CN114267022A - Object abnormality detection method and device, storage medium, and electronic device - Google Patents
Object abnormality detection method and device, storage medium, and electronic device Download PDFInfo
- Publication number
- CN114267022A CN114267022A CN202111642503.5A CN202111642503A CN114267022A CN 114267022 A CN114267022 A CN 114267022A CN 202111642503 A CN202111642503 A CN 202111642503A CN 114267022 A CN114267022 A CN 114267022A
- Authority
- CN
- China
- Prior art keywords
- information
- scene
- scene information
- determining
- event detection
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for detecting object abnormity, a storage medium and an electronic device, wherein the method comprises the following steps: determining first scene information of a first video file acquired at a first time, wherein the first video file comprises image information of a first object; determining an event detection mode corresponding to first scene information under the condition that the first scene information changes relative to second scene information, wherein the second scene information is the scene information of a second video file acquired at a second time, and the second time is earlier than the first time; and detecting whether the first object is abnormal or not according to an event detection mode. The invention solves the problem of traffic incident detection in the related technology, reduces false alarm and missed alarm of the traffic incident caused by scene switching, and improves the accuracy and effectiveness of traffic incident detection.
Description
Technical Field
The embodiment of the invention relates to the field of image processing, in particular to a method and a device for detecting object abnormity, a storage medium and an electronic device.
Background
Traffic event detection on roads today relies heavily on lanes. When the camera is a ball machine, the rule configuration needs to be adjusted based on the preset point under the cruise setting condition. For example, the lane direction has changed, and the distance corresponding to the original resolution has also changed, so it is necessary to detect the change and adjust the rule. In extreme cases, the lane directions are completely opposite due to the rotation of the dome camera, when the detection rule is not changed, the vehicle which normally runs is regarded as a vehicle which runs in the wrong direction, a large amount of false reports occur, and the vehicle which really runs in the wrong direction is regarded as a vehicle which runs in the normal direction, so that a large amount of false reports are caused.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting object abnormity, a storage medium and an electronic device, which are used for at least solving the problem of detecting traffic events in the related art.
According to an embodiment of the present invention, there is provided a method of detecting an abnormality of an object, including: determining first scene information of a first video file acquired at a first time, wherein the first video file comprises image information of a first object; determining an event detection mode corresponding to first scene information when the first scene information changes relative to second scene information, wherein the second scene information is scene information of a second video file acquired at a second time, and the second time is earlier than the first time; and detecting whether the first object is abnormal according to the event detection mode.
According to another embodiment of the present invention, there is provided an apparatus for detecting abnormality of an object, including: the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining first scene information of a first video file acquired at a first time, and the first video file comprises image information of a first object; a second determining module, configured to determine an event detection manner corresponding to first scene information when the first scene information changes relative to second scene information, where the second scene information is scene information of a second video file acquired at a second time, and the second time is earlier than the first time; and the first detection module is used for detecting whether the first object is abnormal or not according to the event detection mode.
In an exemplary embodiment, the apparatus further includes: the first obtaining module is used for obtaining a first zoom multiple of the first video file shot by the camera shooting equipment before determining an event detection mode corresponding to the first scene information under the condition that the first scene information changes relative to the second scene information; the second acquisition module is used for acquiring a second zoom multiple of the second video file shot by the camera equipment; a third determining module, configured to determine that the first scene information is changed with respect to the second scene information when the first zoom factor does not match the second zoom factor.
In an exemplary embodiment, the apparatus further includes: a fourth determining module, configured to determine first motion information of an image capturing apparatus from the first video file before determining an event detection method corresponding to the first scene information when the first scene information changes with respect to the second scene information, where the first motion information includes first rotation information and/or first zoom information of the image capturing apparatus; a fifth determining module, configured to determine that the first scene information is changed with respect to the second scene information when the first motion information is inconsistent with the second motion information, where the second video information includes the second motion information, and the second motion information includes second rotation information and/or second zoom information of the image capturing apparatus.
In an exemplary embodiment, the second determining module includes: a first acquiring unit, configured to acquire a lane line in a target area from the first scene information; a first determining unit configured to determine a lane type and a driving direction of the lane line based on object information and device information included in the video file; a second determining unit configured to determine the event detection method corresponding to the first scene information according to the lane type and the driving direction.
In an exemplary embodiment, the second determining module includes: and the first matching unit is used for searching an event detection mode matched with the lane line in the first scene information from an event detection database.
In an exemplary embodiment, the first detecting module includes: and a third determining unit configured to determine that an abnormality occurs in the first object in a case where a lane type in which the first object travels does not match a lane type of a lane line in the event detection method and/or a traveling direction of the first object is not the same as the traveling direction in the event detection method.
In an exemplary embodiment, the apparatus further includes: and the first filtering module is used for filtering the acquired object abnormal information in the process of detecting whether the first scene information changes.
According to a further embodiment of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the method and the device, the first scene information of the first video file acquired at the first time is determined, wherein the first video file comprises the image information of the first object; determining an event detection mode corresponding to first scene information under the condition that the first scene information changes relative to second scene information, wherein the second scene information is the scene information of a second video file acquired at a second time, and the second time is earlier than the first time; and detecting whether the first object is abnormal or not according to an event detection mode. The purpose of determining different event detection modes based on different scenes is achieved. Therefore, the problem of traffic incident detection in the related technology can be solved, false alarm and false alarm of the traffic incident caused by scene switching are reduced, and the accuracy and effectiveness of traffic incident detection are improved.
Drawings
Fig. 1 is a block diagram of a hardware structure of a mobile terminal of a method for detecting an object abnormality according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of detecting object anomalies according to an embodiment of the invention;
FIG. 3 is a flow diagram of a transformation rule according to an embodiment of the invention;
FIG. 4 is a scene change flow diagram for a ball machine according to an embodiment of the present invention;
fig. 5 is a block diagram of a structure of an apparatus for detecting an abnormality of an object according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking an example of the method running on a mobile terminal, fig. 1 is a block diagram of a hardware structure of the mobile terminal of the method for detecting an object abnormality according to the embodiment of the present invention. As shown in fig. 1, the mobile terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 104 for storing data, wherein the mobile terminal may further include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of an application software, such as a computer program corresponding to the object abnormality detection method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the present embodiment, a method for detecting an object abnormality is provided, and fig. 2 is a flowchart of a method for detecting an object abnormality according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, determining first scene information of a first video file acquired at a first time, wherein the first video file comprises image information of a first object;
the first scene information includes, but is not limited to, scene information where the camera device that acquired the first video file is located, for example, the current resolution of the dome camera;
step S204, under the condition that the first scene information changes relative to the second scene information, determining an event detection mode corresponding to the first scene information, wherein the second scene information is the scene information of the second video file acquired at the second time;
the second scene information includes, but is not limited to, scene information where the camera device that acquires the second video file is located, for example, the current resolution of the dome camera;
step S206, whether the first object is abnormal is detected according to the event detection mode.
In this embodiment, the second video file includes image information of a second object, and the second object and the first object may be the same object or different objects. The first object and the second object include, but are not limited to, a vehicle, a pedestrian, and the like. And judging whether the lane type and/or the lane direction of the first object is changed or not by using the lane type and/or the lane direction of the second object. Thereby determining whether a scene change has occurred.
In this embodiment, the event detection manner includes, but is not limited to, whether an illegal phenomenon, such as going backwards, running a red light, occurs during the driving of the vehicle.
The execution subject of the above steps may be a terminal, but is not limited thereto.
Through the steps, first scene information of a first video file acquired at a first time is determined, wherein the first video file comprises image information of a first object; determining an event detection mode corresponding to first scene information under the condition that the first scene information changes relative to second scene information, wherein the second scene information is the scene information of a second video file acquired at a second time, and the second time is earlier than the first time; and detecting whether the first object is abnormal or not according to an event detection mode. The purpose of determining different event detection modes based on different scenes is achieved. Therefore, the problem of traffic incident detection in the related technology can be solved, false alarm and false alarm of the traffic incident caused by scene switching are reduced, and the accuracy and effectiveness of traffic incident detection are improved.
In an exemplary embodiment, in a case that the first context information changes with respect to the second context information, before determining the event detection manner corresponding to the first context information, the method further includes:
s1, acquiring a first zoom multiple of the first video file shot by the camera device;
s2, acquiring a second zoom multiple of the second video file shot by the camera device;
s3, in the case where the first zoom factor does not match the second zoom factor, it is determined that the first scene information has changed with respect to the second scene information.
In this embodiment, the zoom factor of the image pickup apparatus may be determined by a preset point returned by the image pickup apparatus. I.e., the video scene change of the image pickup apparatus, can be determined by the scene information returned by the image pickup apparatus. The zoom factor is used for adjusting the shooting focal length of the camera device.
In an exemplary embodiment, in a case that the first context information changes with respect to the second context information, before determining the event detection manner corresponding to the first context information, the method further includes:
s1, determining first motion information of the image pickup device from the first video file, wherein the first motion information comprises first rotation information and/or first zooming information of the image pickup device;
and S2, when the first action information is inconsistent with the second action information, determining that the first scene information is changed relative to the second scene information, wherein the second action information is included in the second video information, and the second action information includes second rotation information and/or second zooming information of the image pickup device.
In this embodiment, the first rotation information in the first motion information is compared with the second rotation information in the second motion information, and the first scaling information in the first motion information is compared with the second scaling information in the second motion information. And determining that the scene where the camera is located is changed under the condition that one information is inconsistent or two pieces of information are inconsistent at the same time.
The rotation of the image pickup apparatus is determined by detecting the degree of rotation of the image pickup apparatus. For example, if the ball machine is rotated 180 degrees relative to the position in the second scene, it can be determined that the detection scene will become another direction of vehicle travel, the direction of the lane being opposite to the direction of the lane in the original scene.
In an exemplary embodiment, determining an event detection manner corresponding to first scenario information when the first scenario information changes relative to the second scenario information includes:
s1, acquiring a lane line in the target area from the first scene information;
s2, determining a lane type and a driving direction of the lane line based on the object information and the device information included in the video file;
s3, an event detection method corresponding to the first scene information is determined according to the lane type and the driving direction.
In the embodiment, the lane direction can be drawn according to the traffic sign, especially the lane line, and whether the vehicle is illegal to stop, go backwards, press the line, pedestrian, etc. can be detected.
In an exemplary embodiment, determining an event detection manner corresponding to first scenario information when the first scenario information changes relative to the second scenario information includes:
and S1, searching an event detection mode matched with the lane line in the first scene information from the event detection database.
In this embodiment, after the scene change is finished (after the scene is stabilized), it is determined whether there is a stored event detection mode applicable to the changed scene in the database.
In an exemplary embodiment, detecting whether the first object is abnormal in an event detection manner includes:
s1, in case the lane type of the first object traveling does not match the lane type of the lane line in the event detection mode, and/or the traveling direction of the first object is not the same as the traveling direction in the event detection mode, determining that the first object is abnormal.
In the present embodiment, in the case where the lane type in which the first object is traveling does not match the lane type of the lane line in the event detection manner, it is determined that the first object is abnormal; or determining that the first object is abnormal when the driving direction of the first object is different from the driving direction in the event detection mode; alternatively, in a case where the lane type in which the first object travels does not match the lane type of the lane line in the event detection manner, and the traveling direction of the first object and the traveling direction in the event detection manner are not the same, it is determined that the first object is abnormal.
In this embodiment, in addition to determining the object abnormality based on the lane type and the lane line, the lane attribute and the direction may be determined based on a marker, a pedestrian, and a vehicle in a scene, where the lane attribute includes attributes such as a bicycle lane, a motor lane, and an emergency lane.
In one exemplary embodiment, the method further comprises:
s1, in the process of detecting whether the first scene information changes, the acquired object abnormality information is filtered.
In this embodiment, after the object exception information is acquired, the object exception information is sorted and reported, where the object exception information includes pictures, video information, and the like. The wrong information needs to be filtered, i.e. the wrong information that is considered invalid is filtered out.
The invention is illustrated below with reference to specific examples:
the present embodiment will be described taking the detection of an abnormality of a vehicle as an example. The embodiment can determine the event detection mode of the vehicle according to the difference of the acquired preset points (namely, when the video scene is changed, the scene can be known to be switched through the information returned by the front-end camera). For example, when the ball machine performs scene change (zooming or rotating), the rules that have been configured (corresponding to the event detection manner described above) may be adapted according to the difference in returning the preset points.
The rule can be reconfigured again by judging whether the scene where the camera device is located is changed through video quality diagnosis.
In this embodiment, through scene change of video quality diagnosis, when it is determined that a current video scene is in a change state, all analysis is stopped, and when the scene change is finished (after the scene is stabilized), it is first determined whether a stored scene rule is applicable, and if all the scene rules are not applicable, lane lines and markers in a new scene are automatically identified. And assist in determining lane attributes and directions, e.g., bike lane, motor lane, emergency lane, etc., based on various determinations, e.g., pedestrians, vehicles.
For example, the procedure of the rule automatic identification configuration process is described with a retrograde determination. And judging the reverse running, namely drawing a lane, judging the direction of the lane, and then judging whether the vehicle runs in the lane in the reverse running direction or not by detecting the running direction of the vehicle in the lane. The rules are lane lines and lane directions. Thus, when the scene is fixed, the lane lines (white solid line, white dotted line, yellow solid line, yellow dotted line) are detected. And drawing the lane direction and the lane line attribute (yellow white line and dashed solid line) at the corresponding pixel points in the picture. When the vehicle is detected to travel on the lane, whether the direction is consistent with the lane or not is judged according to the rule.
When the video scene changes (e.g., the ball machine rotates 180 degrees), the detection scene changes to another direction of vehicle travel, and the direction of the lane is exactly the opposite. When the scene changes, the rule is not applicable, and after the change, the normal driving is misjudged as the reverse driving. At the moment, the video quality diagnosis detects scene change, stops analyzing and stops alarm reporting. After the scene is stable, the marks, lane lines and the like on the road surface are detected again, the lane directions (according to the arrow, the advancing directions of a plurality of vehicles and the like) are judged, the road surface rule is correctly identified, and the road surface rule suitable for updating the scene is detected and reported with an alarm.
The generation of the road surface detection rules and the detection of the alarm event are different processing steps. Rules include, but are not limited to: coordinates and direction of the lane, detection area, ratio between video pixels and actual distance, etc. The rule is only generated once when no scene change occurs. After the direction of the current motor lane and the lane line coordinates are detected, secondary detection is not performed any more, and the pixel area is used for corresponding to the actual lane. And whether the vehicle or the pedestrian has the behavior violating the traffic rules or not can be judged according to the positions and the variation tracks of the vehicle or the pedestrian. And detecting an alarm event, namely detecting and tracking the object, when the object type is judged to be a pedestrian and the object type is in a motor vehicle lane, triggering pedestrian detection alarm, and similarly, when the vehicle occupies an emergency lane to run, and line pressing runs and other operations occur (only a dynamic object needs to be detected at the moment, relevant identification and analysis of a detection rule are not processed), triggering a corresponding alarm event.
As shown in fig. 3, it is a flowchart of a transformation rule in the embodiment of the present invention, and specifically includes the following steps:
s301, capturing videos or pictures through a camera (e.g., a dome camera);
s302, detecting the scene change of the camera equipment from the collected video or picture;
s303, judging whether the scene is in the process of transformation;
s304, under the condition that the scene is in the process of transformation, the old rule (corresponding to the event detection mode) is invalid;
s305, under the condition that the scene is not in the process of changing, judging whether the changing of the scene is finished, and under the condition that the changing of the scene is finished, turning to S306, otherwise, turning to S304;
s306, detecting traffic signs in the scene;
s307, judging whether the rule exists in a database or not;
s308, matching the existing rules under the condition that the database comprises the rules;
s309, generating a new rule under the condition that the rule in the database does not exist;
s310, detecting whether a traffic event occurs in the vehicle from the video or the picture;
and S311, finishing the analysis.
As shown in fig. 4, the description is made by using scene change of a dome camera, and specifically includes: whether scene change exists in the video acquired by the dome camera is detected, namely the dome camera rotates, zooms and other actions occur. And detecting lane lines, drawing appropriate rule detection areas such as lanes, advancing directions and zebra stripes, and matching whether rules suitable for the current scene are stored in the existing rules or not according to the lane lines, vehicle guide lines, the advancing directions of the vehicles and the like. If yes, the existing rule is adopted, and if not, the new rule is generated by the rule generation and detection module.
According to the traffic signs, especially the lane lines, the lane directions are drawn, and the parking, the retrograde motion, the line pressing, the pedestrians and the like are detected. And detecting the traffic incident according to a proper detection rule. When it is necessary to say, normal alarm analysis cannot be performed during the rule generation period. And finishing alarm information reporting, including picture and video information. When a scene change is detected, the improper alarm detection needs to be filtered, i.e. false alarm filtering that is considered invalid.
In summary, in the present embodiment, whether the current detection rule is valid is determined according to the scene change condition in the video. When the detection rule is not suitable, the detection rule is automatically adjusted, and the accuracy of event detection is improved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a device for detecting an object abnormality is further provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and the description of the device that has been already made is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram showing a configuration of an apparatus for detecting an abnormality of an object according to an embodiment of the present invention, as shown in fig. 5, the apparatus including:
a first determining module 52, configured to determine first scene information of a first video file acquired at a first time, where the first video file includes image information of a first object;
a second determining module 54, configured to determine an event detection manner corresponding to the first scene information when the first scene information changes relative to second scene information, where the second scene information is scene information of a second video file acquired at a second time;
the first detecting module 56 is configured to detect whether the first object is abnormal according to the event detecting manner.
In an exemplary embodiment, the apparatus further includes:
the first obtaining module is used for obtaining a first zoom multiple of the first video file shot by the camera shooting equipment before determining an event detection mode corresponding to the first scene information under the condition that the first scene information changes relative to the second scene information;
the second acquisition module is used for acquiring a second zoom multiple of the second video file shot by the camera equipment;
a third determining module, configured to determine that the first scene information is changed with respect to the second scene information when the first zoom factor does not match the second zoom factor.
In an exemplary embodiment, the apparatus further includes:
a fourth determining module, configured to determine first motion information of an image capturing apparatus from the first video file before determining an event detection method corresponding to the first scene information when the first scene information changes with respect to the second scene information, where the first motion information includes first rotation information and/or first zoom information of the image capturing apparatus;
a fifth determining module, configured to determine that the first scene information is changed with respect to the second scene information when the first motion information is inconsistent with the second motion information, where the second video information includes the second motion information, and the second motion information includes second rotation information and/or second zoom information of the image capturing apparatus.
In an exemplary embodiment, the second determining module includes:
a first acquiring unit, configured to acquire a lane line in a target area from the first scene information;
a first determining unit configured to determine a lane type and a driving direction of the lane line based on object information and device information included in the video file;
a second determining unit configured to determine the event detection method corresponding to the first scene information according to the lane type and the driving direction.
In an exemplary embodiment, the second determining module includes:
and the first matching unit is used for searching an event detection mode matched with the lane line in the first scene information from an event detection database.
In an exemplary embodiment, the first detecting module includes:
and a third determining unit configured to determine that an abnormality occurs in the first object in a case where a lane type in which the first object travels does not match a lane type of a lane line in the event detection method and/or a traveling direction of the first object is not the same as the traveling direction in the event detection method.
In an exemplary embodiment, the apparatus further includes:
and the first filtering module is used for filtering the acquired object abnormal information in the process of detecting whether the first scene information changes.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.
In the present embodiment, the above-described computer-readable storage medium may be configured to store a computer program for executing the above steps.
In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
In an exemplary embodiment, the processor may be configured to execute the above steps by a computer program.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and they may be implemented using program code executable by the computing devices, such that they may be stored in a memory device and executed by the computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into various integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for detecting an abnormality in an object, comprising:
determining first scene information of a first video file acquired at a first time, wherein the first video file comprises image information of a first object;
determining an event detection mode corresponding to first scene information under the condition that the first scene information changes relative to second scene information, wherein the second scene information is scene information of a second video file acquired at a second time, and the second time is earlier than the first time;
and detecting whether the first object is abnormal or not according to the event detection mode.
2. The method according to claim 1, wherein before determining the event detection mode corresponding to the first context information when the first context information changes with respect to the second context information, the method further comprises:
acquiring a first zoom multiple of the first video file shot by the camera equipment;
acquiring a second zoom multiple of the second video file shot by the camera equipment;
determining that the first scene information has changed relative to the second scene information if the first zoom factor does not match the second zoom factor.
3. The method according to claim 1, wherein before determining the event detection mode corresponding to the first context information when the first context information changes with respect to the second context information, the method further comprises:
determining first motion information of an image pickup device from the first video file, wherein the first motion information comprises first rotation information and/or first scaling information of the image pickup device;
and when the first motion information is inconsistent with second motion information, determining that the first scene information is changed relative to the second scene information, wherein the second video information comprises the second motion information, and the second motion information comprises second rotation information and/or second zooming information of the image pickup device.
4. The method according to claim 1, wherein determining an event detection mode corresponding to the first context information when the first context information changes with respect to the second context information comprises:
acquiring a lane line in a target area from the first scene information;
determining a lane type and a driving direction of the lane line based on object information and device information included in the video file;
and determining the event detection mode corresponding to the first scene information according to the lane type and the driving direction.
5. The method according to claim 4, wherein determining an event detection mode corresponding to the first context information when the first context information changes with respect to the second context information comprises:
and searching an event detection mode matched with the lane line in the first scene information from an event detection database.
6. The method of claim 1, wherein detecting whether the first object is abnormal according to the event detection manner comprises:
and determining that the first object is abnormal under the condition that the lane type of the first object running does not match with the lane type of the lane line in the event detection mode and/or the running direction of the first object is not the same as the running direction in the event detection mode.
7. The method of claim 1, further comprising:
and filtering the acquired object abnormal information in the process of detecting whether the first scene information changes.
8. An apparatus for detecting an abnormality in an object, comprising:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining first scene information of a first video file acquired at a first time, and the first video file comprises image information of a first object;
a second determining module, configured to determine an event detection manner corresponding to first scene information when the first scene information changes relative to second scene information, where the second scene information is scene information of a second video file acquired at a second time, and the second time is earlier than the first time;
and the first detection module is used for detecting whether the first object is abnormal or not according to the event detection mode.
9. A computer-readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, carries out the method of any one of claims 1 to 7.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111642503.5A CN114267022A (en) | 2021-12-29 | 2021-12-29 | Object abnormality detection method and device, storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111642503.5A CN114267022A (en) | 2021-12-29 | 2021-12-29 | Object abnormality detection method and device, storage medium, and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114267022A true CN114267022A (en) | 2022-04-01 |
Family
ID=80831691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111642503.5A Pending CN114267022A (en) | 2021-12-29 | 2021-12-29 | Object abnormality detection method and device, storage medium, and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114267022A (en) |
-
2021
- 2021-12-29 CN CN202111642503.5A patent/CN114267022A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmad et al. | {CarMap}: Fast 3d feature map updates for automobiles | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN106571039A (en) | Automatic snapshot system for highway traffic offence | |
| JP2020061079A (en) | Traffic violation vehicle identification system, server, and vehicle control program | |
| CN103886759A (en) | System and method for snapshotting behavior of running red light | |
| KR102297217B1 (en) | Method and apparatus for identifying object and object location equality between images | |
| CN110533921B (en) | Triggering snapshot method and system for vehicle | |
| CN112455465B (en) | Driving environment sensing method and device, electronic equipment and storage medium | |
| WO2024098992A1 (en) | Vehicle reversing detection method and apparatus | |
| CN110444026B (en) | Triggering snapshot method and system for vehicle | |
| CN112201044A (en) | Road violation vehicle identification method and system, storage medium and terminal | |
| CN114267022A (en) | Object abnormality detection method and device, storage medium, and electronic device | |
| CN115601738B (en) | Parking information acquisition method, device, equipment, storage medium and program product | |
| CN113888865B (en) | Electronic device and vehicle information acquisition method | |
| CN116311166A (en) | Traffic obstacle recognition method and device and electronic equipment | |
| CN113538925B (en) | Method, equipment and storage medium for monitoring behavior of vehicle not giving away pedestrians | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device | |
| CN116152691A (en) | Image detection method, device, equipment and storage medium | |
| CN113994391A (en) | Vehicle passing reminding method and device and vehicle-mounted terminal | |
| CN115620244A (en) | Image detection method, device and equipment based on vehicle-road cooperation and storage medium | |
| KR101956008B1 (en) | Apparatus for Providing Trajectory and Data Building Method Thereof | |
| CN110581979A (en) | Image acquisition system, method and device | |
| CN112365465B (en) | Synthetic image category determining method and device, storage medium and electronic device | |
| CN115472014B (en) | Traffic tracing method, system, server and computer storage medium | |
| CN111104900B (en) | Highway fee sorting method and device |
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 |