CN111931575A - Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration - Google Patents
Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration Download PDFInfo
- Publication number
- CN111931575A CN111931575A CN202010645129.3A CN202010645129A CN111931575A CN 111931575 A CN111931575 A CN 111931575A CN 202010645129 A CN202010645129 A CN 202010645129A CN 111931575 A CN111931575 A CN 111931575A
- Authority
- CN
- China
- Prior art keywords
- tracking
- line segment
- mixing drum
- steering
- classifier
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000010354 integration Effects 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000003756 stirring Methods 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000009432 framing Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 239000002689 soil Substances 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention designs a method for detecting and tracking the steering of a mixing drum of a concrete mixer truck based on classifier integration. The method comprises the steps of detecting and tracking a running video stream of a stirring barrel, detecting the characteristics of the stirring barrel by utilizing three detection algorithms of linear detection, angular point detection and contour detection according to the inherent characteristics of the stirring barrel, marking the characteristics and a characteristic central point, judging the running direction of the stirring barrel through the displacement of the central point in a sequence image, and only ensuring the tracking accuracy difficultly.
Description
Technical Field
The invention relates to the field of image processing, target detection and target tracking, and particularly designs a method for detecting and tracking the steering of a mixing tank of a concrete mixer truck based on classifier integration.
Background
The traditional image detection and tracking algorithm generally adopts a single classifier for detection and tracking, however, the acquired video data is easily interfered by external factors such as light, sludge and the like, and the sensitivities of different classifiers to different interferences are different. Under the interference factors, a single classifier often gives wrong judgment results due to the interference, the accuracy and the reliability are difficult to guarantee, and the method has great influence on practical application such as detection, tracking and the like.
In the process of researching and analyzing relevant contents and problems of machine learning, ensemble learning is one of key components of the study, and in the past, research fields are more systematically and comprehensively researched around ensemble learning. The method reasonably utilizes various classification algorithms, can obtain various base classifiers, combines the base classifiers by various means on the basis, and finally constructs the integrated classifier. The classifier has more outstanding performance compared with a single classifier. Further, the basic measurement of the integrated method idea can be concluded and summarized, the basic measurement is used for calling a part of algorithm generation base classifiers, and in addition, corresponding strategies are applied according to actual needs, and finally the base classifiers are smoothly combined.
A concrete mixer is a machine with blades and a shaft rotating in a barrel or a groove to mix cement, gravel aggregate and water and prepare a concrete mixture. In practical application scenarios, the materials in the mixing tank often face a series of risks. For example, drivers may accidentally operate in a transportation way, which results in raw material theft; after the concrete mixer truck arrives at a construction site, the mixing tank enters an unplanned discharging mode due to reasons such as misoperation and the like, so that concrete is released accidentally; the mixing drum stops due to operation or mechanical failure, so that raw materials are solidified in the drum and are difficult to clean, and even the mixing drum is scrapped. These risks are difficult to control using conventional means and therefore monitoring of the mixing drum is essential, but how to control such risks out of the traditional framework is a big research challenge.
Disclosure of Invention
The invention designs a method for detecting and tracking the steering of a mixing drum of a concrete mixer truck based on classifier integration. The method is used for solving the problems that the detection and tracking of the steering of the mixing drum of the concrete mixer truck by the conventional framework in the industry are unreliable, the precision is low, the real-time monitoring efficiency is low and the like.
Different from the existing treatment method, the invention has the beneficial effects that: the traditional frame adopts the mode of single classifier to agitator detection and tracking process, and its tracking result is reliable inadequately, produces great tracking error easily. Secondly, when the feature is lost, the feature of the single classifier cannot be detected and tracked, so that the steering result cannot be obtained, and the tracking precision of the traditional frame is low. According to the invention, on the premise of not increasing extra hardware requirements, the influence of feature loss on detection and tracking is considered in sorting, and meanwhile, the steering of the current frame is predicted according to the probability condition of the steering of the previous frame, so that the tracking precision is effectively improved.
Drawings
FIG. 1 is a schematic view of a line fit according to the present invention; FIG. 2 is a schematic diagram of the present invention using cluster feature corners to extract cluster center points; fig. 3 is a schematic diagram of extracting a maximum profile of a mixer drum pattern according to the present invention, and fig. 4 is a schematic diagram of a technical scheme of a method for detecting and tracking a mixer drum steering of a concrete mixer truck based on classifier integration according to the present invention.
Detailed Description
1. A method for detecting and tracking the steering direction of a mixing tank of a concrete mixer truck based on classifier integration is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that a mixing drum of the concrete mixer operates to collect a video data set, a video image of the mixing drum in operation is collected, areas except the mixing drum are removed as far as possible in the video collection process, a data source for detecting and tracking is screened out, then an area of interest is selected, and image preprocessing operation is carried out;
step two: detecting the characteristics of the mixing tank, namely performing linear detection, angular point detection and contour detection on the data set acquired in the step one, marking the detected characteristics, and extracting the central points of the corresponding characteristics;
step three: tracking the characteristics of the mixing drum, tracking the characteristics of the mixing drum according to the characteristic central point obtained in the step two by comparing the change of the characteristic position central point of the sequence image to obtain a result, and preliminarily judging the steering of the mixing drum;
step four: predicting a tracking result and integrating the tracking result by using a classifier, giving a predicted value to an initial image, calculating the size of the predicted value of each frame of image, judging a base classifier tracking result according to the predicted value, voting the predicted tracking result by adopting a voting method, and judging the final steering of the mixing tank;
2. the method for detecting and tracking the steering of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the method for acquiring the running video data set of the mixing drum of the concrete mixer truck in the first step comprises the following steps;
the method comprises the following steps: firstly, simulating a concrete mixer agitator operation video by using the existing tool, or automatically acquiring a construction site video to perform picture framing extraction;
step two: then manually setting an interested region, or automatically selecting the interested region by using the existing method, wherein the interested region requires the feature region which maximally contains the stirring barrel, and simultaneously excludes the part outside the feature region so as to avoid the interference on the image feature detection process;
step three: finally, image preprocessing operation is executed, and the image preprocessing process can be carried out according to common image processing methods, such as graying, binarization processing and the like; or the image is smoother by using a morphological operation method, and the influence of tiny noise points (such as mud points stuck on a stirring barrel) in the image on the detection process is eliminated; or the image quality is improved by using a deep learning related algorithm.
3. The method for detecting and tracking the steering of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the characteristic detection of the mixing drum in the second step comprises the following steps:
the method comprises the following steps: the line segment characteristics of the stirring barrel are extracted and marked through a line detection algorithm, in order to accurately extract the line segment characteristics on the stirring barrel, the angle of the detected line segment needs to be limited, and the angle of the real line segment is maximally met. In addition, if a line segment with similar position or ductility tendency is encountered, the line segment needs to be fitted, the distance between the center points of the two line segments is set to be less than d, and the fitting operation is performed on the line segment, wherein the position coordinate (x) of the center point M ism，ym) The calculation formula of (2) is as follows:
wherein (x)i，yi) (i ═ 1, 2.., N) denotes the coordinates of the left end point of the detected line segment, (x ═ yj，yj) (j ═ 1, 2.. multidot.n) represents the coordinates of the right end point of the detection line segment, and then the distance of the center point of the line segment to be fitted is calculated, and the distance calculation formula is as follows;
wherein (x)i，yi) (i ═ 1, 2.. times, m) denotes the coordinates of the center point at which the line segment i to be fitted was detected, (x) denotes the coordinates of the center point at which the line segment i to be fitted was detectedj，yj) And (j ═ 1, 2., N) represents the coordinates of the center point of the detected line segment j to be fitted, and d represents the distance from the center point of the line segment to be fitted.
Step two: extracting and marking the corner features of the intensive pattern area of the stirring barrel by using a corner detection algorithm, clustering the corners into clusters by using a clustering method in order to avoid interference of the interference corners, discarding points far away from the center of the cluster, and summing and averaging the central points by using a formula (1) if more cluster centers exist;
step three: extracting and marking partial pattern contours of the stirring barrel by using a contour detection algorithm, wherein the algorithm can detect a plurality of contours with different sizes, and the small contours belonging to one part of the pattern contours are combined into a contour closest to the pattern features on the stirring barrel, and the calculation formula of the contour central point is as follows;
wherein (x)a，ya)，(xb，yb)，(xc，yc) And (x)d，yd) Position coordinates (x) representing four corners of the outline, respectivelym，ym) (m ═ 1, 2., N) represents a single contour center point coordinate position, and finally all the contour center point coordinates meeting the conditions are collected, and the calculation formula is as follows:
4. the method for detecting and tracking the steering direction of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the characteristic tracking of the mixing drum in the third step comprises the following steps:
the method comprises the following steps: positioning by using the central point extracted by the detection algorithm, taking the coordinate point of the image, and comparing the coordinates of the characteristic central point detected on the adjacent images of the continuous frames;
step two: comparing the characteristic center points, calculating the characteristic center point p of the current frame by using the x axis or the y axis as a standardc(xc，yc) And the feature central point p of the previous framec-1(xc-1，yc-1) The coordinate difference in the x-axis or y-axis is used to track the feature, and the calculation formula is as follows:
5. the method for detecting and tracking the steering direction of the mixing tank of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the step four of tracking result prediction and classifier integration is used, and comprises the following steps:
the method comprises the following steps: in the process of detecting and tracking single characteristics, the characteristics cannot be detected or the tracking result is wrong, the prediction method is used for setting a predicted value for the tracking result of each frame and judging the steering of the current frame according to the predicted value of the previous steering;
the calculation mode of the prediction method is as follows:
wherein threshold represents a threshold (probability) for judging drum turning, the default value is 0.5, initial predicted values of clockwise and counterclockwise are 0.5, p1 represents a predicted value of clockwise of the previous frame, p2 represents a predicted value of counterclockwise of the previous frame, if the tracking result before predicting the current frame is 1 (i.e. clockwise), p1 increases at a probability of each k, p2 decreases at a probability of each k, and conversely, when the tracking result is 0 (i.e. counterclockwise), p1 decreases at a probability of each k, and p2 increases at a probability of each k. Typically k takes the empirical value of 0.1. The final steering is determined by the result calculated by the prediction method;
step two: each detection method can be regarded as a classifier, and the three classifiers are integrated by adopting a voting method because the rotation direction of the drum of the soil mixing and stirring truck is judged to be not met by a single classifier; the voting method can adopt a simple majority voting method or a weighted voting method, and the specific calculation mode is as follows;
a) let basic classifier hi(i＝1，2，3)，CjIs a steering judgment flag, hi(x) Is hiAt the turning judgment mark CjThe final result H (x) of the simple majority voting method can be expressed as:
b) let wiIs hi(x) Weight of (1), usually wi≥0，
The final result of the weighted voting method, H (x), can be expressed as:
i.e. the mark predicted to have the most votes, and randomly selecting one of the marks if a plurality of marks have the highest votes at the same time. And voting the tracking result by a voting method to obtain more accurate steering judgment of the stirring barrel.
The invention comprises the technologies of a line detection algorithm, an angular point detection algorithm, a contour detection algorithm, a clustering algorithm, morphological operation and the like.
The algorithm described above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method for detecting and tracking the steering direction of a mixing tank of a concrete mixer truck based on classifier integration is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that a mixing drum of the concrete mixer operates to collect a video data set, a video image of the mixing drum in operation is collected, areas except the mixing drum are removed as far as possible in the video collection process, a data source for detecting and tracking is screened out, then an area of interest is selected, and image preprocessing operation is carried out;
step two: detecting the characteristics of the mixing tank, namely performing linear detection, angular point detection and contour detection on the data set acquired in the step one, marking the detected characteristics, and extracting the central points of the corresponding characteristics;
step three: tracking the characteristics of the mixing drum, tracking the characteristics of the mixing drum according to the characteristic central point obtained in the step two by comparing the change of the characteristic position central point of the sequence image to obtain a result, and preliminarily judging the steering of the mixing drum;
step four: and predicting the tracking result and integrating by using a classifier, giving a predicted value to the initial image, calculating the size of the predicted value of each frame of image, judging the tracking result of the base classifier according to the predicted value, voting the predicted tracking result by adopting a voting method, and judging the final steering of the mixing tank.
2. The method for detecting and tracking the steering direction of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the method for acquiring the video data set of the operation of the mixing drum of the concrete mixer truck in the first step comprises the following steps;
the method comprises the following steps: firstly, simulating a concrete mixer agitator operation video by using the existing tool, or automatically acquiring a construction site video to perform picture framing extraction;
step two: then manually setting an interested region, or automatically selecting the interested region by using the existing method, wherein the interested region requires the feature region which maximally contains the stirring barrel, and simultaneously excludes the part outside the feature region so as to avoid the interference on the image feature detection process;
step three: finally, image preprocessing operation is executed, and the image preprocessing process can be carried out according to common image processing methods, such as graying, binarization processing and the like; or the image is smoother by using a morphological operation method, and the influence of tiny noise points (such as mud points stuck on a stirring barrel) in the image on the detection process is eliminated; or the image quality is improved by using a deep learning related algorithm.
3. The method for detecting and tracking the steering direction of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the mixing drum characteristic detection in the second step comprises the following steps:
the method comprises the following steps: extracting and marking line segment characteristics of the stirring barrel through a straight line detection algorithm, and accurately extracting and stirringThe line segment characteristics on the barrel need to limit the angle of the detected line segment, and the angle which accords with the real line segment is maximized. In addition, if a line segment with similar position or ductility tendency is encountered, the line segment needs to be fitted, the distance between the center points of the two line segments is set to be less than d, and the fitting operation is performed on the line segment, wherein the position coordinate (x) of the center point M ism，ym) The calculation formula of (2) is as follows:
wherein (x)i，yi) (i ═ 1, 2.., N) denotes the coordinates of the left end point of the detected line segment, (x ═ yj，yj) (j ═ 1, 2.. multidot.n) represents the coordinates of the right end point of the detection line segment, and then the distance of the center point of the line segment to be fitted is calculated, and the distance calculation formula is as follows;
wherein (x)i，yi) (i ═ 1, 2.. times, m) denotes the coordinates of the center point at which the line segment i to be fitted was detected, (x) denotes the coordinates of the center point at which the line segment i to be fitted was detectedj，yj) And (j ═ 1, 2., N) represents the coordinates of the center point of the detected line segment j to be fitted, and d represents the distance from the center point of the line segment to be fitted.
Step two: extracting and marking the corner features of the intensive pattern area of the stirring barrel by using a corner detection algorithm, clustering the corners into clusters by using a clustering method in order to avoid interference of the interference corners, discarding points far away from the center of the cluster, and summing and averaging the central points by using a formula (1) if more cluster centers exist;
step three: extracting and marking partial pattern contours of the stirring barrel by using a contour detection algorithm, wherein the algorithm can detect a plurality of contours with different sizes, and the small contours belonging to one part of the pattern contours are combined into a contour closest to the pattern features on the stirring barrel, and the calculation formula of the contour central point is as follows;
wherein (x)a，ya)，(xb，yb)，(xc，yc) And (x)d，yd) Position coordinates (x) representing four corners of the outline, respectivelym，ym) (m ═ 1, 2., N) represents a single contour center point coordinate position, and finally all the contour center point coordinates meeting the conditions are collected, and the calculation formula is as follows:
4. the method for detecting and tracking the steering direction of the mixing drum of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the tracking of the characteristics of the mixing drum in the third step comprises the following steps:
the method comprises the following steps: positioning by using the central point extracted by the detection algorithm, taking the coordinate point of the image, and comparing the coordinates of the characteristic central point detected on the adjacent images of the continuous frames;
step two: comparing the characteristic center points, calculating the characteristic center point p of the current frame by using the x axis or the y axis as a standardc(xc，yc) And the feature central point p of the previous framec-1(xc-1，yc-1) The coordinate difference in the x-axis or y-axis is used to track the feature, and the calculation formula is as follows:
5. the method for detecting and tracking the steering direction of the mixing tank of the concrete mixer truck based on the classifier integration as claimed in claim 1, wherein the step four tracking result prediction and use of the classifier integration comprises the following steps:
the method comprises the following steps: in the process of detecting and tracking single characteristics, the characteristics cannot be detected or the tracking result is wrong, the prediction method is used for setting a predicted value for the tracking result of each frame and judging the steering of the current frame according to the predicted value of the previous steering;
the calculation mode of the prediction method is as follows:
wherein threshold represents a threshold (probability) for judging drum turning, the default value is 0.5, initial predicted values of clockwise and counterclockwise are 0.5, p1 represents a predicted value of clockwise of the previous frame, p2 represents a predicted value of counterclockwise of the previous frame, if the tracking result before predicting the current frame is 1 (i.e. clockwise), p1 increases at a probability of each k, p2 decreases at a probability of each k, and conversely, when the tracking result is 0 (i.e. counterclockwise), p1 decreases at a probability of each k, and p2 increases at a probability of each k. Typically k takes the empirical value of 0.1. The final steering is determined by the result calculated by the prediction method;
step two: each detection method can be regarded as a classifier, and the three classifiers are integrated by adopting a voting method because the rotation direction of the drum of the soil mixing and stirring truck is judged to be not met by a single classifier; the voting method can adopt a simple majority voting method or a weighted voting method, and the specific calculation mode is as follows;
a) let basic classifier hi(i＝1，2，3)，CjIs a steering judgment flag, hi(x) Is hiAt the turning judgment mark CjThe final result H (x) of the simple majority voting method can be expressed as:
b) let wiIs hi(x) Weight of (1), usually wi≥0，
The final result of the weighted voting method, H (x), can be expressed as:
i.e. the mark predicted to have the most votes, and randomly selecting one of the marks if a plurality of marks have the highest votes at the same time. And voting the tracking result by a voting method to obtain more accurate steering judgment of the stirring barrel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010645129.3A CN111931575A (en) | 2020-07-01 | 2020-07-01 | Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010645129.3A CN111931575A (en) | 2020-07-01 | 2020-07-01 | Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931575A true CN111931575A (en) | 2020-11-13 |
Family
ID=73312739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010645129.3A Pending CN111931575A (en) | 2020-07-01 | 2020-07-01 | Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931575A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785639A (en) * | 2021-01-06 | 2021-05-11 | 鞍钢矿业***有限公司 | Video analysis-based method for metering bagged materials into and out of warehouse |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018095082A1 (en) * | 2016-11-28 | 2018-05-31 | 江苏东大金智信息***有限公司 | Rapid detection method for moving target in video monitoring |
| CN109215084A (en) * | 2018-08-06 | 2019-01-15 | 杭州雄迈集成电路技术有限公司 | A method of for distortion correction location of the core |
| CN109719849A (en) * | 2019-01-17 | 2019-05-07 | 北汽福田汽车股份有限公司 | Agitating lorry tank body turns to detection system and method |
-
2020
- 2020-07-01 CN CN202010645129.3A patent/CN111931575A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018095082A1 (en) * | 2016-11-28 | 2018-05-31 | 江苏东大金智信息***有限公司 | Rapid detection method for moving target in video monitoring |
| CN109215084A (en) * | 2018-08-06 | 2019-01-15 | 杭州雄迈集成电路技术有限公司 | A method of for distortion correction location of the core |
| CN109719849A (en) * | 2019-01-17 | 2019-05-07 | 北汽福田汽车股份有限公司 | Agitating lorry tank body turns to detection system and method |
Non-Patent Citations (1)
| Title |
|---|
| 谭继安;林德丰;梁建胜;: "基于混合光流的非刚体目标追踪***", 控制工程, no. 05 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785639A (en) * | 2021-01-06 | 2021-05-11 | 鞍钢矿业***有限公司 | Video analysis-based method for metering bagged materials into and out of warehouse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akagic et al. | Pavement crack detection using Otsu thresholding for image segmentation | |
| CN108805904B (en) | Moving ship detection and tracking method based on satellite sequence image | |
| US8180158B2 (en) | Image processing device and image processing method for detecting a specific shape from an image | |
| CN102184550B (en) | Mobile platform ground movement object detection method | |
| EP1780675B1 (en) | Object detector | |
| Yu et al. | Automated detection of urban road manhole covers using mobile laser scanning data | |
| CN112419297A (en) | Bolt looseness detection method, device, equipment and storage medium | |
| Lin et al. | Temporal image analytics for abnormal construction activity identification | |
| CN108846402B (en) | Automatic extraction method for terrace field ridges based on multi-source data | |
| CN109117702B (en) | Target vehicle detection, tracking and counting method and system | |
| Gui et al. | Automated defect detection and visualization for the robotic airport runway inspection | |
| CN110519566B (en) | Belt motion state monitoring method based on video processing | |
| Li et al. | A lane marking detection and tracking algorithm based on sub-regions | |
| JP2021527256A (en) | Systems and methods for detecting and classifying patterns in images with a vision system | |
| Yang et al. | Vision-based crane tracking for understanding construction activity | |
| CN109410248B (en) | Flotation froth motion characteristic extraction method based on r-K algorithm | |
| CN107516315B (en) | Tunneling machine slag tapping monitoring method based on machine vision | |
| CN111931575A (en) | Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration | |
| Xu et al. | A defect inspection for explosive cartridge using an improved visual attention and image-weighted eigenvalue | |
| CN110414425A (en) | A kind of adaptive method for detecting lane lines of width and system based on vanishing point detection | |
| CN109785318B (en) | Remote sensing image change detection method based on facial line primitive association constraint | |
| CN112308842B (en) | Positioning core automatic extraction method based on printed matter image | |
| CN114299247A (en) | Rapid detection and problem troubleshooting method for road traffic sign lines | |
| KR100603027B1 (en) | A 3-D display method of materials laid under ground | |
| Zhuang et al. | Visual detection of construction and demolition waste using multi-sensor fusion |
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 | ||
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Zhao Yuming Document name: Deemed withdrawal notice |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201113 |