CN111046797A - Oil pipeline warning method based on personnel and vehicle behavior analysis - Google Patents
Oil pipeline warning method based on personnel and vehicle behavior analysis Download PDFInfo
- Publication number
- CN111046797A CN111046797A CN201911275646.XA CN201911275646A CN111046797A CN 111046797 A CN111046797 A CN 111046797A CN 201911275646 A CN201911275646 A CN 201911275646A CN 111046797 A CN111046797 A CN 111046797A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- training
- detected
- personnel
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The invention provides an oil pipeline warning method based on personnel and vehicle behavior analysis, which comprises the following steps: s1, collecting a sample set used for training the model; processing and training the sample set, and outputting a training model; s2, acquiring an image to be detected, and preprocessing the image to be detected; and S3, processing the image to be detected by using the training model, detecting the positions of the personnel and the vehicles in the image to obtain a detection structure, setting a confidence threshold value of 0.5, and outputting target information with a confidence score larger than 0.5 in the detection result. The invention divides different target behaviors in detail, can give warning prompts to targets in a monitoring area in different degrees aiming at the behaviors, provides basis for working personnel to make countermeasures, can effectively prevent suspicious personnel and vehicles from stealing and extracting petroleum, and prevent heavy vehicles from driving above an oil pipeline and staying for a long time, and avoids the possible accidental damage to the oil pipeline in the construction process of mistakenly entering the warning area by construction vehicles.
Description
Technical Field
The invention belongs to the field of video monitoring, and particularly relates to an oil pipeline warning method based on personnel and vehicle behavior analysis.
Background
In recent years, the speed of oil pipeline construction is increased rapidly in China, and the phenomena of illegal mining, nearby vehicle construction, running of heavy vehicles above a pipeline and the like can be effectively avoided by applying a video monitoring technology in the field of oil pipeline protection. The monitoring method mainly comprises the steps that the warning function of personnel and vehicles in the existing monitoring technology cannot meet the requirements of petroleum pipeline protection, the requirements of the current petroleum pipeline protection not only need to detect the personnel and various vehicles near an oil pipeline, but also need to accurately identify various vehicle types, judge whether the personnel and the vehicles are in the scene or not through continuous video images, and send corresponding warning situations to workers according to different behaviors, so that the purpose of protecting the petroleum pipeline in real time and efficiently is achieved.
Disclosure of Invention
In view of the above, the present invention provides a method for warning an oil pipeline based on analysis of human and vehicle behaviors, which is aimed at overcoming the above-mentioned drawbacks of the prior art.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
an oil pipeline warning method based on personnel and vehicle behavior analysis, comprising:
s1, collecting a sample set used for training the model; processing and training the sample set, and outputting a training model;
s2, acquiring an image to be detected, and preprocessing the image to be detected;
s3, processing the image to be detected by using the training model, detecting the positions of the personnel and the vehicles in the image to obtain a detection structure, setting a confidence threshold value of 0.5, and outputting target information with a confidence score larger than 0.5 in the detection result;
s4, tracking and detecting an output target frame; recording target frames detected in continuous video images, setting an iou (area intersection ratio) threshold value of 0.2, wherein the target frames iou detected in two frames before and after are possibly the same target when the target frames iou are larger than the threshold value, considering that a current frame detection frame with the largest iou of a previous frame detection frame is the same target and is counted in the same target track, and forming a plurality of target tracks when a plurality of target frames are detected in the images simultaneously;
s5, establishing a corresponding relation between a target category and a target behavior;
s6, analyzing the target track and prejudging target behaviors; and selecting the target category, the target area central point and the target area aspect ratio which are stored in the target track according to the time sequence as training characteristics, analyzing the target behavior by using the training characteristics, and sending different alarms to the alarm according to the analysis result.
Further, in step S1, a specific processing method of the sample set is as follows:
s11, collecting images including pedestrians and various vehicle targets;
s12, processing the collected images by using a data enhancement method, marking the positions and the types of the persons, the vehicles and the types in the images after the enhancement processing by using a marking tool, randomly dividing the xml marking file generated after marking and the corresponding image file into two parts which are respectively used as a training sample set and a test sample set, wherein the ratio is 3: 1;
s13, setting the training input size of the model to be 1152 x 640, and performing repeated iterative training on the training sample set and the test sample set obtained after the processing of the step S12 by using a YOLOV3 network structure to obtain model weight data;
and S14, quantizing the model weight data by using a ruyi quantization tool, wherein the quantized picture selection comprises the pictures of the pedestrians and the vehicles mentioned in the step S11, n images are selected for each type of image, and the backgrounds of the n images are the earth surfaces under different illumination environments in the day and at night respectively.
Further, in step S2, a specific method for acquiring an image to be detected is as follows:
s21, acquiring continuous video images from the monitoring camera as images to be detected;
s22, keeping the resolution of the zoomed image unchanged, and calculating the size of the target zoomed image according to the size of the original image and the model input size 1152 x 640;
and S23, scaling the original image to the size of the target scaled image by using a differential reduction method, and supplementing the gray of the part of the scaled image which is less than 1152-640.
Further, in step S5, a specific method for establishing the correspondence between the target category and the target behavior is as follows: and setting three groups of corresponding relations according to the behavior commonalities among different categories: the pedestrian has three behaviors of walking, running and staying; the common vehicle has two behaviors of running and staying; the engineering vehicle has three driving states of driving, construction and staying.
Further, the specific method for analyzing the behavior of the target in step S6 is as follows: selecting a target category, a target area central point and a target area aspect ratio which are stored in a target track according to a time sequence as training characteristics, inputting the training characteristics into an SVM classifier, performing behavior classification on a detection target in a video to be detected by using the SVM classifier obtained through training, and finally sending a corresponding behavior warning condition to an alarm according to the target behavior category calculated by the SVM classifier.
Compared with the prior art, the invention has the following advantages:
the invention can realize real-time detection of personnel and vehicles in a certain range, can accurately predict the behavior state of a target, and realizes the warning effect on the personnel and vehicles near the petroleum pipeline; by adopting the deep learning model to select 1152 × 640 large-size input images, the large-size input images can accurately detect targets at a far position in the visual field range of the camera, so that the method is particularly suitable for being applied to scenes which are long in distance with an oil pipeline and need wide monitoring range.
The invention divides different target behaviors in detail, can give warning prompts to targets in a monitoring area in different degrees aiming at the behaviors, provides basis for working personnel to make countermeasures, can effectively prevent suspicious personnel and vehicles from stealing and extracting petroleum, and prevent heavy vehicles from driving above an oil pipeline and staying for a long time, and avoids the possible accidental damage to the oil pipeline in the construction process of mistakenly entering the warning area by construction vehicles.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart of an oil pipeline warning method based on personnel and vehicle behavior analysis according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
A method for oil pipeline surveillance based on analysis of personnel and vehicle behavior, as shown in fig. 1, comprising:
s1, collecting a sample set used for training the model; processing and training the sample set, and outputting a training model;
s2, acquiring an image to be detected, and preprocessing the image to be detected;
s3, processing the image to be detected by using the training model, detecting the positions of the personnel and the vehicles in the image to obtain a detection structure, setting a confidence threshold value of 0.5, and outputting target information with a confidence score larger than 0.5 in the detection result;
s4, tracking and detecting an output target frame; recording target frames detected in continuous video images, setting an iou (area intersection ratio) threshold value of 0.2, wherein the target frames iou detected in two frames before and after are possibly the same target when the target frames iou are larger than the threshold value, considering that a current frame detection frame with the largest iou of a previous frame detection frame is the same target and is counted in the same target track, and forming a plurality of target tracks when a plurality of target frames are detected in the images simultaneously;
s5, establishing a corresponding relation between a target category and a target behavior;
s6, analyzing the target track and prejudging target behaviors; and selecting the target category, the target area central point and the target area aspect ratio which are stored in the target track according to the time sequence as training characteristics, analyzing the target behavior by using the training characteristics, and sending different alarms to the alarm according to the analysis result.
In step S1, the specific processing method of the sample set is as follows:
s11, collecting images including pedestrians and various vehicle targets;
s12, processing the collected images by using a data enhancement method, marking the positions and the types of the persons, the vehicles and the types in the images after the enhancement processing by using a marking tool, randomly dividing the xml marking file generated after marking and the corresponding image file into two parts which are respectively used as a training sample set and a test sample set, wherein the ratio is 3: 1;
s13, setting the training input size of the model to be 1152 x 640, and performing repeated iterative training on the training sample set and the test sample set obtained after the processing of the step S12 by using a YOLOV3 network structure to obtain model weight data;
and S14, quantizing the model weight data by using a ruyi quantization tool, wherein the quantized picture selection comprises the pictures of the pedestrians and the vehicles mentioned in the step S11, n images are selected for each type of image, and the backgrounds of the n images are the earth surfaces under different illumination environments in the day and at night respectively.
In step S2, the specific method for obtaining the image to be detected is as follows:
s21, acquiring continuous video images from the monitoring camera as images to be detected;
s22, keeping the resolution of the zoomed image unchanged, and calculating the size of the target zoomed image according to the size of the original image and the model input size 1152 x 640;
and S23, scaling the original image to the size of the target scaled image by using a differential reduction method, and supplementing the gray of the part of the scaled image which is less than 1152-640.
In step S5, the specific method for establishing the correspondence between the target category and the target behavior is as follows: and setting three groups of corresponding relations according to the behavior commonalities among different categories: the pedestrian has three behaviors of walking, running and staying; the common vehicle has two behaviors of running and staying; the engineering vehicle has three driving states of driving, construction and staying.
The specific method for analyzing the behavior of the target in step S6 is as follows: selecting a target category, a target area central point and a target area aspect ratio which are stored in a target track according to a time sequence as training characteristics, inputting the training characteristics into an SVM classifier, performing behavior classification on a detection target in a video to be detected by using the SVM classifier obtained through training, and finally sending a corresponding behavior warning condition to an alarm according to the target behavior category calculated by the SVM classifier.
Specifically, the deep learning target detection algorithm based on YOLOV3 is adopted, video image information is obtained according to monitoring equipment, people and vehicle targets in the images are detected and classified, information such as positions and types of each target in the images within a recent period of time is recorded, behavior information of the target in the current period of time is deduced according to the information, and corresponding warning situations are sent according to target behaviors, so that the purpose of real-time warning is achieved in a monitoring area near an oil pipeline;
(i.) A sample set of training models is collected. Collecting images of objects including pedestrians, cars, SUVs, minivans, tank trucks, excavators, forklifts, engineering trucks and the like; processing the collected images by using a data enhancement method, marking the positions and the types of the personnel, the vehicles in the images after the enhancement processing by using a marking tool, randomly dividing an xml marking file generated after marking and a corresponding image file into two parts which are respectively used as a training sample set and a testing sample set, wherein the ratio is 3: 1;
(ii.) model training. Setting a model training input size to be 1152 × 640, repeatedly and iteratively training a training sample set and a test sample set which are processed in the step (i.) by using a YOLOV3 network structure to obtain model weight data, quantizing the model weight data by using a ruyi quantization tool provided by Haisi, selecting and containing pictures of pedestrians and vehicles mentioned in the step (i.), selecting 6 images of each category, wherein 6 image backgrounds respectively comprise a day normal light, a strong backlight, a dark place and a road at night, and 42 images;
(iii.) image pre-processing to be detected. Acquiring continuous video images from a monitoring camera as images to be detected, keeping the resolution of the zoomed images unchanged, calculating the size of a target zoomed image according to the size of an original image and a model input size (1152 x 640), zooming the original image to the size of the target zoomed image by using a difference image zooming method, and supplementing gray to the part of the zoomed image which is less than 1152 x 640;
(iv) detecting the position of the person or vehicle in the image. And (5) sending the image obtained in the step (iii) into the model obtained in the step (ii) for processing to obtain a detection result, setting a confidence coefficient threshold value of 0.5, and outputting target information with a confidence coefficient score larger than 0.5 in the detection result.
(v.) tracking the target frame of the detection output. Recording target frames detected in continuous video images, setting an iou (area intersection ratio) threshold value of 0.2, wherein the target frames detected in two frames before and after the iou is larger than the threshold value and possibly the same target, considering that a current frame detection frame with the largest iou of a previous frame detection frame is the same target and is counted in the same track, and forming a plurality of tracks when a plurality of target frames are detected in the images simultaneously;
(vi.) analyzing the target track and prejudging the target behavior. Establishing a corresponding relation between a target category and a target behavior;
the invention sets three groups of corresponding relations according to the behavior commonalities among different categories: (1) the pedestrian has three behaviors of walking, running and staying; (2) the car, SUV, minibus and tank wagon have two behavior states of running and staying; (3) the excavator, the forklift and the engineering truck have three running states of running, construction and residence; the method selects a target category, a target area central point and a target area aspect ratio which are stored in a target track according to a time sequence as training characteristics, uses an SVM classifier for a target behavior classification result, then performs behavior analysis on a target detected and tracked in a video to be detected by using the SVM classifier obtained by training, and finally sends out different alarms to an alarm according to the analyzed result, so that the purpose of real-time monitoring on a monitored area is achieved, and a worker can be reminded to take corresponding countermeasures according to different behavior alarms in real time; the invention is suitable for monitoring equipment in the area around the oil pipeline, and can play a real-time warning role around the oil pipeline.
The invention can realize real-time detection of personnel and vehicles in a certain range, can accurately predict the behavior state of a target, and realizes the warning effect on the personnel and vehicles near the petroleum pipeline; by adopting the deep learning model to select 1152 × 640 large-size input images, the large-size input images can accurately detect targets at a far position in the visual field range of the camera, so that the method is particularly suitable for being applied to scenes which are long in distance with an oil pipeline and need wide monitoring range.
The invention divides different target behaviors in detail, can give warning prompts to targets in a monitoring area in different degrees aiming at the behaviors, provides basis for working personnel to make countermeasures, can effectively prevent suspicious personnel and vehicles from stealing and extracting petroleum, and prevent heavy vehicles from driving above an oil pipeline and staying for a long time, and avoids the possible accidental damage to the oil pipeline in the construction process of mistakenly entering the warning area by construction vehicles.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (5)
1. An oil pipeline warning method based on personnel and vehicle behavior analysis is characterized by comprising the following steps:
s1, collecting a sample set used for training the model; processing and training the sample set, and outputting a training model;
s2, acquiring an image to be detected, and preprocessing the image to be detected;
s3, processing the image to be detected by using the training model, detecting the positions of the personnel and the vehicles in the image to obtain a detection structure, setting a confidence threshold value of 0.5, and outputting target information with a confidence score larger than 0.5 in the detection result;
s4, tracking and detecting an output target frame; recording target frames detected in continuous video images, setting an iou (area intersection ratio) threshold value of 0.2, wherein the target frames iou detected in two frames before and after are possibly the same target when the target frames iou are larger than the threshold value, considering that a current frame detection frame with the largest iou of a previous frame detection frame is the same target and is counted in the same target track, and forming a plurality of target tracks when a plurality of target frames are detected in the images simultaneously;
s5, establishing a corresponding relation between a target category and a target behavior;
s6, analyzing the target track and prejudging target behaviors; and selecting the target category, the target area central point and the target area aspect ratio which are stored in the target track according to the time sequence as training characteristics, analyzing the target behavior by using the training characteristics, and sending different alarms to the alarm according to the analysis result.
2. The method for monitoring an oil pipeline according to claim 1, wherein the specific processing method of the sample set in step S1 is as follows:
s11, collecting images including pedestrians and various vehicle targets;
s12, processing the collected images by using a data enhancement method, marking the positions and the types of the persons, the vehicles and the types in the images after the enhancement processing by using a marking tool, randomly dividing the xml marking file generated after marking and the corresponding image file into two parts which are respectively used as a training sample set and a test sample set, wherein the ratio is 3: 1;
s13, setting the training input size of the model to be 1152 x 640, and performing repeated iterative training on the training sample set and the test sample set obtained after the processing of the step S12 by using a YOLOV3 network structure to obtain model weight data;
and S14, quantizing the model weight data by using a ruyi quantization tool, wherein the quantized picture selection comprises the pictures of the pedestrians and the vehicles mentioned in the step S11, n images are selected for each type of image, and the backgrounds of the n images are the earth surfaces under different illumination environments in the day and at night respectively.
3. The method for monitoring an oil pipeline based on personnel and vehicle behavior analysis as claimed in claim 1, wherein the specific method for acquiring the image to be detected in step S2 is as follows:
s21, acquiring continuous video images from the monitoring camera as images to be detected;
s22, keeping the resolution of the zoomed image unchanged, and calculating the size of the target zoomed image according to the size of the original image and the model input size 1152 x 640;
and S23, scaling the original image to the size of the target scaled image by using a differential reduction method, and supplementing the gray of the part of the scaled image which is less than 1152-640.
4. The oil pipeline warning method based on personnel and vehicle behavior analysis according to claim 1, wherein in step S5, the specific method for establishing the corresponding relationship between the target category and the target behavior is as follows: and setting three groups of corresponding relations according to the behavior commonalities among different categories: the pedestrian has three behaviors of walking, running and staying; the common vehicle has two behaviors of running and staying; the engineering vehicle has three driving states of driving, construction and staying.
5. The method for monitoring an oil pipeline based on personnel and vehicle behavior analysis according to claim 1, wherein the concrete method for analyzing the behavior of the target in the step S6 is as follows: selecting a target category, a target area central point and a target area aspect ratio which are stored in a target track according to a time sequence as training characteristics, inputting the training characteristics into an SVM classifier, performing behavior classification on a detection target in a video to be detected by using the SVM classifier obtained through training, and finally sending a corresponding behavior warning condition to an alarm according to the target behavior category calculated by the SVM classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911275646.XA CN111046797A (en) | 2019-12-12 | 2019-12-12 | Oil pipeline warning method based on personnel and vehicle behavior analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911275646.XA CN111046797A (en) | 2019-12-12 | 2019-12-12 | Oil pipeline warning method based on personnel and vehicle behavior analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111046797A true CN111046797A (en) | 2020-04-21 |
Family
ID=70236629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911275646.XA Pending CN111046797A (en) | 2019-12-12 | 2019-12-12 | Oil pipeline warning method based on personnel and vehicle behavior analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046797A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597962A (en) * | 2020-05-12 | 2020-08-28 | 三一重工股份有限公司 | Storage material anti-theft alarm method and device and electronic equipment |
| CN111860140A (en) * | 2020-06-10 | 2020-10-30 | 北京迈格威科技有限公司 | Target event detection method and device, computer equipment and storage medium |
| CN112542046A (en) * | 2020-12-07 | 2021-03-23 | 无锡科晟光子科技有限公司 | Early warning monitoring method for long-distance pipeline heavy vehicle based on DAS |
| CN112541452A (en) * | 2020-12-18 | 2021-03-23 | 中用科技有限公司 | Management and control method, system and equipment for suspicious personnel |
| CN112579724A (en) * | 2020-12-24 | 2021-03-30 | 广州小马智行科技有限公司 | Semantic map construction method, semantic map construction device, semantic map processor and vehicle system |
| CN113139427A (en) * | 2021-03-12 | 2021-07-20 | 浙江智慧视频安防创新中心有限公司 | Steam pipe network intelligent monitoring method, system and equipment based on deep learning |
| CN113255500A (en) * | 2021-05-18 | 2021-08-13 | 山东交通学院 | Method and device for detecting random lane change of vehicle |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120075450A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Activity determination as function of transaction log |
| CN102663452A (en) * | 2012-04-14 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Suspicious act detecting method based on video analysis |
| CN105046285A (en) * | 2015-08-31 | 2015-11-11 | 武汉鹰视智能科技有限公司 | Abnormal behavior identification method based on motion constraints |
| CN108921875A (en) * | 2018-07-09 | 2018-11-30 | 哈尔滨工业大学（深圳） | A kind of real-time traffic flow detection and method for tracing based on data of taking photo by plane |
| CN109325418A (en) * | 2018-08-23 | 2019-02-12 | 华南理工大学 | Based on pedestrian recognition method under the road traffic environment for improving YOLOv3 |
| CN109711320A (en) * | 2018-12-24 | 2019-05-03 | 兴唐通信科技有限公司 | A kind of operator on duty's unlawful practice detection method and system |
| CN109711322A (en) * | 2018-12-24 | 2019-05-03 | 天津天地伟业信息系统集成有限公司 | A kind of people's vehicle separation method based on RFCN |
| CN109948582A (en) * | 2019-03-28 | 2019-06-28 | 湖南大学 | A kind of retrograde intelligent detecting method of vehicle based on pursuit path analysis |
| CN110288032A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of vehicle driving trace type detection method and device |
-
2019
- 2019-12-12 CN CN201911275646.XA patent/CN111046797A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120075450A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Activity determination as function of transaction log |
| CN102663452A (en) * | 2012-04-14 | 2012-09-12 | 中国人民解放军国防科学技术大学 | Suspicious act detecting method based on video analysis |
| CN105046285A (en) * | 2015-08-31 | 2015-11-11 | 武汉鹰视智能科技有限公司 | Abnormal behavior identification method based on motion constraints |
| CN108921875A (en) * | 2018-07-09 | 2018-11-30 | 哈尔滨工业大学（深圳） | A kind of real-time traffic flow detection and method for tracing based on data of taking photo by plane |
| CN109325418A (en) * | 2018-08-23 | 2019-02-12 | 华南理工大学 | Based on pedestrian recognition method under the road traffic environment for improving YOLOv3 |
| CN109711320A (en) * | 2018-12-24 | 2019-05-03 | 兴唐通信科技有限公司 | A kind of operator on duty's unlawful practice detection method and system |
| CN109711322A (en) * | 2018-12-24 | 2019-05-03 | 天津天地伟业信息系统集成有限公司 | A kind of people's vehicle separation method based on RFCN |
| CN109948582A (en) * | 2019-03-28 | 2019-06-28 | 湖南大学 | A kind of retrograde intelligent detecting method of vehicle based on pursuit path analysis |
| CN110288032A (en) * | 2019-06-27 | 2019-09-27 | 武汉中海庭数据技术有限公司 | A kind of vehicle driving trace type detection method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597962A (en) * | 2020-05-12 | 2020-08-28 | 三一重工股份有限公司 | Storage material anti-theft alarm method and device and electronic equipment |
| CN111597962B (en) * | 2020-05-12 | 2023-05-02 | 盛景智能科技(嘉兴)有限公司 | Antitheft alarm method and device for warehouse materials and electronic equipment |
| CN111860140A (en) * | 2020-06-10 | 2020-10-30 | 北京迈格威科技有限公司 | Target event detection method and device, computer equipment and storage medium |
| CN112542046A (en) * | 2020-12-07 | 2021-03-23 | 无锡科晟光子科技有限公司 | Early warning monitoring method for long-distance pipeline heavy vehicle based on DAS |
| CN112542046B (en) * | 2020-12-07 | 2022-03-11 | 无锡科晟光子科技有限公司 | Early warning monitoring method for long-distance pipeline heavy vehicle based on DAS |
| CN112541452A (en) * | 2020-12-18 | 2021-03-23 | 中用科技有限公司 | Management and control method, system and equipment for suspicious personnel |
| CN112579724A (en) * | 2020-12-24 | 2021-03-30 | 广州小马智行科技有限公司 | Semantic map construction method, semantic map construction device, semantic map processor and vehicle system |
| CN113139427A (en) * | 2021-03-12 | 2021-07-20 | 浙江智慧视频安防创新中心有限公司 | Steam pipe network intelligent monitoring method, system and equipment based on deep learning |
| CN113255500A (en) * | 2021-05-18 | 2021-08-13 | 山东交通学院 | Method and device for detecting random lane change of vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046797A (en) | Oil pipeline warning method based on personnel and vehicle behavior analysis | |
| KR101095528B1 (en) | An outomatic sensing system for traffic accident and method thereof | |
| CN113256924A (en) | Monitoring system, monitoring method and monitoring device for rail train | |
| CN103400111B (en) | Method for detecting fire accident on expressway or in tunnel based on video detection technology | |
| US8301577B2 (en) | Intelligent monitoring system for establishing reliable background information in a complex image environment | |
| CN111800507A (en) | Traffic monitoring method and traffic monitoring system | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN105809679A (en) | Mountain railway side slope rockfall detection method based on visual analysis | |
| CN102496275B (en) | Method for detecting overload of coach or not | |
| KR102282800B1 (en) | Method for trackig multi target employing ridar and camera | |
| CN106570444A (en) | On-board smart prompting method and system based on behavior identification | |
| Ketcham et al. | The intruder detection system for rapid transit using CCTV surveillance based on histogram shapes | |
| CN109086682A (en) | A kind of intelligent video black smoke vehicle detection method based on multi-feature fusion | |
| CN113658427A (en) | Road condition monitoring method, system and equipment based on vision and radar | |
| CN115083088A (en) | Railway perimeter intrusion early warning method | |
| CN111783700A (en) | Automatic recognition early warning method and system for road foreign matters | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN112347906B (en) | Method for detecting abnormal aggregation behavior in bus | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN112434564B (en) | Detection system for abnormal aggregation behavior in bus | |
| CN114170272A (en) | Accident reporting and storing method based on sensing sensor in cloud environment | |
| CN109886100A (en) | A kind of pedestrian detecting system based on Area generation network | |
| CN112598865A (en) | Monitoring method and system for preventing cable line from being damaged by external force | |
| CN113554872B (en) | Detection early warning method and system for traffic intersection and curve |
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 |