CN118025762B - Dynamic control method for logistics warehouse conveying line - Google Patents
Dynamic control method for logistics warehouse conveying line Download PDFInfo
- Publication number
- CN118025762B CN118025762B CN202410368038.8A CN202410368038A CN118025762B CN 118025762 B CN118025762 B CN 118025762B CN 202410368038 A CN202410368038 A CN 202410368038A CN 118025762 B CN118025762 B CN 118025762B
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- level
- conveyor belt
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 238000012937 correction Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000005265 energy consumption Methods 0.000 abstract description 2
- 230000001276 controlling effect Effects 0.000 description 11
- 238000005259 measurement Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
Landscapes
- Control Of Conveyors (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a dynamic control method for a logistics warehouse conveying line; the conveying system adopted by the method comprises a plurality of conveying belts and a plurality of monitoring cameras which are connected in sequence. Monitoring cameras are distributed at the joint of every two adjacent conveyor belts. The monitoring camera can shoot two monitored areas at the same time. The two monitored areas are respectively an output area of the former conveyor belt and an input area of the latter conveyor belt. The invention uses a camera to collect the image of the joint of two adjacent belts; according to the standard deviation, brightness and definition of the green channel of the image after brightness correction, the busyness of the two conveying belts is obtained, and the conveying speed of each conveying belt is dynamically adjusted according to the busyness of the obtained busyness, so that energy consumption caused by invalid working is saved, the average running power of a logistics warehouse conveying line is reduced, and electric energy waste is reduced under the condition of meeting the requirement of conveying functions.
Description
Technical Field
The invention belongs to the technical field of in-bin energy-saving control, and particularly relates to a dynamic control method for a logistics warehouse conveying line.
Background
In an express warehouse, a large number of belt conveyor lines are required to be arranged for conveying packages from a warehouse entrance to a position where a sorting machine is located; in the prior art, the control of the belt conveyor lines is single, and the start and stop are generally controlled by physical control; for some large sorting centers, the belt conveyor line runs continuously for 24 hours a day, and the goods amount fluctuates in the process; when the amount of goods is small, running the belt conveyor line at standard speed can result in waste of electrical energy. Therefore, a control method capable of automatically judging busyness of different belt conveyor lines and automatically regulating and controlling conveying speeds of different belt conveyor lines according to the busyness is needed to be designed.
Disclosure of Invention
The invention aims to provide a dynamic control method for a logistics warehouse conveying line.
The invention provides a dynamic control method for a logistics warehouse conveying line, the adopted conveying system comprises a plurality of conveying belts and a plurality of monitoring cameras which are connected in sequence. Monitoring cameras are distributed at the joint of every two adjacent conveyor belts. The monitoring camera can shoot two monitored areas at the same time. The two monitored areas are respectively an output area of the former conveyor belt and an input area of the latter conveyor belt. Each conveyor belt has three operating conditions. The three operating states are respectively a low-speed operating state with the operating speeds increased in sequence normal operating conditions and high speed operating conditions.
Step one, an image acquisition stage.
Each monitoring camera continuously shoots. Each monitoring camera collects images of two corresponding monitored areas.
And step two, a preliminary analysis stage of the parcel quantity.
And acquiring the standard deviation of a green channel of the monitored area image, and converting the standard deviation into the brightness average value of the saturation channel after the HSV model. And if the image of the monitored area at the current moment and the image of the monitored area at the last moment meet the following judging conditions, judging that the busyness level of the monitored area is one level, and directly executing the fourth step.
The judgment conditions are as follows: (1) The standard deviation of the green channel of the image at the current time and the image at the previous time are both smaller than the standard deviation threshold alpha. (2) The difference between the standard deviation of the image at the current moment and the green channel at the previous moment is within a preset standard deviation error interval. (3) The saturation channel brightness average of the image at the current moment and the image at the previous moment is smaller than the first brightness threshold value beta. (4) The difference between the brightness average value of the image at the current moment and the saturation channel of the image at the previous moment is in a preset brightness error interval.
And step three, a secondary analysis stage of the parcel quantity.
Step 3-1 brightness analysis
And converting the monitored area image into a gray scale image, and measuring the brightness of the obtained gray scale image. And if the brightness average value of the obtained gray scale image is smaller than the second brightness threshold epsilon. Step 3-2 is performed. Otherwise, judging the busy level of the corresponding monitored area as the second level, and directly entering the fourth step.
Step 3-2. Image Secondary processing stage
And (3) sequentially performing image brightness correction, gaussian filtering, multi-threshold binarization and definition evaluation on the gray level image obtained in the step (3-1) to obtain a definition comprehensive evaluation index C.
And step 3-3, judging that the busyness grade of the conveyor belt is three-level if the definition comprehensive evaluation index C obtained in the step 3-2 is greater than a definition threshold T1 or the saturation channel brightness average value obtained in the step two is greater than a third brightness threshold T2. Otherwise, judging the busy level of the conveyer belt as a second level.
And step four, a dynamic control stage of the conveyer belt.
And if the busy levels of the output area of the front conveying belt and the input area of the rear conveying belt are all at one level, controlling the rear conveying belt to be switched to a low-speed running state.
And if the busyness level of the output area of the former conveyor belt is one level and the busyness level of the input area of the latter conveyor belt is two or three levels, controlling the latter conveyor belt to switch to a normal running state.
And if the busy level of the output area of the former conveyor belt is two or three, and the busy level of the input area of the latter conveyor belt is one or two, controlling the latter conveyor belt to switch to a normal running state.
And if the busyness level of the output area of the former conveyor belt is two or three stages and the busyness level of the input area of the latter conveyor belt is three stages, controlling the latter conveyor belt to switch to a high-speed running state.
Preferably, the busy level of the monitored area is divided into primary, secondary and tertiary. The proportion t of the wrapping coverage on the monitored areas of the first level, the second level and the third level is sequentially increased. When t is less than or equal to 5%, the busy grade is first-grade. When 5% < t.ltoreq.85%, the busy grade is considered as second grade. When t > 85%, the busy level is considered to be three levels.
Preferably, the low-speed running state has a running speed of 0.1m/s to 0.3m/s. The operating speed of the normal operating state is 0.4 m/s-0.6 m/s. The running speed of the high-speed running state is 0.7 m/s-0.8 m/s.
Preferably, the process of acquiring the images of the two monitored areas corresponding to the same monitoring camera is as follows: and performing Mask processing on the image shot by the monitoring camera, removing the background part outside the conveyor belt in the image, and acquiring two monitored area images.
Preferably, the standard deviation threshold value α is 40 to 60.
Preferably, the method for taking the value of the first brightness threshold value beta is as follows: and in 24 continuous hours, acquiring an image of the monitored area under the condition of no package every other hour, and taking the maximum saturation channel brightness average value in each acquired image to be added with 5-15 as a first brightness threshold value beta.
Preferably, in the second step, for an image of a monitored area, the standard deviation of the green channel is acquired first. And if the standard deviation of the obtained green channel is smaller than the standard deviation threshold alpha, carrying out brightness measurement on the monitored area image. Otherwise, the brightness measurement of the monitored area image is skipped directly.
Preferably, the method for taking the value of the second brightness threshold epsilon in the step 3-1 is as follows: and in 24 continuous hours, acquiring images of the monitored area under the condition that a busy level is at a first level every preset time period, and taking the maximum value in the brightness average value of the gray level images corresponding to the images as a second brightness threshold epsilon.
Preferably, the image brightness correction in step 3-2 is performed as follows:
L＝L0+LS
Wherein, L 0 and L are respectively the brightness values before and after correction of the same pixel point in the gray scale image. L S is a brightness correction value, the expression is To correct the average brightness of the front gray map.
Preferably, the multi-threshold binarization process in the step 3-2 is as follows: and changing the gray values of the pixel points with gray values in the interval [80,120] U [200,210] U [235,245] in the gray map subjected to image brightness correction and Gaussian filtering into black, and changing the gray values of the rest pixel points into white.
Preferably, the process of sharpness evaluation is:
(1) Contour detection: an edge detection algorithm is used to detect contours in the image.
(2) The profile is simplified.
(3) Line analysis: and calculating a definition comprehensive evaluation index C. The expression is as follows:
C＝wlength·length+wdirection·direction+wdensity·density
Wherein w length、wdirection and w density represent weights of line length, direction and density, respectively; length is the average length of all lines in the gray scale map; direction is the average value of angle deviation values of angles of all lines in the gray level diagram and the vertical direction; the density is a line density index, and the value of the density index is the average value of the length area ratios of all the profiles; the length area of a contour is the ratio of the sum of all line lengths contained in the contour to the contour area.
Preferably, in the third step, the value of the definition threshold T1 is 200-400; the third brightness threshold T2 has a value of 150 to 170.
The invention has the beneficial effects that:
1. The invention uses a camera to collect the image of the joint of two adjacent belts; according to the standard deviation, brightness and definition of the green channel of the image after brightness correction, the busyness of the two conveying belts is obtained, and the conveying speed of each conveying belt is dynamically adjusted according to the busyness of the obtained busyness, so that energy consumption caused by invalid working is saved, the average running power of a logistics warehouse conveying line is reduced, and electric energy waste is reduced under the condition of meeting the requirement of conveying functions.
2. The invention can reduce the running speed of the conveyer belt when the transport capacity requirement is low, thereby reducing the loss of the conveyer belt and the driving element thereof and prolonging the service life of the logistics warehouse conveying line.
3. The invention combines the busyness of two adjacent conveyor belts to comprehensively regulate the conveying speed of the latter conveyor belt, thereby being beneficial to avoiding the problem of untimely response of speed change of the conveyor belt caused by sudden increase of the number of packages.
4. The invention can display the package image on each section of conveyor belt in real time, and can realize package early warning display by combining with the image recognition module.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic flow chart of an image acquisition stage in the present invention;
FIG. 3 is a schematic illustration of two monitored regions in an image acquired in accordance with the present invention;
FIG. 4 is a schematic flow chart of the primary parcel analysis stage and the secondary parcel analysis stage of the present invention;
FIG. 5 is a schematic diagram of the multi-threshold binarization process according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, in the method for dynamically controlling the conveying line of the logistics warehouse, the adopted conveying system is used for conveying the packages at the warehouse entrance to the packing area of the sorting equipment in the warehouse, and then the code scanning packing operation is carried out by manual or automatic equipment. The conveying system comprises a plurality of conveying belts and a plurality of monitoring cameras which are sequentially connected in series. Monitoring cameras are distributed at the joint of every two adjacent conveyor belts. The monitoring camera is arranged above the conveyer belt and can shoot the output area of the former conveyer belt and the input area of the latter conveyer belt at the same time.
For two adjacent conveyor belts, the output area of the former conveyor belt and the input area of the latter conveyor belt are respectively used as a monitored area. So each monitoring camera shoots two monitored areas at the same time.
For each monitored area, the busyness of the conveyor belt is measured through busyness grades; the busy class is divided into primary, secondary and tertiary. The number of the primary, the secondary and the tertiary packages is smaller, general and more.
In some embodiments, the busy level corresponds to the size of the proportion t of the conveyor belt covered by the parcel; when t is less than or equal to 5%, the busy grade is a first grade; when 5% < t is less than or equal to 85%, the busyness grade is regarded as a second grade; when t is more than 85%, the busy grade is regarded as three grades;
Each conveyor belt has three running states; the three operating states are a low-speed operating state, a normal operating state and a high-speed operating state respectively. The running speed of the low-speed running state is 0.1 m/s-0.3 m/s; the running speed of the normal running state is 0.4 m/s-0.6 m/s; the running speed of the high-speed running state is 0.7 m/s-0.8 m/s.
In this embodiment, the color of the conveyor belt is gray black.
The dynamic control method for the logistics warehouse conveyor line comprises the following steps:
Step one, a starting stage.
Starting and logging in all monitoring cameras; the monitoring cameras are respectively matched with the camera channels, and the image quality and the resolution of the monitoring cameras are set, so that the monitoring cameras can better record the package distribution condition on the conveyer belt.
And step two, an image acquisition stage.
The monitoring camera continuously shoots images of front and rear areas of the connecting position of the two corresponding conveyor belts, and forms a real-time picture byte stream for uploading; each image is correspondingly matched with the corresponding conveyer belt number of the record. And respectively performing Mask processing on each image, removing background parts outside the conveyor belt in the images, and cutting and separating two monitored area images (specifically, an output area image of the previous conveyor belt and an input area image of the previous conveyor belt) from one complete image.
The Mask processing process comprises the following steps: and overlapping the pre-acquired mask image with the picture frame image to be identified to obtain two monitored area images so as to carry out subsequent specific operation on the transmission belt area. The mask image acquisition process comprises the following steps: randomly extracting an image of a monitoring area, and setting vertex coordinate values (mostly four vertexes of a trapezoid, clockwise setting-X 1,Y1)、(X2,Y2)、(X3,Y3 and X 4,Y4) of the monitored area of the conveyor belt in the image; creating an image with the same pixel value as the monitoring picture as a mask image; and filling the quadrilateral areas corresponding to the two monitored areas in the mask image with white, and filling other background areas with black. And finally, superposing the mask image and a picture frame image to be identified later so as to carry out subsequent specific operation on the transmission belt region.
And step three, a preliminary analysis stage of the parcel quantity.
And 3-1, analyzing the standard deviation of the color.
Performing RGB color measurement on the monitored area image processed in the second step respectively to obtain the standard deviation of the green channel of the monitored area image; if the standard deviation is smaller than the standard deviation threshold alpha, executing the step 3-2; otherwise, directly executing the step 3-3. The value of alpha is 40-60, the value is set according to the area of the monitored area, and the larger the area is, the smaller the value of the standard deviation threshold alpha is.
And 3-2, a brightness analysis stage.
Converting the monitored area image processed in the second step into an HSV model from an RGB color model, and collecting a saturation channel image of the obtained HSV model; and carrying out brightness measurement on the saturation channel image to obtain the average value of the saturation channel brightness of the monitored area image.
3-3, If the image of the monitored area at the current moment and the image of the monitored area at the last moment meet the following judging conditions, judging that the busy level of the monitored area is one level (less package quantity is indicated), and directly executing the step five; otherwise, executing the fourth step.
The judgment conditions are as follows:
(1) The standard deviation of the green channel of the image at the current moment and the image at the previous moment is smaller than the standard deviation threshold alpha;
(2) The difference between the standard deviation of the image at the current moment and the standard deviation of the green channel at the previous moment is in a preset standard deviation error interval; the value of the preset standard deviation error interval is-1.5 to 1.5. This condition indicates that the standard deviation of the green channel fluctuates little between the present time and the previous time.
(3) The saturation channel brightness average of the image at the current moment and the image at the previous moment is smaller than the first brightness threshold value beta. The value method of the first brightness threshold value beta is as follows: in 24 continuous hours, an image of a monitored area without wrapping is acquired every other hour, and the saturation channel brightness average value of the image of the saturation channel brightness average value of the HSV model in each acquired image is added with 5-15 (preferably 10) to be used as a first brightness threshold value beta.
(4) The difference between the brightness average value of the image at the current moment and the saturation channel of the image at the previous moment is in a preset brightness error interval; the preset brightness error interval is within the range of-1.8 to 1.8. This condition indicates that the luminance fluctuation of the image saturation channel at the present time and the last time is small.
The reason why the standard deviation of the green channel is used in the determination condition is that: most of the colors of the express packages are gray, black, orange or brown, the fluctuation range of the express packages is small by using the standard deviation of the green channel, and the express packages are more stable than the red channel and the blue channel.
The reason why the saturation channel luminance average value is used in the determination condition is that: because the saturation channel brightness of the conveyor belt image is lower than the saturation channel brightness of most of the wrapping image; therefore, the first brightness threshold β is used to measure whether a larger area on the conveyor belt presents higher brightness, so that when the package size is larger, the color standard deviation in the step 3-1 cannot be used to accurately determine the package amount on the conveyor belt.
And step four, a secondary analysis stage of the parcel quantity.
4-1 Brightness analysis
Converting the monitored area image into a gray level image, and measuring the brightness of the obtained gray level image; if the brightness average value of the obtained gray level image is smaller than the second brightness threshold epsilon; step 4-2 is performed; otherwise, judging that the busy level of the corresponding monitored area is two-level (representing the parcel quantity and the like), and directly entering the step five.
The value method of the second brightness threshold epsilon is as follows: in 24 continuous hours, an image of the monitored area with a busy grade being classified as one grade (in this embodiment, an image of the monitored area without a package is collected) is collected every one hour, and the brightness average value of the gray level map of the image with the largest brightness average value after each obtained image is converted into the gray level map is taken as the second brightness threshold epsilon. Since the conveyor belt is gray black, the conveyor belt image brightness is less than the package image brightness, and therefore, basically, the second brightness threshold epsilon will be larger than the first brightness threshold beta.
4-2 Image secondary processing stage
And (3) sequentially performing image brightness correction, gaussian filtering, multi-threshold binarization and definition evaluation on the gray level image of the monitored area image obtained in the step (4-1), and then entering the step (4-3).
The expression for image brightness correction is as follows:
L＝L0+LS
Wherein, L 0 and L are respectively the brightness values before and after correction of the same pixel point in the image; l S is a brightness correction value, the expression is The average brightness of the image before correction;
the multi-threshold binarization process is as follows:
multiple threshold binarization: the gray values of the pixel points with gray values in the interval [80,120] U [200,210] U [235,245] in the image are changed to black, and the gray values of the other pixel points are changed to white; the operation is shown in fig. 5.
The process of sharpness evaluation is:
(1) Contour detection: an edge detection algorithm (e.g., canny edge detection algorithm) is used to detect contours in the image. Black lines in the image are found.
(2) And (3) simplifying the profile: for the detected contours, a straight line fitting or polyline approximation method is used for simplification.
(3) Line analysis: the simplified profile is analyzed, taking into account the following factors: a. length of line: the stubs may be noisy or cluttered lines, with greater definition at a greater number of stubs representing a greater number of packages. b. The direction of the lines: if the line direction is too vertical or horizontal, this indicates a lower clarity of the package and a lower number of packages. c density of lines: the higher the density of lines, the more complex the image, the higher the sharpness and the greater the number of packages.
Evaluation index: considering the above factors in combination, this embodiment designs a comprehensive evaluation index. The weighting of the different factors can be considered using a weighted summation, and then a sharpness expression is obtained as follows:
C＝wlength·length+wdirection·direction+wdensity·density
Wherein w length、wdirection and w density respectively represent weights of length, direction and density of the lines, and the values are preferably 0.5, 0.3 and 0.2 respectively. length is a line length index, and the value of the length index is the average length of all lines in the image, namely the ratio of the sum of the lengths of all lines to the number of the lines; the direction is a line direction index, and the value of the direction index is the average value of angle deviation values of angles and vertical directions of all lines in the image; the density is a line density index, and the value of the density index is the average value of the length area ratios of all the profiles; the length area of a contour is the ratio of the sum of all line lengths contained in the contour to the contour area.
And 4-3, if the definition obtained in the step 4-2 is greater than a definition threshold T1, or the saturation channel brightness average value of the monitored area image obtained in the step 3-2 is greater than a third brightness threshold T2, judging that the busyness level of the conveyer belt is three-level (more packages are indicated), and entering a step five.
Otherwise, judging that the busy level of the conveyer belt is two-level (representing the parcel volume and the like), and entering a step five.
The value of the definition threshold T1 is 200-400; the value of the third brightness threshold T2 is 150-170, the specific value is adjusted according to the color condition of the transported package in the actual scene, and the more vivid the average color condition of the transported package is, the larger the value of the third brightness threshold T2 is.
And fifthly, a conveying belt dynamic control stage.
And controlling the speed of each conveyor belt according to the busy level of each monitored area, wherein the control conditions are as follows:
And if the busy levels of the output area of the front conveying belt and the input area of the rear conveying belt are all at one level, controlling the rear conveying belt to be switched to a low-speed running state.
And if the busyness level of the output area of the former conveyor belt is one level and the busyness level of the input area of the latter conveyor belt is two or three levels, controlling the latter conveyor belt to switch to a normal running state.
And if the busy level of the output area of the former conveyor belt is two or three, and the busy level of the input area of the latter conveyor belt is one or two, controlling the latter conveyor belt to switch to a normal running state.
And if the busyness level of the output area of the former conveyor belt is two or three stages and the busyness level of the input area of the latter conveyor belt is three stages, controlling the latter conveyor belt to switch to a high-speed running state.
The conveying speed of the conveying belt in the energy-saving mode is lower than that in the standard mode.
Claims (10)
1. A dynamic control method for a logistics warehouse conveying line is characterized by comprising the following steps: the adopted conveying system comprises a plurality of conveying belts and a plurality of monitoring cameras which are sequentially connected; monitoring cameras are distributed at the joint of every two adjacent conveyor belts; the monitoring camera can shoot two monitored areas simultaneously; the two monitored areas are respectively an output area of the former conveyor belt and an input area of the latter conveyor belt; each conveyor belt has three running states; the three operating states are respectively a low-speed operating state with the operating speeds increased in sequence a normal operating state and a high-speed operating state;
Step one, an image acquisition stage;
shooting is continuously carried out by each monitoring camera; each monitoring camera acquires images of two corresponding monitored areas;
step two, a preliminary analysis stage of the parcel quantity;
Collecting the standard deviation of a green channel of the monitored area image, and converting the standard deviation into a saturation channel brightness average value of an HSV model; if the image of the monitored area at the current moment and the image of the monitored area at the last moment meet the following judging conditions, judging that the busyness level of the monitored area is one level, and directly executing the fourth step;
The judgment conditions are as follows: (1) The standard deviation of the green channel of the image at the current moment and the image at the previous moment is smaller than the standard deviation threshold alpha; (2) The difference between the standard deviation of the image at the current moment and the standard deviation of the green channel at the previous moment is in a preset standard deviation error interval; (3) The average value of the brightness of the saturation channel of the image at the current moment and the image at the last moment is smaller than a first brightness threshold value beta; (4) The difference between the brightness average value of the image at the current moment and the saturation channel of the image at the previous moment is in a preset brightness error interval;
The judging condition is that the standard deviation of the green channel of the image is smaller than a standard deviation threshold alpha, and the brightness average value of the image is smaller than a first brightness threshold beta;
step three, a secondary analysis stage of the parcel quantity;
step 3-1 brightness analysis
Converting the monitored area image into a gray level image, and measuring the brightness of the obtained gray level image; if the brightness average value of the obtained gray level image is smaller than the second brightness threshold epsilon; step 3-2 is performed; otherwise, judging the busy level of the corresponding monitored area as a second level, and directly entering the fourth step;
step 3-2. Image Secondary processing stage
Sequentially performing image brightness correction, gaussian filtering, multi-threshold binarization and definition evaluation on the gray level image obtained in the step 3-1 to obtain a definition comprehensive evaluation index C;
Step 3-3, judging that the busyness grade of the conveyor belt is three-level if the definition comprehensive evaluation index C obtained in the step 3-2 is greater than a definition threshold T1 or the saturation channel brightness average value obtained in the step two is greater than a third brightness threshold T2; otherwise, judging the busy level of the conveyer belt as a second level;
step four, a conveyor belt dynamic control stage;
if the busy levels of the output area of the former conveyor belt and the input area of the latter conveyor belt are all the first level, the latter conveyor belt is controlled to be switched to a low-speed running state;
if the busy level of the output area of the former conveyor belt is one level and the busy level of the input area of the latter conveyor belt is two or three levels, controlling the latter conveyor belt to switch to a normal running state;
If the busy level of the output area of the former conveyor belt is two or three, and the busy level of the input area of the latter conveyor belt is one or two, controlling the latter conveyor belt to switch to a normal running state;
and if the busyness level of the output area of the former conveyor belt is two or three stages and the busyness level of the input area of the latter conveyor belt is three stages, controlling the latter conveyor belt to switch to a high-speed running state.
2. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the running speed of the low-speed running state is 0.1 m/s-0.3 m/s; the running speed of the normal running state is 0.4 m/s-0.6 m/s; the running speed of the high-speed running state is 0.7 m/s-0.8 m/s.
3. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the image acquisition process of the two monitored areas corresponding to the same monitoring camera comprises the following steps: and performing mask processing on the image shot by the monitoring camera, removing the background part outside the conveyer belt in the image, and acquiring two monitored area images.
4. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the standard deviation threshold alpha has a value of 40-60.
5. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the value method of the first brightness threshold value beta is as follows: and in 24 continuous hours, acquiring an image of the monitored area under the condition of no package every other hour, and taking the maximum saturation channel brightness average value in each acquired image to be added with 5-15 as a first brightness threshold value beta.
6. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the second brightness threshold epsilon in the step 3-1 is obtained by the following method: and in 24 continuous hours, acquiring images of the monitored area under the condition that a busy level is at a first level every preset time period, and taking the maximum value in the brightness average value of the gray level images corresponding to the images as a second brightness threshold epsilon.
7. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the process of image brightness correction in step 3-2 is as follows:
L=L0+LS
Wherein, L 0 and L are respectively the brightness values before and after correction of the same pixel point in the gray scale image; l S is a brightness correction value, the expression is ；To correct the average brightness of the front gray map.
8. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the multi-threshold binarization process in step 3-2 is as follows: and changing the gray values of the pixel points with gray values in the interval [80,120] U [200,210] U [235,245] in the gray map subjected to image brightness correction and Gaussian filtering into black, and changing the gray values of the rest pixel points into white.
9. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: the process of sharpness evaluation is:
(1) Contour detection: detecting contours in the image using an edge detection algorithm;
(2) The outline is simplified;
(3) Line analysis: calculating a definition comprehensive evaluation index C; the expression is as follows:
C= wlength·length+ wdirection·direction+ wdensity· density
wherein w length、wdirection and w density represent weights of line length, direction and density, respectively; length is the average length of all lines in the gray scale map; direction is the average value of angle deviation values of angles of all lines in the gray level diagram and the vertical direction; the density is a line density index, and the value of the density index is the average value of the length area ratios of all the profiles; the length area of a contour is the ratio of the sum of all line lengths contained in the contour to the contour area.
10. The dynamic control method for the logistics warehouse conveyor line according to claim 1, wherein: in the third step, the value of the definition threshold T1 is 200-400; the third brightness threshold T2 has a value of 150 to 170.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368038.8A CN118025762B (en) | 2024-03-28 | 2024-03-28 | Dynamic control method for logistics warehouse conveying line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410368038.8A CN118025762B (en) | 2024-03-28 | 2024-03-28 | Dynamic control method for logistics warehouse conveying line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118025762A CN118025762A (en) | 2024-05-14 |
| CN118025762B true CN118025762B (en) | 2024-09-06 |
Family
ID=91000699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410368038.8A Active CN118025762B (en) | 2024-03-28 | 2024-03-28 | Dynamic control method for logistics warehouse conveying line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118025762B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651855A (en) * | 2016-12-30 | 2017-05-10 | 国网山东省电力公司济宁供电公司 | Image monitoring and shooting method for automatic identification and alarming of hidden troubles of power transmission line channel |
| CN109715528A (en) * | 2017-04-06 | 2019-05-03 | 新日铁住金系统集成株式会社 | Information processing unit, information processing method, program and recording medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2666315B1 (en) * | 1990-09-04 | 1992-12-11 | France Etat | DEVICE FOR CONTROLLING AND REGULARIZING THE SPACING OF PARCELS, PACKAGES OR THE LIKE, PARTICULARLY POSTAL PARCELS. |
| JP6903922B2 (en) * | 2017-01-18 | 2021-07-14 | 横浜ゴム株式会社 | Conveyor belt monitoring system |
| CN115924492A (en) * | 2021-08-16 | 2023-04-07 | 山东新北洋信息技术股份有限公司 | Package separation method and apparatus |
| CN113651061B (en) * | 2021-08-18 | 2023-04-14 | 上海德启信息科技有限公司 | A monitoring method and monitoring system for logistics flow status |
-
2024
- 2024-03-28 CN CN202410368038.8A patent/CN118025762B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651855A (en) * | 2016-12-30 | 2017-05-10 | 国网山东省电力公司济宁供电公司 | Image monitoring and shooting method for automatic identification and alarming of hidden troubles of power transmission line channel |
| CN109715528A (en) * | 2017-04-06 | 2019-05-03 | 新日铁住金系统集成株式会社 | Information processing unit, information processing method, program and recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118025762A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814678B (en) | Method and system for identifying coal flow in conveyor belt based on video monitoring | |
| CN111402247B (en) | Machine vision-based method for detecting defects of suspension clamp on power transmission line | |
| Bulanon et al. | Development of a real-time machine vision system for the apple harvesting robot | |
| CN105466950A (en) | Bamboo dice online detection method and system based on vision | |
| CN106384117A (en) | Vehicle color recognition method and device | |
| CN107976447A (en) | A kind of accessory detection method and system based on machine vision | |
| CN112837313A (en) | A method for image segmentation of foreign objects in transmission lines | |
| CN111842216A (en) | Agricultural product quality detection automatic sorting management system based on machine vision | |
| CN116524196B (en) | Intelligent power transmission line detection system based on image recognition technology | |
| CN118025762B (en) | Dynamic control method for logistics warehouse conveying line | |
| CN119574563A (en) | A method and system for detecting ribbon defects based on artificial intelligence | |
| CN113569880B (en) | Quick primary separation system and primary separation method for naturally curled tobacco leaves after baking | |
| CN117351021B (en) | Intelligent detection method for production quality of photovoltaic connecting wire | |
| CN112419431A (en) | Method and system for detecting product color | |
| CN112489018A (en) | Intelligent power line inspection method and inspection line | |
| JPH0520426A (en) | Fruit hue judgement device using neural network | |
| CN111402189A (en) | Video image color cast detection device and method | |
| CN115063793A (en) | Restaurant self-service charging method based on dish color identification and management | |
| CN107552415A (en) | A kind of orange petal method for sorting applied to orange petal sorter | |
| CN116883370B (en) | Agricultural product appearance quality detecting system | |
| CN111182698B (en) | Control method and control system for automatically adjusting illumination brightness of material | |
| JPH08247962A (en) | Color filter defect detection method and defect detection device, and panel display defect detection method and defect detection device | |
| CN114472203B (en) | Sorting method and device thereof | |
| CN113255658B (en) | Medium authentication method and device, electronic equipment and storage medium | |
| CN118823616B (en) | Multi-model cascade power transmission line defect identification false alarm rate optimization method and system |
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 |