CN111488803A - Airport target behavior understanding system integrating target detection and target tracking - Google Patents
Airport target behavior understanding system integrating target detection and target tracking Download PDFInfo
- Publication number
- CN111488803A CN111488803A CN202010183545.6A CN202010183545A CN111488803A CN 111488803 A CN111488803 A CN 111488803A CN 202010183545 A CN202010183545 A CN 202010183545A CN 111488803 A CN111488803 A CN 111488803A
- Authority
- CN
- China
- Prior art keywords
- target
- unit
- tracking
- alarm
- module
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19608—Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
Abstract
The invention provides an airport target behavior understanding system integrating target detection and target tracking, which comprises: the system comprises a target monitoring and tracking module, a far-end video analysis module, a parallel alarm module and a remote configuration and control module; the target monitoring and tracking module is used for transmitting the real-time video stream to the far-end video analysis module; the remote video analysis module is used for dynamically tracking the moving object in the set area and detecting whether a suspicious target invades and lingers in the set area; the parallel alarm module is used for carrying out parallel alarm on a plurality of abnormal behaviors in a monitoring area; the remote configuration and control module comprises a cooperative decision unit, a server, a display unit for displaying detailed information of on-site alarm and a rule management unit, and the system can realize automatic detection and alarm of the abnormal event behaviors of the airport scene, such as the situation that vehicles enter dangerous areas such as airplane sliding areas and the like and luggage package omission occurs.
Description
Technical Field
The invention relates to the technical field of airport scene activity monitoring, in particular to an airport target behavior understanding system integrating target detection and target tracking.
Background
Along with the improvement of the social living standard, the aviation transportation volume is also rapidly increased, the airport scale is continuously enlarged, the increasingly complex airport scene activities become important factors influencing the flight safety, throughput and operating efficiency of airports, therefore, the intelligent monitoring of the scene activity target of the airport is very important, so that the airport operation management personnel can know the real-time position and the driving condition of the airplane and the vehicle in the airport in time, the existing monitoring system generally adopts a field monitoring radar, a video monitoring system and the like to complete the auxiliary monitoring of the airport scene, the communication efficiency of dispatching personnel and support personnel is improved by various modes such as digital voice, instruction, cluster talkback and the like in the airport, but the function of automatically alarming the abnormal activities of the scene is lacked, and the flight safety and the event processing efficiency of the airport are reduced because a monitor is required to carry out scheduling and monitoring.
In summary, how to provide an airport target behavior understanding system that can implement automatic detection and alarm of airport scene abnormal event behaviors, thereby avoiding occurrence of safety accidents and having a low false alarm rate and integrating target detection and target tracking is a problem that needs to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above-mentioned problems and needs, the present solution provides an airport target behavior understanding system and method that combines target detection and target tracking, which can solve the above technical problems by adopting the following technical solutions.
In order to achieve the purpose, the invention provides the following technical scheme: an airport target behavior understanding system integrating target detection and target tracking comprises: the system comprises a target monitoring and tracking module, a far-end video analysis module, a parallel alarm module and a remote configuration and control module;
the target monitoring and tracking module comprises a plurality of field real-time video monitoring points, a primary acquisition coordination control unit and an equipment self-checking unit, wherein the primary acquisition coordination control unit is used for transmitting real-time video streams of the field real-time video monitoring points to the far-end video analysis module, and the equipment self-checking unit is connected with a feedback end of the primary acquisition coordination control unit and is used for detecting the fault condition of each field real-time video monitoring point;
the remote video analysis module comprises a target counting unit, a target detection tracking unit, an auxiliary detection unit, a behavior recognition unit and a self-correction output unit, the remote video analysis module is used for dynamically tracking a moving object in a set area and detecting whether a suspicious target invades and lingers in the set area, and the auxiliary detection unit can monitor the directional approach detection that vehicles, airplanes or pedestrians approach or depart from the determined area according to a plurality of predefined directions;
the parallel alarm module is used for performing parallel alarm on a plurality of abnormal behaviors in a monitored area, the parallel alarm module can construct an alarm multidimensional historical data set, deduces influence factors aiming at historical data, calculates weight parameters occupied by the influence factors by adopting a deep learning algorithm, and feeds the weight parameters back to the remote configuration and control module positioned in the monitoring center so as to facilitate flight flow allocation and realize the pre-allocation of airspace capacity and the real-time scheduling of flight operation;
the remote configuration and control module comprises a cooperative decision unit, a server, a display unit for displaying detailed field alarm information and a rule management unit, wherein the display unit and the rule management unit are both connected with the server, a supervisor can check live video images and real-time alarm information of a plurality of field terminals and perform offline search and playback alarm through the server, the rule management unit is used for user permission verification, camera application permission and load operation balance adjustment, and the cooperative decision unit is connected with the server.
Furthermore, the remote configuration and control module also comprises an event association list unit and an interactive electronic map unit which are used for text description and alarm image snapshot association, and the event association list unit and the interactive electronic map unit are connected to display alarm position and field information on a map.
Further, the site alarm detailed information comprises alarm type, alarm time, alarm place and video source information.
Further, the specific detecting and tracking step of the target detecting and tracking unit includes: preprocessing the real-time video stream, inputting the preprocessed image into a CNN convolutional neural network of a target detection module, and detecting whether abnormal behaviors of vehicles entering dangerous areas such as airplane sliding areas, luggage package omission and external personnel entering airport areas from an outlet exist or not through an abnormal behavior detection algorithm based on the convolutional neural network; and after the abnormal frame is detected, marking an abnormal target in the image and tracking the target by adopting an improved particle filter algorithm through a tracking module.
Further, the pretreatment specifically comprises: and decompressing the real-time video stream and acquiring a sequence image.
Still further, the tracking module includes: firstly, parameter initialization is completed and a target template is calculated; reading in the next frame of image and generating a group of new particles according to state transition; training a CNN network by using a large number of scene activity databases, extracting the depth feature of a target area by using the trained CNN network, simultaneously calculating a color histogram of the target area in HSV space, and combining the depth feature and the color feature to obtain an overall feature; and (3) carrying out target on-line tracking by adopting particle filtering, evaluating each particle state to determine the target position, and updating the template according to a set threshold value.
Further, the target detection tracking unit and the auxiliary detection unit are connected with the behavior identification unit, the behavior identification unit sends an identification result to the self-correcting output unit, and the self-correcting output unit is connected with the cooperative decision unit and sends a corrected result to the cooperative decision unit.
Further, when the behavior recognition unit detects that the tracking target stops or stays at a non-parking position for more than a certain time, the tracking target is determined to be a dangerous target, and alarm information is sent to the parallel alarm module.
Furthermore, each field real-time video monitoring point comprises a secondary acquisition coordination control unit and an image acquisition unit connected with the secondary acquisition coordination control unit, wherein the image acquisition unit comprises a camera, an image brightness and image definition self-adaptive adjustment module and an image automatic focusing control module, the camera is connected with the secondary acquisition coordination control unit, the image brightness and image definition self-adaptive adjustment module is connected with a feedback interface of the camera, and the automatic focusing control module is connected with a focal length driving device of the camera.
The invention has the advantages that the invention can realize automatic detection and alarm of the abnormal event behavior of the airport scene, automatically generate alarm signals to remind monitoring personnel to pay attention when the vehicle enters dangerous areas such as airplane sliding areas and the like, luggage is omitted, external personnel enter the airport area from an exit and the like, so that management departments can timely react and organize strength to process the accidental events, thereby avoiding the occurrence of safety accidents and simultaneously reducing the possible loss of the airport.
The following description of the preferred embodiments for carrying out the present invention will be made in detail with reference to the accompanying drawings so that the features and advantages of the present invention can be easily understood.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly described below. Wherein the drawings are only for purposes of illustrating some embodiments of the invention and are not to be construed as limiting the invention to all embodiments thereof.
FIG. 1 is a schematic view of the structure of the present invention.
Fig. 2 is a schematic diagram of a structure of a remote configuration and control module according to the present invention.
Fig. 3 is a schematic diagram of the composition structure of each real-time video monitoring point on site in the present invention.
Fig. 4 is a schematic diagram of a specific detection and tracking step of the target detection and tracking unit in this embodiment.
Fig. 5 is a schematic diagram illustrating a flow of the target tracking algorithm in the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of specific embodiments of the present invention. Like reference symbols in the various drawings indicate like elements. It should be noted that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
The invention provides an airport target behavior understanding system which can realize automatic detection and alarm of airport scene abnormal event behaviors, automatically generate alarm signals to remind monitoring personnel to pay attention when vehicles enter dangerous areas such as airplane sliding areas and the like, luggage package omission exists, external personnel enter airport areas from an exit and the like, so that management departments can timely react and organize strength to process accidental events in time, safety accidents are avoided, and simultaneously target detection and target tracking which are possibly lost in airports are reduced. As shown in fig. 1 to 5, the airport target behavior understanding system integrating target detection and target tracking includes: the system comprises a target monitoring and tracking module, a far-end video analysis module, a parallel alarm module and a remote configuration and control module; the target monitoring and tracking module comprises a plurality of on-site real-time video monitoring points, a primary acquisition coordination control unit and an equipment self-checking unit, wherein the primary acquisition coordination control unit is used for transmitting real-time video streams of the on-site real-time video monitoring points to the remote video analysis module, the equipment self-checking unit is connected with the feedback end of the primary acquisition coordination control unit and is used for detecting the fault condition of each on-site real-time video monitoring point, each on-site real-time video monitoring point comprises a secondary acquisition coordination control unit and an image acquisition unit connected with the secondary acquisition coordination control unit, the image acquisition unit comprises a camera, an image brightness and image definition self-adaptive adjustment module and an image automatic focusing control module, the camera is connected with the secondary acquisition coordination control unit, and the image brightness and image definition self-adaptive adjustment module is connected with the feedback interface of the camera, the automatic focusing control module is connected with a focal length driving device of the camera, the plurality of secondary acquisition coordination control units are connected with the primary acquisition coordination control unit, and the primary acquisition coordination control unit carries out shunt output on information sent by the primary acquisition coordination control unit.
The remote video analysis module comprises a target counting unit, a target detection tracking unit, an auxiliary detection unit, a behavior identification unit and a self-correction output unit, the remote video analysis module is used for dynamically tracking a moving object in a set area and detecting whether a suspicious target invades or lingers in the set area, the auxiliary detection unit can monitor vehicles, airplanes or pedestrians to approach or depart from the determined area in multiple predefined directions for directional approach detection, the target detection tracking unit and the auxiliary detection unit are connected with the behavior identification unit, the behavior identification unit sends an identification result to the self-correction output unit, and the self-correction output unit is connected with the cooperative decision unit and sends a corrected result to the cooperative decision unit. When the behavior recognition unit detects that the tracking target stops or stays at a non-parking position for more than a certain time, the tracking target is judged to be a dangerous target and alarm information is sent to the parallel alarm module.
The parallel alarm module is used for performing parallel alarm on a plurality of abnormal behaviors in a monitoring area, the parallel alarm module can construct an alarm multidimensional historical data set, influence factors are deduced according to historical data, weight parameters occupied by the influence factors are calculated by adopting a deep learning algorithm, and the weight parameters are fed back to the remote configuration and control module positioned in the monitoring center, so that the flight flow allocation is facilitated, the pre-allocation of airspace capacity is realized, and the real-time scheduling of flight operation is realized.
The remote configuration and control module comprises a cooperative decision unit, a server, a display unit and a rule management unit, wherein the display unit is used for displaying field alarm detailed information, the field alarm detailed information comprises alarm types, alarm time, alarm places and video source information, the display unit and the rule management unit are both connected with the server, a supervisor can check live video images and real-time alarm information of a plurality of field terminals through the server and perform offline search and playback alarm, the rule management unit is used for verifying user permissions, adjusting camera application permissions and balancing load operation, and the cooperative decision unit is connected with the server. The remote configuration and control module further comprises an event association list unit and an interactive electronic map unit, wherein the event association list unit is used for text description and alarm image snapshot association, the event association list unit and the interactive electronic map unit are connected to display alarm positions and field information on a map, and the interactive electronic map unit is connected with the server.
As shown in fig. 4, the specific detecting and tracking steps of the target detecting and tracking unit in the far-end video analysis module include: s1, preprocessing the real-time video stream, S2, inputting the preprocessed image into a CNN convolutional neural network of a target detection module, and detecting whether the vehicle enters dangerous areas such as an airplane sliding area and the like, luggage package omission exists and abnormal behaviors of external personnel entering an airport area from an outlet or not through an abnormal behavior detection algorithm based on the convolutional neural network; s3, marking an abnormal target in the image and tracking the target by adopting an improved particle filter algorithm through a tracking module after the abnormal frame is detected; s4, sending the detection and tracking result to a behavior recognition unit, wherein the behavior recognition unit classifies and judges the target behaviors according to the detection and tracking result, the target number sent by the target counting unit and the target motion direction information sent by the auxiliary detection unit; and S5, correcting the classification judgment result by a self-correcting output unit and outputting the result. The preprocessing is specifically to decompress the real-time video stream and obtain a sequence image. As shown in the flowchart of the tracking algorithm of fig. 5, the tracking module comprises: firstly, initializing parameters and calculating a target template, wherein the central position of a target area in a first frame is taken as Y, and the initial positions S of N initial particlesii, each granuleWeight ω of childrenjInitializing W to be 1/N, wherein the weight of a particle is the similarity between the feature vector of the particle and a target template, and the number of the particles is set to be N-60; reading in the next frame image, generating a new set of particles according to the state transition, tracking the next frame, and generating a new set of particles according to the initial position in the first frame according to the Gaussian distribution
Randomly broadcasting a number of new particles to estimate the target position, wherein,
for each example position in the k-th frame, μkIs the mean, σ, of the Gaussian distribution in the k-th framekIs the variance of the gaussian distribution in the kth frame; training a CNN network by using a large number of scene activity databases, extracting depth features of a target region by using the trained CNN network, simultaneously calculating a color histogram of the target region in HSV space, combining the depth features and the color features to obtain overall features, calculating feature vectors of each particle, and then calculating the Babbitt distance d between the feature vector of each particle and a target template to obtain the weight of each particle
Finally, the positions of all the particles and the corrected weight value are used
Carrying out weighted average to predict the target position of the current frame
Adopting particle filtering to carry out target on-line tracking to evaluate each particle state to determine the target position, carrying out template updating according to a set threshold value, and carrying out threshold value updating
Is the average of the posterior probabilities of the previous 10 frames of the current frame, where PkThe posterior probability value of the tracking result and the template is obtained, if the posterior probability is more than u, the result is obtained according to Nk＝αAk+(1-α)MkPerforming template update, wherein NkTo update the rear template, AkAs a current frame template, MkThe method is a previous frame template, α is a model coefficient, 0.1 is generally adopted, resampling is needed to obtain new high-quality particles to avoid the degradation phenomenon in the particle filter algorithm, and whether resampling is needed or not can be judged according to the effective particle number M.
In this embodiment, the wireless communication mode uses a TCP/IP network for data communication, and uses IP as an address for data exchange, and the suspicious target detection includes pedestrian, vehicle and package detection.
It should be noted that the described embodiments of the invention are only preferred ways of implementing the invention, and that all obvious modifications, which are within the scope of the invention, are all included in the present general inventive concept.
Claims (9)
1. An airport target behavior understanding system integrating target detection and target tracking, comprising: the system comprises a target monitoring and tracking module, a far-end video analysis module, a parallel alarm module and a remote configuration and control module;
the target monitoring and tracking module comprises a plurality of field real-time video monitoring points, a primary acquisition coordination control unit and an equipment self-checking unit, wherein the primary acquisition coordination control unit is used for transmitting real-time video streams of the field real-time video monitoring points to the far-end video analysis module, and the equipment self-checking unit is connected with a feedback end of the primary acquisition coordination control unit and is used for detecting the fault condition of each field real-time video monitoring point;
the remote video analysis module comprises a target counting unit, a target detection tracking unit, an auxiliary detection unit, a behavior recognition unit and a self-correction output unit, the remote video analysis module is used for dynamically tracking a moving object in a set area and detecting whether a suspicious target invades and lingers in the set area, and the auxiliary detection unit can monitor the directional approach detection that vehicles, airplanes or pedestrians approach or depart from the determined area according to a plurality of predefined directions;
the parallel alarm module is used for performing parallel alarm on a plurality of abnormal behaviors in a monitored area, the parallel alarm module can construct an alarm multidimensional historical data set, deduces influence factors aiming at historical data, calculates weight parameters occupied by the influence factors by adopting a deep learning algorithm, and feeds the weight parameters back to the remote configuration and control module positioned in the monitoring center so as to facilitate flight flow allocation and realize the pre-allocation of airspace capacity and the real-time scheduling of flight operation;
the remote configuration and control module comprises a cooperative decision unit, a server, a display unit for displaying detailed field alarm information and a rule management unit, wherein the display unit and the rule management unit are both connected with the server, a supervisor can check live video images and real-time alarm information of a plurality of field terminals and perform offline search and playback alarm through the server, the rule management unit is used for user permission verification, camera application permission and load operation balance adjustment, and the cooperative decision unit is connected with the server.
2. The airport target behavior understanding system with integrated target detection and target tracking according to claim 1, wherein the remote configuration and control module further comprises an event association list unit and an interactive electronic map unit for associating text description and alarm image snapshot, wherein the event association list unit is connected with the interactive electronic map unit to display alarm position and scene information on a map.
3. The airport target behavior understanding system with fused target detection and target tracking according to claim 1, wherein the site alarm details include alarm type, alarm time, alarm location and video source information.
4. The airport target behavior understanding system integrating target detection and target tracking according to claim 1, wherein the target detection tracking unit specifically detects and tracks the airport target, and comprises: preprocessing the real-time video stream, inputting the preprocessed image into a CNN convolutional neural network of a target detection module, and detecting whether abnormal behaviors of vehicles entering dangerous areas such as airplane sliding areas, luggage package omission and external personnel entering airport areas from an outlet exist or not through an abnormal behavior detection algorithm based on the convolutional neural network; and after the abnormal frame is detected, marking an abnormal target in the image and tracking the target by adopting an improved particle filter algorithm through a tracking module.
5. The airport target behavior understanding system integrating target detection and target tracking according to claim 4, wherein the preprocessing specifically comprises: and decompressing the real-time video stream and acquiring a sequence image.
6. The airport target behavior understanding system fusing target detection and target tracking according to claim 4, wherein the tracking module comprises: firstly, parameter initialization is completed and a target template is calculated; reading in the next frame of image and generating a group of new particles according to state transition; training a CNN network by using a large number of scene activity databases, extracting the depth feature of a target area by using the trained CNN network, simultaneously calculating a color histogram of the target area in HSV space, and combining the depth feature and the color feature to obtain an overall feature; and (3) carrying out target on-line tracking by adopting particle filtering, evaluating each particle state to determine the target position, and updating the template according to a set threshold value.
7. The airport target behavior understanding system integrating target detection and target tracking according to claim 1, wherein the target detection tracking unit and the auxiliary detection unit are connected to the behavior recognition unit, the behavior recognition unit sends a recognition result to the self-calibration output unit, and the self-calibration output unit is connected to the cooperative decision unit and sends a corrected result to the cooperative decision unit.
8. The airport target behavior understanding system integrating target detection and target tracking according to claim 1, wherein when the behavior recognition unit detects that a tracked target is parked or detained in a non-parking space for more than a certain time, the tracked target is determined to be a dangerous target and alarm information is sent to the parallel alarm module.
9. The airport target behavior understanding system integrating target detection and target tracking according to claim 1, wherein each live real-time video monitoring point comprises a secondary acquisition coordination control unit and an image acquisition unit connected with the secondary acquisition coordination control unit, the image acquisition unit comprises a camera, an image brightness and image definition adaptive adjustment module and an image automatic focusing control module, the camera is connected with the secondary acquisition coordination control unit, the image brightness and image definition adaptive adjustment module is connected with a feedback interface of the camera, and the automatic focusing control module is connected with a focal length driving device of the camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183545.6A CN111488803A (en) | 2020-03-16 | 2020-03-16 | Airport target behavior understanding system integrating target detection and target tracking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183545.6A CN111488803A (en) | 2020-03-16 | 2020-03-16 | Airport target behavior understanding system integrating target detection and target tracking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111488803A true CN111488803A (en) | 2020-08-04 |
Family
ID=71810775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010183545.6A Pending CN111488803A (en) | 2020-03-16 | 2020-03-16 | Airport target behavior understanding system integrating target detection and target tracking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111488803A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881247A (en) * | 2020-09-28 | 2020-11-03 | 民航成都物流技术有限公司 | Luggage path planning method, system and device and readable storage medium |
| CN112767626A (en) * | 2021-01-07 | 2021-05-07 | 长沙树根互联技术有限公司 | Position monitoring method, device, equipment and storage medium |
| CN113012136A (en) * | 2021-03-24 | 2021-06-22 | 中国民航大学 | Airport luggage counting method and counting system based on target detection |
| CN113665495A (en) * | 2021-09-23 | 2021-11-19 | 温州大学大数据与信息技术研究院 | Vehicle-mounted target tracker convenient to install and based on computer vision |
| CN113816082A (en) * | 2021-08-19 | 2021-12-21 | 昆明昆船逻根机场系统有限公司 | Operation and maintenance system for guaranteeing operation and maintenance personnel safety of luggage conveying system |
| CN113891010A (en) * | 2021-09-23 | 2022-01-04 | 温州大学大数据与信息技术研究院 | Behavior recognition system based on visual technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101609588A (en) * | 2008-06-16 | 2009-12-23 | 云南正卓信息技术有限公司 | Full-automatic anti-intrusion intelligent video monitoring alarm system for unattended villa |
| CN201773466U (en) * | 2009-09-09 | 2011-03-23 | 深圳辉锐天眼科技有限公司 | Video monitoring and pre-warning device for detecting, tracking and identifying object detention/stealing event |
| CN108182447A (en) * | 2017-12-14 | 2018-06-19 | 南京航空航天大学 | A kind of adaptive particle filter method for tracking target based on deep learning |
-
2020
- 2020-03-16 CN CN202010183545.6A patent/CN111488803A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101609588A (en) * | 2008-06-16 | 2009-12-23 | 云南正卓信息技术有限公司 | Full-automatic anti-intrusion intelligent video monitoring alarm system for unattended villa |
| CN201773466U (en) * | 2009-09-09 | 2011-03-23 | 深圳辉锐天眼科技有限公司 | Video monitoring and pre-warning device for detecting, tracking and identifying object detention/stealing event |
| CN108182447A (en) * | 2017-12-14 | 2018-06-19 | 南京航空航天大学 | A kind of adaptive particle filter method for tracking target based on deep learning |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881247A (en) * | 2020-09-28 | 2020-11-03 | 民航成都物流技术有限公司 | Luggage path planning method, system and device and readable storage medium |
| CN111881247B (en) * | 2020-09-28 | 2020-12-22 | 民航成都物流技术有限公司 | Luggage path planning method, system and device and readable storage medium |
| CN112767626A (en) * | 2021-01-07 | 2021-05-07 | 长沙树根互联技术有限公司 | Position monitoring method, device, equipment and storage medium |
| CN113012136A (en) * | 2021-03-24 | 2021-06-22 | 中国民航大学 | Airport luggage counting method and counting system based on target detection |
| CN113816082A (en) * | 2021-08-19 | 2021-12-21 | 昆明昆船逻根机场系统有限公司 | Operation and maintenance system for guaranteeing operation and maintenance personnel safety of luggage conveying system |
| CN113816082B (en) * | 2021-08-19 | 2022-08-05 | 昆明昆船逻根机场系统有限公司 | Operation and maintenance system for guaranteeing operation and maintenance personnel safety of luggage conveying system |
| CN113665495A (en) * | 2021-09-23 | 2021-11-19 | 温州大学大数据与信息技术研究院 | Vehicle-mounted target tracker convenient to install and based on computer vision |
| CN113891010A (en) * | 2021-09-23 | 2022-01-04 | 温州大学大数据与信息技术研究院 | Behavior recognition system based on visual technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488803A (en) | Airport target behavior understanding system integrating target detection and target tracking | |
| CN108053427B (en) | Improved multi-target tracking method, system and device based on KCF and Kalman | |
| CN104020751B (en) | Campus Security monitoring method based on Internet of Things | |
| US11217088B2 (en) | Alert volume normalization in a video surveillance system | |
| CN108009473B (en) | Video structuralization processing method, system and storage device based on target behavior attribute | |
| CN108446630B (en) | Intelligent monitoring method for airport runway, application server and computer storage medium | |
| CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
| CN108052859B (en) | Abnormal behavior detection method, system and device based on clustering optical flow characteristics | |
| EP2009604B1 (en) | A security device and system | |
| WO2008103206A1 (en) | Surveillance systems and methods | |
| CN108009506A (en) | Intrusion detection method, application server and computer-readable recording medium | |
| CN109484935A (en) | A kind of lift car monitoring method, apparatus and system | |
| CN112686090B (en) | Intelligent monitoring system for abnormal behavior in bus | |
| CN112633057B (en) | Intelligent monitoring method for abnormal behavior in bus | |
| CN105426820A (en) | Multi-person abnormal behavior detection method based on security monitoring video data | |
| Kulkarni et al. | Real time vehicle detection, tracking and counting using Raspberry-Pi | |
| CN103246896A (en) | Robust real-time vehicle detection and tracking method | |
| CN111294561A (en) | Video-based online patrol method, electronic device, storage medium and system | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN109544870A (en) | Alarm decision method and intelligent monitor system for intelligent monitor system | |
| US10860865B2 (en) | Predictive security camera system | |
| CN116310922A (en) | Petrochemical plant area monitoring video risk identification method, system, electronic equipment and storage medium | |
| CN113095160A (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
| CN116308960B (en) | Intelligent park property prevention and control management system based on data analysis and implementation method thereof | |
| CN116758441A (en) | Unmanned aerial vehicle cluster intelligent scheduling management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |