CN104657975B - A kind of method of video image travers Disturbance Detection - Google Patents
A kind of method of video image travers Disturbance Detection Download PDFInfo
- Publication number
- CN104657975B CN104657975B CN201410202825.1A CN201410202825A CN104657975B CN 104657975 B CN104657975 B CN 104657975B CN 201410202825 A CN201410202825 A CN 201410202825A CN 104657975 B CN104657975 B CN 104657975B
- Authority
- CN
- China
- Prior art keywords
- video
- disturbance
- image
- mrow
- horizontal stripe
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000533950 Leucojum Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
本发明提供一种视频横向条纹扰动检测的方法，涉及视频图像处理技术领域。所述方法包括：输入待检测视频图像；获得差分图像并过滤；在时间域中检测视频横向条纹扰动；在空间域中检测视频横向条纹扰动；如果在时间域中和空间域中有任意一步判断出视频有条纹扰动，则判定视频中含有视频横向条纹扰动，反之则判断视频中不含有视频横向条纹扰动。
The invention provides a video horizontal stripe disturbance detection method, which relates to the technical field of video image processing. The method includes: inputting a video image to be detected; obtaining a differential image and filtering it; detecting the horizontal stripe disturbance of the video in the time domain; detecting the horizontal stripe disturbance of the video in the space domain; If there is stripe disturbance in the video, it is determined that the video contains video horizontal stripe disturbance, otherwise, it is judged that the video does not contain video horizontal stripe disturbance.
Description
技术领域technical field
本发明属于视频图像异常检测技术领域，尤其是指一种视频图像横向条纹扰动检测的方法。The invention belongs to the technical field of video image anomaly detection, in particular to a method for detecting video image transverse stripe disturbances.
背景技术Background technique
随着视频监控系统在社会防控领域应用的规模化，视频监控录像为执法机关在案件侦破，紧急事态处置等方面发挥了巨大作用。然而由于后期建设导致监控设备周围环境发生变化或者监控设备自身使用周期寿命的影响，部分监控设备采集的视频图像出现了各种视频扰动，常见的有视频模糊、视频过暗、视频过亮、视频颜色异常、雪花等视频异常。对于视频质量影响较大的一种扰动便是视频横向条纹扰动。这种视频横向条纹扰动具有以下特征：With the large-scale application of video surveillance systems in the field of social prevention and control, video surveillance recordings have played a huge role for law enforcement agencies in case detection and emergency handling. However, due to the changes in the surrounding environment of the monitoring equipment caused by the later construction or the influence of the service life of the monitoring equipment itself, various video disturbances appear in the video images collected by some monitoring equipment, such as blurred video, too dark video, too bright video, and Abnormal colors, snowflakes and other video abnormalities. A disturbance that has a greater impact on video quality is video horizontal stripe disturbance. This video horizontal stripe disturbance has the following characteristics:
1)条纹横向贯穿屏幕、纵向具有一定的高度；1) The stripes run through the screen horizontally and have a certain height vertically;
2)条纹一般在垂直方向做匀速移动；2) The stripes generally move at a constant speed in the vertical direction;
3)条纹以视频图像纵向中轴线为轴，左右对称；3) The stripes take the longitudinal central axis of the video image as the axis and are symmetrical left and right;
4)条纹的颜色为白色或黑色4) The color of the stripes is white or black
这种视频横向条纹扰动会影响获取感兴趣区域目标的有效信息。This kind of video horizontal stripe disturbance will affect the acquisition of effective information of the target in the region of interest.
目前视频横条纹扰动噪声检测方法存在的问题是：现有的方法主要针对以大量贯穿整幅图片、明暗交替出现为特征的细条纹，其利用条纹的周期性，采用傅里叶变换方法对其进行检测。然而视频横向条纹扰动并不会大量出现在视频中，没有满足傅里叶变换方法检测条纹需要的周期性。The problem existing in the current video horizontal stripe disturbance noise detection method is that the existing method is mainly aimed at a large number of thin stripes that run through the whole picture and appear alternately between light and dark. to test. However, video horizontal stripe disturbances do not appear in large quantities in the video, and there is no periodicity that meets the requirements of the Fourier transform method to detect stripes.
发明内容Contents of the invention
为了克服现有技术存在的缺点和不足，本发明利用视频条纹扰动的如下特征：In order to overcome the shortcoming and the deficiency that prior art exists, the present invention utilizes the following characteristics of video fringe disturbance:
1)条纹横向贯穿屏幕、纵向具有一定的高度；1) The stripes run through the screen horizontally and have a certain height vertically;
2)条纹一般在垂直方向做匀速移动；2) The stripes generally move at a constant speed in the vertical direction;
3)条纹以视频图像纵向中轴线为轴，左右对称；3) The stripes take the longitudinal central axis of the video image as the axis and are symmetrical left and right;
4)条纹的颜色为白色或黑色4) The color of the stripes is white or black
提供了一种可靠、快速的视频横向条纹扰动检测的方法。A reliable and fast method for video horizontal stripe disturbance detection is provided.
一种视频横向条纹扰动检测的方法，它包括如下步骤：A method for video horizontal stripe disturbance detection, comprising the steps of:
步骤一，输入视频流：输入待检测视频数据，帧图像分辨率为M×N；Step 1, input video stream: input video data to be detected, frame image resolution is M×N;
步骤二，运动性检测，提取条纹扰动信息：利用部分条纹具有运动的特征，将前后帧图像fn和fn+1做帧差，即将fn和fn+1按空间位置相对应的像素取差绝对值，得到提取条纹信息的差分图像gn；Step 2, motion detection, extracting fringe disturbance information: using part of the fringes to have motion characteristics, make a frame difference between f n and f n+ 1 of the front and rear frame images, that is, the pixels corresponding to f n and f n+1 according to the spatial position Take the absolute value of the difference to obtain the difference image g n for extracting fringe information;
步骤三，利用条纹的空间对称性，对差分图像gn对称性滤波，过滤图像gn中的伪条纹区域，得到图像g′n；Step 3, using the spatial symmetry of stripes, symmetrically filtering the difference image g n , filtering the pseudo stripe area in the image g n , and obtaining the image g′ n ;
步骤四，在时间域中，对g′n投影筛选特征数据，并初次判断视频横向条纹扰动是否存在；Step 4, in the time domain, filter the feature data for g' n projection, and judge whether the horizontal stripe disturbance of the video exists for the first time;
步骤五，在空间域中，对图像fn提取特征数据，再次判断视频横向条纹扰动是否存在；Step 5, in the spatial domain, extract feature data from the image f n , and judge again whether the horizontal stripe disturbance of the video exists;
步骤六，整合步骤四、五中的算法结果，完成对视频横向条纹扰动的最终判定：若步骤四、五中皆判定视频无条纹扰动，则判定视频横向条纹扰动不存在，若步骤四中判定视频横向条纹扰动存在，则根据步骤五判定条纹颜色状态，其中步骤四、五中任意一步判定结果为存在视频条纹扰动，则算法结果为视频存在条纹扰动。Step 6: Integrate the algorithm results in steps 4 and 5 to complete the final determination of the video horizontal stripe disturbance: if it is determined in steps 4 and 5 that the video has no stripe disturbance, then it is determined that the video horizontal stripe disturbance does not exist; if it is determined in step 4 If there is horizontal stripe disturbance in the video, the color state of the stripe is judged according to step 5, and the judgment result in any step 4 and 5 is that there is video stripe disturbance, and the algorithm result is that there is stripe disturbance in the video.
步骤三中，所述的过滤差分图像gn中的伪条纹区域方法为：以差分图像的垂直方向中线x0＝N/2为对称轴，如果|gn(x0-k，y)-gn(x0+k，y)|＞T0，则令g′n(x0-k，y)＝0，g′n(x0+k，y)＝0，得到过滤了伪条纹区域的图像g′n，其中k∈[1，N/2]，T0为判断阈值。In step 3, the method for filtering the pseudo-stripe region in the differential image g n is: take the vertical centerline x 0 =N/2 of the differential image as the axis of symmetry, if |g n (x 0 -k, y)- g n (x 0 +k, y)|>T 0 , then let g′ n (x 0 -k, y)=0, g′ n (x 0 +k, y)=0, get filtered pseudo-stripes The image g′ n of the region, where k∈[1, N/2], T 0 is the judgment threshold.
步骤四中，所述的时间域中判定视频横向条纹扰动是否存在的方法为：计算g′n的平均幅值m、最大行均值和最大列均值由于条纹具有运动的特性，相邻帧图像的帧差法可以过滤图像gn的背景信息，从而得到条纹扰动信息，所以求得的若图像g′n中的上述统计数据如果同时满足若图像g′n中的上述统计数据如果同时满足：In step 4, the method for determining whether the horizontal stripe disturbance of the video exists in the time domain is: calculate the average amplitude m of g' n , the maximum row average value and the largest column mean Because the stripes have the characteristic of movement, the frame difference method of adjacent frame images can filter the background information of the image g n , thereby obtaining the stripe disturbance information, so if the above statistical data in the obtained image g′ n satisfies at the same time if the image g If the above statistical data in ′ n are satisfied at the same time:
则判定在时间域中有视频横向条纹扰动，其中T1，T2为判断阈值，其中T1＝20，T2＝3。Then it is determined that there is video horizontal stripe disturbance in the time domain, where T 1 and T 2 are judgment thresholds, where T 1 =20 and T 2 =3.
步骤五中，空间域中判断视频横向条纹扰动是否存在的方法为：由于条纹的颜色特征为白色或黑色，所以条纹扰动对应的区域方差必然很低，均值或接近于0或接近于255，故对图像fn提取行方差以及行均值，并在其中寻找行方差最小值δmin及其对应的行号l1，图像行均值最大值最小值及其分别对应的行号l2、l3，如果条件同时满足：In step 5, the method for judging the existence of video horizontal stripe disturbance in the spatial domain is as follows: Since the color feature of the stripe is white or black, the variance of the area corresponding to the stripe disturbance must be very low, and the mean value is close to 0 or close to 255, so Extract the row variance and row mean value of the image f n , and find the row variance minimum value δ min and its corresponding row number l 1 , and the image row mean value maximum value minimum value and their corresponding line numbers l 2 and l 3 , if the conditions are met at the same time:
(B1)|l1-l2|<T4， (4)(B1)|l 1 -l 2 |<T 4 ，(4)
(C1)δmin<T5， (5)(C1)δ min <T 5 , (5)
则判定在空间域中有黑色视频横向条纹扰动，Then it is determined that there is a black video horizontal stripe disturbance in the spatial domain,
如果条件同时满足：If both conditions are met:
(B2)|l1-l3|<T4， (7)(B2)|l 1 -l 3 |<T 4 ， (7)
(C2)δmin<T5， (8)(C2)δ min <T 5 , (8)
则判定在空间域中有白色视频横向条纹扰动，其中T3＝15，T4＝10，T5＝0.1。Then it is determined that there is white video horizontal stripe disturbance in the space domain, where T 3 =15, T 4 =10, T 5 =0.1.
本发明的有益效果是：本发明的一种视频横向条纹扰动检测的方法，能够有效的结合视频条纹扰动在时间域、空间域的运动特性和颜色特性对条纹进行检测，保证了对运动性条纹信息的有效提取，同时利用条纹的颜色信息兼容检测静止性条纹，实现了对条纹信息的完善提取，满足对视频条纹扰动检测的实时性、准确性的要求。The beneficial effects of the present invention are: a method for detecting video horizontal stripe disturbances of the present invention can effectively detect stripes in combination with the motion characteristics and color characteristics of video stripe disturbances in the time domain and space domain, ensuring the detection of motion stripes. The effective extraction of information and the use of the color information of the stripes to detect static stripes compatibly achieve the perfect extraction of stripe information and meet the requirements for real-time and accuracy of video stripe disturbance detection.
附图说明Description of drawings
图1为本发明在时间域中视频横向条纹扰动检测方法的流程图；Fig. 1 is the flow chart of the present invention in time domain video transverse stripe disturbance detection method;
图2为本发明在空间域中视频横向条纹扰动检测方法的流程图。Fig. 2 is a flow chart of the method for detecting video horizontal stripe disturbance in the spatial domain according to the present invention.
具体实施方式detailed description
本实例给出了一种视频横向条纹扰动检测的方法，根据视频横向条纹扰动具有以下特征：This example gives a method for video horizontal stripe disturbance detection, according to the video horizontal stripe disturbance has the following characteristics:
1)条纹横向贯穿屏幕、纵向具有一定的高度；1) The stripes run through the screen horizontally and have a certain height vertically;
2)条纹一般在垂直方向做匀速移动；2) The stripes generally move at a constant speed in the vertical direction;
3)条纹以视频图像纵向中轴线为轴，左右对称；3) The stripes take the longitudinal central axis of the video image as the axis and are symmetrical left and right;
4)条纹的颜色为白色或黑色4) The color of the stripes is white or black
提供了一种可靠、快速的视频横向条纹扰动检测的方法。A reliable and fast method for video horizontal stripe disturbance detection is provided.
一种视频横向条纹扰动检测的方法，如图1、图2所示，它包括如下步骤：A method for video horizontal stripe disturbance detection, as shown in Figure 1 and Figure 2, it comprises the steps:
步骤一，输入视频流：输入待检测视频数据，帧图像分辨率为M×N；Step 1, input video stream: input video data to be detected, frame image resolution is M×N;
步骤二，运动性检测，提取条纹扰动信息：利用部分条纹具有运动的特征，将前后帧图像fn和fn+1做帧差，即将fn和fn+1按空间位置相对应的像素取差绝对值，得到提取条纹信息的差分图像gn；Step 2, motion detection, extracting fringe disturbance information: using part of the fringes to have motion characteristics, make a frame difference between f n and f n+ 1 of the front and rear frame images, that is, the pixels corresponding to f n and f n+1 according to the spatial position Take the absolute value of the difference to obtain the difference image g n for extracting fringe information;
步骤三，利用条纹的空间对称性，对差分图像gn对称性滤波，过滤图像gn中的伪条纹区域，得到图像g′n；Step 3, using the spatial symmetry of stripes, symmetrically filtering the difference image g n , filtering the pseudo stripe area in the image g n , and obtaining the image g′ n ;
步骤四，在时间域中，对g′n投影筛选特征数据，并初次判断视频横向条纹扰动是否存在；Step 4, in the time domain, filter the feature data for g' n projection, and judge whether the horizontal stripe disturbance of the video exists for the first time;
步骤五，在空间域中，对图像fn提取特征数据，再次判断视频横向条纹扰动是否存在；Step 5, in the spatial domain, extract feature data from the image f n , and judge again whether the horizontal stripe disturbance of the video exists;
步骤六，整合步骤四、五中的算法结果，完成对视频横向条纹扰动的最终判定：若步骤四、五中皆判定视频无条纹扰动，则判定视频横向条纹扰动不存在，若步骤四中判定视频横向条纹扰动存在，则根据步骤五判定条纹颜色状态，其中步骤四、五中任意一步判定结果为存在视频条纹扰动，则算法结果为视频存在条纹扰动。Step 6: Integrate the algorithm results in steps 4 and 5 to complete the final determination of the video horizontal stripe disturbance: if it is determined in steps 4 and 5 that the video has no stripe disturbance, then it is determined that the video horizontal stripe disturbance does not exist; if it is determined in step 4 If there is horizontal stripe disturbance in the video, the color state of the stripe is judged according to step 5, and the judgment result in any step 4 and 5 is that there is video stripe disturbance, and the algorithm result is that there is stripe disturbance in the video.
步骤三中，所述的过滤差分图像gn中的伪条纹区域方法为：以差分图像的垂直方向中线x0＝N/2为对称轴，如果|gn(x0-k，y)-gn(x0+k，y)|>T0，则令g′n(x0-k，y)＝0，g′n(x0+k，y)＝0，得到过滤了伪条纹区域的图像g′n，其中k∈[1，N/2]，T0为判断阈值。In step 3, the method for filtering the pseudo-stripe region in the differential image g n is: take the vertical centerline x 0 =N/2 of the differential image as the axis of symmetry, if |g n (x 0 -k, y)- g n (x 0 +k, y)|>T 0 , then let g′ n (x 0 -k, y)=0, g′ n (x 0 +k, y)=0, get filtered pseudo stripes The image g′ n of the region, where k∈[1, N/2], T 0 is the judgment threshold.
步骤四中，所述的时间域中判定视频横向条纹扰动是否存在的方法为：计算g′n的平均幅值m、最大行均值和最大列均值由于条纹具有运动的特性，相邻帧图像的帧差法可以过滤图像gn的背景信息，从而得到条纹扰动信息，所以求得的若图像g′n中的上述统计数据如果同时满足若图像g′n中的上述统计数据如果同时满足：In step 4, the method for determining whether the horizontal stripe disturbance of the video exists in the time domain is: calculate the average amplitude m of g' n , the maximum row average value and the largest column mean Because the stripes have the characteristic of movement, the frame difference method of adjacent frame images can filter the background information of the image g n , thereby obtaining the stripe disturbance information, so if the above statistical data in the obtained image g′ n satisfies at the same time if the image g If the above statistical data in ′ n are satisfied at the same time:
则判定在时间域中有视频横向条纹扰动，其中T1，T2为判断阈值，其中T1＝20，T2＝3。Then it is determined that there is video horizontal stripe disturbance in the time domain, where T 1 and T 2 are judgment thresholds, where T 1 =20 and T 2 =3.
步骤五中，空间域中判断视频横向条纹扰动是否存在的方法为：由于条纹的颜色特征为白色或黑色，所以条纹扰动对应的区域方差必然很低，均值或接近于0或接近于255，故对图像fn提取行方差以及行均值，并在其中寻找行方差最小值δmin及其对应的行号l1，图像行均值最大值最小值及其分别对应的行号l2、l3，如果条件同时满足：In step 5, the method for judging the existence of video horizontal stripe disturbance in the spatial domain is as follows: Since the color feature of the stripe is white or black, the variance of the area corresponding to the stripe disturbance must be very low, and the mean value is close to 0 or close to 255, so Extract the row variance and row mean value of the image f n , and find the row variance minimum value δ min and its corresponding row number l 1 , and the image row mean value maximum value minimum value and their corresponding line numbers l 2 and l 3 , if the conditions are met at the same time:
(B1)|l1-l2|<T4， (4)(B1)|l 1 -l 2 |<T 4 ，(4)
(C1)δmin<T5， (5)(C1)δ min <T 5 , (5)
则判定在空间域中有黑色视频横向条纹扰动，Then it is determined that there is a black video horizontal stripe disturbance in the spatial domain,
如果条件同时满足：If both conditions are met:
(B2)|l1-l3|<T4， (7)(B2)|l 1 -l 3 |<T 4 ， (7)
(C2)δmin<T5，(8)(C2)δ min <T 5 , (8)
则判定在空间域中有白色视频横向条纹扰动，其中T3＝15，T4＝10，T5＝0.1。Then it is determined that there is white video horizontal stripe disturbance in the space domain, where T 3 =15, T 4 =10, T 5 =0.1.
最后应说明的是：以上所述仅为本发明的优选实施例而已，并不用于限制本发明，尽管按照前述实施例对本发明进行了详细的说明，对于本领域的技术人员来说，依然可以对前述实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。Finally, it should be noted that: the above is only a preferred embodiment of the present invention, and is not intended to limit the present invention. Although the present invention has been described in detail according to the foregoing embodiments, it is still possible for those skilled in the art Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.
以上描述了本发明的基本原理和主要特征以及本发明的优点。本行业技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。The basic principles and main features of the present invention and the advantages of the present invention have been described above. It should be understood by those skilled in the art that the present invention is not limited by the above-mentioned embodiments, and that described in the above-mentioned embodiments and description only illustrates the principle of the present invention, and the present invention also has various aspects without departing from the spirit and scope of the present invention. Variations and improvements all fall within the scope of the claimed invention.
Claims (3)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410202825.1A CN104657975B (en) | 2014-05-13 | 2014-05-13 | A kind of method of video image travers Disturbance Detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410202825.1A CN104657975B (en) | 2014-05-13 | 2014-05-13 | A kind of method of video image travers Disturbance Detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104657975A CN104657975A (en) | 2015-05-27 |
| CN104657975B true CN104657975B (en) | 2017-10-24 |
Family
ID=53249052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410202825.1A Expired - Fee Related CN104657975B (en) | 2014-05-13 | 2014-05-13 | A kind of method of video image travers Disturbance Detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104657975B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105282542B (en) * | 2015-10-21 | 2017-06-30 | 上海熙菱信息技术有限公司 | The detection method and system of abnormal striped in a kind of video image |
| CN106303158B (en) * | 2016-09-30 | 2019-05-21 | 杭州电子科技大学 | A kind of striped method for detecting abnormality in video image |
| CN108921823B (en) * | 2018-06-08 | 2020-12-01 | Oppo广东移动通信有限公司 | Image processing method, apparatus, computer-readable storage medium and electronic device |
| CN113766089B (en) * | 2021-09-18 | 2023-08-18 | 北京百度网讯科技有限公司 | Method, device, electronic device and storage medium for detecting video rolling stripes |
| CN115022564A (en) * | 2022-06-10 | 2022-09-06 | 杭州海康威视数字技术股份有限公司 | a camera |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010052741A1 (en) * | 2008-11-07 | 2010-05-14 | Telecom Italia S.P.A. | Method and system for producing multi-view 3d visual contents |
| CN103093179A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Video strip quantitative calculation method |
| CN103473779A (en) * | 2013-09-22 | 2013-12-25 | 北京智诺英特科技有限公司 | Method and device for detecting stripe interference in image |
-
2014
- 2014-05-13 CN CN201410202825.1A patent/CN104657975B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010052741A1 (en) * | 2008-11-07 | 2010-05-14 | Telecom Italia S.P.A. | Method and system for producing multi-view 3d visual contents |
| CN103093179A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Video strip quantitative calculation method |
| CN103473779A (en) * | 2013-09-22 | 2013-12-25 | 北京智诺英特科技有限公司 | Method and device for detecting stripe interference in image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104657975A (en) | 2015-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110268190B (en) | Underground pipe gallery leakage detection method based on static infrared thermography processing | |
| CN104657975B (en) | A kind of method of video image travers Disturbance Detection | |
| CN104469345B (en) | A kind of video method for diagnosing faults based on image processing | |
| CN103077526B (en) | There is train method for detecting abnormality and the system of depth detection function | |
| CN106303158B (en) | A kind of striped method for detecting abnormality in video image | |
| CN111179279A (en) | Comprehensive flame detection method based on ultraviolet and binocular vision | |
| US20160371827A1 (en) | Method and apparatus for recognizing moving target | |
| CN109087363B (en) | HSV color space-based sewage discharge detection method | |
| EP2743886B1 (en) | System for detecting structured artifacts in video sequences | |
| CN103886598B (en) | A kind of tunnel smog detection means and method based on Computer Vision | |
| CN107705288A (en) | Hazardous gas spillage infrared video detection method under pseudo- target fast-moving strong interferers | |
| CN106599783B (en) | Video occlusion detection method and device | |
| CN102881106A (en) | A forest fire identification system and its identification method based on thermal imaging and video | |
| CN104182983B (en) | Highway monitoring video definition detection method based on corner features | |
| CN104301712A (en) | Monitoring camera shake detection method based on video analysis | |
| CN110458157A (en) | A kind of power cable production process intelligent monitor system | |
| CN102111530B (en) | Mobile object detection device and method | |
| CN104486618A (en) | Video image noise detection method and device | |
| CN109242861A (en) | A kind of monitoring water quality method based on image procossing | |
| JP6214426B2 (en) | Object detection device | |
| CN103473779B (en) | The detection method of stripe interference and device in image | |
| CN105787912A (en) | Classification-based step type edge sub pixel localization method | |
| JP2014007498A (en) | Disaster detection system | |
| CN106408563A (en) | Snow noise detection method based on variation coefficient | |
| CN117710266A (en) | Night road visibility monitoring method based on video image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171024 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |