volume of the single stock item according to the analysis result;
dividing the volume of the stack of inventory items by the volume of the individual inventory item to yield the number of inventory items in the stack of inventory items.
3. The inventory detection method as recited in claim 1, wherein searching within the warehouse and scanning the item when found comprises:
exploring the warehouse environment by adopting a semi-random strategy, and exploring forward straight line running;
when an item is found within a distance less than a predetermined threshold, the item is scanned from different directions and at different angles.
4. The inventory detection method according to claim 1, wherein the clustering of the points on all the maps obtained by the conversion to generate the clustering points of different categories is performed by:
presetting a clustering threshold value, and setting a first point obtained by conversion as a first clustering point;
and when the distance between a second point adjacent to the first point and the first point is greater than a clustering threshold value, setting the second clustering point as a second clustering point, and when the distance between a third point adjacent to the second clustering point is greater than the clustering threshold value, setting the third clustering point as a third clustering point, and sequentially comparing until the distance between the nth point adjacent to the (n-1) th clustering point is greater than the clustering threshold value, and generating the nth clustering point.
5. The inventory detection method of claim 4, wherein matching the cluster points to points in pre-stored map data and determining whether the cluster points match the pre-stored map data comprises:
sampling the clustering points for the first time, presetting an inspection window, and judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than a preset window percentage threshold value, wherein the window percentage threshold value is used for identifying whether the sampled clustering points are matched with data stored in a pre-stored map;
if yes, outputting the clustering point to be matched with data stored in a pre-stored map; if not, increasing the preset clustering threshold value, carrying out secondary sampling on the clustering points, judging whether the ratio of the number of the clustering points in the inspection window to the number of the sampled clustering points is greater than the preset window percentage threshold value or not, and judging that the clustering points are not matched with the points in the pre-stored map data until the clustering threshold value is greater than the preset mismatching count threshold value.
6. The inventory detection method as recited in claim 1, wherein mapping all of the inventory items in sequence around the stack of inventory items is by:
recording the image, color and size information of the inventory item at regular intervals around the inventory item stack, and storing the data recorded each time in the map data as point cloud.
7. An inventory detection device, characterized in that the device comprises: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of any of claims 1 to 6.
8. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of any of the claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192769.0A CN109948979B (en) | 2019-03-14 | 2019-03-14 | Inventory detection method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192769.0A CN109948979B (en) | 2019-03-14 | 2019-03-14 | Inventory detection method, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109948979A CN109948979A (en) | 2019-06-28 |
| CN109948979B true CN109948979B (en) | 2021-05-11 |
Family
ID=67009830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910192769.0A Active CN109948979B (en) | 2019-03-14 | 2019-03-14 | Inventory detection method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948979B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626660B (en) * | 2020-04-21 | 2024-03-12 | 普洛斯企业发展(上海)有限公司 | Inventory determination method and device for bearing device and computer readable storage medium |
| CN116029536B (en) * | 2023-03-28 | 2023-06-27 | 深圳市实佳电子有限公司 | NFC technology-based intelligent warehouse cargo scheduling method, NFC technology-based intelligent warehouse cargo scheduling device, NFC technology-based intelligent warehouse cargo scheduling equipment and NFC technology-based intelligent warehouse cargo scheduling medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105931117A (en) * | 2016-04-28 | 2016-09-07 | 感知控股集团有限公司 | Internet of things movable property supervision method and system |
| US9691151B1 (en) * | 2015-08-25 | 2017-06-27 | X Development Llc | Using observations from one or more robots to generate a spatio-temporal model that defines pose values for a plurality of objects in an environment |
| CN106934826A (en) * | 2017-02-28 | 2017-07-07 | 东华理工大学 | A kind of modeling of rock side slope fine structure and block identification method |
| CN107667366A (en) * | 2015-03-24 | 2018-02-06 | 开利公司 | Systems and methods for capturing and analyzing multi-dimensional building information |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
| CN108779980A (en) * | 2016-03-14 | 2018-11-09 | 讯宝科技有限责任公司 | The device and method of size are determined using digital picture and depth data |
| CN108960738A (en) * | 2018-07-17 | 2018-12-07 | 重庆大学 | A kind of laser radar data clustering method under warehouse aisles environment |
| CN109325998A (en) * | 2018-10-08 | 2019-02-12 | 香港理工大学 | Indoor 3D modeling method, system and related device based on point cloud data |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9599715B2 (en) * | 2010-08-03 | 2017-03-21 | Faro Technologies, Inc. | Scanner display |
| US10913604B2 (en) * | 2017-06-21 | 2021-02-09 | Locus Robotics Corp. | System and method for queuing robots destined for one or more processing stations |
-
2019
- 2019-03-14 CN CN201910192769.0A patent/CN109948979B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107667366A (en) * | 2015-03-24 | 2018-02-06 | 开利公司 | Systems and methods for capturing and analyzing multi-dimensional building information |
| US9691151B1 (en) * | 2015-08-25 | 2017-06-27 | X Development Llc | Using observations from one or more robots to generate a spatio-temporal model that defines pose values for a plurality of objects in an environment |
| CN108779980A (en) * | 2016-03-14 | 2018-11-09 | 讯宝科技有限责任公司 | The device and method of size are determined using digital picture and depth data |
| CN105931117A (en) * | 2016-04-28 | 2016-09-07 | 感知控股集团有限公司 | Internet of things movable property supervision method and system |
| CN106934826A (en) * | 2017-02-28 | 2017-07-07 | 东华理工大学 | A kind of modeling of rock side slope fine structure and block identification method |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
| CN108960738A (en) * | 2018-07-17 | 2018-12-07 | 重庆大学 | A kind of laser radar data clustering method under warehouse aisles environment |
| CN109325998A (en) * | 2018-10-08 | 2019-02-12 | 香港理工大学 | Indoor 3D modeling method, system and related device based on point cloud data |
Non-Patent Citations (2)
| Title |
|---|
| An approach for segmenting 3D LiDAR data using Multi-Volume grid structures;Selma Gaga;《IEEE》;20171212;全文 * |
| 激光测距在仓储搬运机器人运动中的应用;孙海;《电子技术与软件工程》;20170111;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948979A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113412505B (en) | Processing unit and method for ordered representation and feature extraction of point clouds obtained by detection and ranging sensors | |
| CN111624622B (en) | Obstacle detection method and device | |
| CN109829032B (en) | Method, equipment and storage medium for article identification | |
| CN108875804B (en) | Data processing method based on laser point cloud data and related device | |
| KR20210020945A (en) | Vehicle tracking in warehouse environments | |
| CN108007451B (en) | Method and device for detecting position and posture of cargo carrying device, computer equipment and storage medium | |
| CN103443838B (en) | Object recognition device | |
| JPH07225275A (en) | Vehicle distance data processing device | |
| CN110780276A (en) | Tray identification method and system based on laser radar and electronic equipment | |
| WO2025002358A1 (en) | Methods and systems for locating targets and device docking | |
| CN110471086B (en) | Radar fault detection system and method | |
| CN113776533A (en) | Repositioning method and device for movable equipment | |
| CN110390706B (en) | Object detection method and device | |
| CN109948979B (en) | Inventory detection method, equipment and storage medium | |
| CN113375657B (en) | Method, device and electronic device for updating electronic map | |
| KR102114558B1 (en) | Ground and non ground detection apparatus and method utilizing lidar | |
| WO2023155793A1 (en) | Point cloud processing method and apparatus, and laser radar | |
| KR20220078219A (en) | Method for determining tuning parameter, group density-based clustering method, method and apparatus for tracking object using LiDAR sensor | |
| Manurung et al. | Custom pallet detection using YOLOv5 deep learning architecture | |
| KR101097182B1 (en) | Method to extract information advantageous for matching with altitude map from 3D distance information | |
| CN115047472A (en) | Method, device and equipment for determining laser radar point cloud layering and storage medium | |
| CN109752730B (en) | Laser positioning method and system based on V-groove detection | |
| CN115390051B (en) | Laser radar calibration method, device, equipment and storage medium | |
| WO2022009090A1 (en) | System and method for detecting proximity between objects using threshold based clustering | |
| Önen et al. | LiDAR-based occupancy grid map estimation exploiting spatial sparsity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 510000 Room 601, building 5, CRCC global center, No.1 Jingang Avenue, Nansha District, Guangzhou City, Guangdong Province Patentee after: Guangzhou lanpangzi Mobile Technology Co.,Ltd. Address before: 510000 No.106 Fengze East Road, Nansha District, Guangzhou City, Guangdong Province (self compiled Building 1) x1301-g6161 (cluster registration) (JM) Patentee before: GUANGZHOU LANPANGZI ROBOT Co.,Ltd. |