CN106796754A - Accident detection method, device and frequency image monitoring system - Google Patents
Accident detection method, device and frequency image monitoring system Download PDFInfo
- Publication number
- CN106796754A CN106796754A CN201580055116.8A CN201580055116A CN106796754A CN 106796754 A CN106796754 A CN 106796754A CN 201580055116 A CN201580055116 A CN 201580055116A CN 106796754 A CN106796754 A CN 106796754A
- Authority
- CN
- China
- Prior art keywords
- destination object
- period
- time
- movement locus
- accident 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of accident detection method, device and frequency image monitoring system.The accident detection method includes：Passing rules are set to the monitor area for being divided into many sub-regions according to transport information within a period of time；Destination object is detected and followed the trail of based on the video for obtaining, movement locus of the destination object within described a period of time is obtained；According to the passing rules and the movement locus, determine whether the destination object occurs traffic abnormity within described a period of time.Thereby, it is possible to be applied to more traffic scenes, and for more traffic abnormity types；In addition realize that algorithm is simple, can be used for real-time monitoring and there is accuracy of detection very high.
Description
The present invention relates to video frequency graphic monitoring technical field, more particularly to a kind of accident detection method, device and video monitoring system.
With increasing sharply for motor vehicles, some abnormal traffic situations (such as traffic accident, traffic jam, violate the traffic regulations) occur often.Abnormality detection technology be used to detect the abnormal traffic situation；The use of traditional transit equipment (such as coil checker) is difficult to detect these abnormal traffic situations.
At present, increasing monitoring camera be used to monitor traffic.
It should be noted that the introduction to technical background is intended merely to the convenient explanation clear, complete to technical scheme progress above, and facilitates the understanding of those skilled in the art and illustrate.Can not be merely because these schemes be set forth in the background section of the present invention and think that above-mentioned technical proposal is known to those skilled in the art.
The content of the invention
But, inventor has found：, only can be for a limited number of kind of scene, with the application scenarios not enough extensive and not high enough defect of accuracy of detection when the video for obtaining camera in current technology is used for abnormality detection.
The embodiment of the present invention provides a kind of accident detection method, device and video monitoring system.It is desirable to be applied to all traffic scenes, and for all traffic abnormity types, and with very high accuracy of detection.
One side according to embodiments of the present invention is there is provided a kind of accident detection method, and the accident detection method includes：
Passing rules are set to the monitor area for being divided into many sub-regions according to transport information within a period of time；
Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；
According to the passing rules and the movement locus, determine whether the destination object occurs traffic abnormity within described a period of time.
Second aspect according to embodiments of the present invention is there is provided a kind of accident detection device, and the accident detection device includes：
Rule settings unit, passing rules are set within a period of time according to transport information to the monitor area for being divided into many sub-regions；
Detection and tracing unit, the video based on acquisition are detected and followed the trail of to destination object, obtain movement locus of the destination object within described a period of time；
As a result determining unit, determines whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.
The 3rd aspect according to embodiments of the present invention there is provided a kind of frequency image monitoring system, including：
Camera, obtains the video of monitor area；And
Accident detection device as described above.
Another aspect according to embodiments of the present invention is there is provided a kind of computer-readable program, wherein when performing described program in picture control equipment, described program causes computer to perform accident detection method as described above in described image monitoring device.
Another aspect according to embodiments of the present invention is there is provided a kind of storage medium for the computer-readable program that is stored with, wherein the computer-readable program causes computer to perform accident detection method as described above in picture control equipment.
The beneficial effect of the embodiment of the present invention is, passing rules are set to the monitor area for being divided into many sub-regions according to transport information within a period of time；Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；And determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.Thereby, it is possible to suitable for more traffic scenes, and for more traffic abnormity types；In addition realize that algorithm is simple, can be used for monitoring in real time and with very high accuracy of detection.
With reference to explanation hereinafter and accompanying drawing, only certain exemplary embodiments of this invention is disclose in detail, the principle for specifying the present invention can be in adopted mode.It should be understood that embodiments of the present invention are not so limited in scope.In the range of the spirit and terms of appended claims, embodiments of the present invention include many changes, modifications and equivalent.
Described for a kind of embodiment and/or the feature that shows can be used in same or similar mode in one or more other embodiments, it is combined with feature in other embodiment, or substitute the feature in other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when being used herein, but it is not precluded from the presence or additional of one or more further features, one integral piece, step or component.
Many aspects of the present invention may be better understood with reference to following accompanying drawing.Part in accompanying drawing is not proportional drafting, and is intended merely to show the principle of the present invention.It may be exaggerated or minimized for the ease of showing and describing corresponding part in some parts of the present invention, accompanying drawing.
The element and feature that element and feature described in a kind of accompanying drawing or embodiment of the present invention can be shown in one or more other accompanying drawings or embodiment are combined.In addition, in the accompanying drawings, similar label represents corresponding part in several accompanying drawings, and may be used to indicate the corresponding component used in more than one embodiment.
Fig. 1 is a schematic diagram of the accident detection method of the embodiment of the present invention；
Fig. 2 is another schematic diagram of the accident detection method of the embodiment of the present invention；
Fig. 3 is a schematic diagram of the corresponding monitor area of camera of the embodiment of the present invention；
Fig. 4 is a schematic diagram of the sub-district Domain Properties of the embodiment of the present invention；
Fig. 5 is that the monitor area of the embodiment of the present invention is divided into the schematic diagram after many sub-regions；
Fig. 6 is the schematic diagram that is defined of many sub-regions for the embodiment of the present invention；
Fig. 7 is a schematic diagram of the destination object detection of the embodiment of the present invention；
Fig. 8 is a schematic diagram of the attribute of the destination object of the embodiment of the present invention；
Fig. 9 is a schematic diagram of the accident detection device of the embodiment of the present invention；
Figure 10 is another schematic diagram of the accident detection device of the embodiment of the present invention；
Figure 11 is that the picture control equipment one of the embodiment of the present invention constitutes schematic diagram.
Referring to the drawings, by following specification, foregoing and further feature of the invention will be apparent.In the specification and illustrated in the drawings, specifically disclose only certain exemplary embodiments of this invention, which show some embodiments for the principle that can wherein use the present invention, it will be appreciated that, the invention is not restricted to described embodiment, on the contrary, the present invention includes whole modifications, modification and the equivalent fallen within the scope of the appended claims.
Embodiment 1
The embodiment of the present invention provides a kind of accident detection method, applied in a picture control equipment.Fig. 1 is a schematic diagram of the accident detection method of the embodiment of the present invention.As shown in figure 1, methods described includes：
Step 101, logical is set to the monitor area for being divided into many sub-regions according to transport information within a period of time
Line discipline；
Step 102, the video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；
Step 103, according to the passing rules and the movement locus, determine whether the destination object occurs traffic abnormity within described a period of time.
In the present embodiment, the video that can be obtained according to camera carries out the detection of traffic abnormity.Wherein, monitor area can be statically divided into many sub-regions in advance, for example, can in advance be divided according to traffic mark (such as curved mark of turning left, straight trip mark, zebra stripes etc.)；Image detection can also be carried out to monitor area according to video, then be divided according to testing result.The embodiment that limited area is not divided of the embodiment of the present invention.
Fig. 2 is another schematic diagram of the accident detection method of the embodiment of the present invention.As shown in Fig. 2 methods described includes：
Step 201, monitor area is divided into many sub-regions；
Step 202, passing rules are set to monitor area according to transport information within a period of time；
Step 203, the video based on acquisition is detected and followed the trail of to destination object；
Step 204, movement locus of the destination object within described a period of time is obtained；
Step 205, judge whether the movement locus in described a period of time meets the passing rules；Step 206 is performed in the case where meeting；Step 207 is performed in the case of incongruent；
Step 206, determine that traffic of the destination object within described a period of time is normal；
Step 207, traffic abnormity of the destination object within described a period of time is determined.
Figures 1 and 2 show that the accident detection carried out for a destination object or multiple destination objects within a period of time.For multiple periods, 102 can be repeated the above steps to step 103, or step 203 is to step 207.
Still it is further described below by taking a period of time and a destination object as an example for the embodiment of the present invention.
Fig. 3 is a schematic diagram of the corresponding monitor area of camera of the embodiment of the present invention.As shown in figure 3, camera can be arranged on to the upper zone at crossing and obtain larger observation visual angle.
For the monitor area in camera coverage, many sub-regions can be divided into advance.Non-motor vehicle region, motor vehicle region, sweep region of turning left, sweep region of turning right, Through Lane region etc. for example can be divided into according to traffic marking.
There can be following one or more attributes i.e. per sub-regions：The identifying of the subregion, the subregion exists
The location of in the monitor area, the subregion is car lane or bicycle lane, the subregion are reversible lame or Through Lane.In the present embodiment, the attribute per sub-regions can be indicated using such as 16, i.e., can have the property value from 0x0 to 0xFFFF per sub-regions.
Fig. 4 is a schematic diagram of the sub-district Domain Properties of the embodiment of the present invention.As shown in Figure 4, preceding 4 bits (0-3) can represent position of the subregion in whole monitor area (for example, compared with the central point of monitor area, represented if the subregion is located at the left side with 1000, then represented positioned at top with 0100, then represented positioned at the right with 0010, positioned at then being represented below with 0001).
As shown in figure 4,3 bits (4-6) afterwards can represent the deflecting mark of the subregion (for example, waiting stand-by 100 to represent, turn round is represented to the left with 010, is turned right and is represented with 001)；Then 3 bits (7-9) can represent the straight trip mark of the subregion (for example, straight trip 1 is represented with 100, straight trip 2 is represented with 010, and straight trip 3 is represented with 001).
As shown in figure 4,2 bits (10-11) afterwards can represent area type (for example, it is allowed to which the region that motor vehicle and non-motor vehicle pass through is represented with 00；The region for allowing non-motor vehicle to pass through is represented with 01；The region for allowing motor vehicle to pass through is represented with 10；And allow motor vehicle and non-motor vehicle to pass through, but the region for forbidding pedestrian to pass through is represented with 11).It can be used for other various purposes for last 4 bits (12-15).
Thus, it is possible to which monitor area is divided into different types of many sub-regions.
Fig. 5 is that the monitor area of the embodiment of the present invention is divided into the schematic diagram after many sub-regions, as shown in figure 5, monitor area can be formed 1. to 9. and A to D multiple types.Wherein, labeled region is not had to be designated as NONE in Fig. 5, all types of corresponding marks are as follows in addition：
①：NONE_POWER；
②：YELLOW_LINE；
③：SIDEWALK；
④：NONE_POWER；
⑤：STRAIGHT_1；
⑥：STRAIGHT_2；
⑦：STRAIGHT_3；
⑧：TURNLEFT；
⑨：LEFTWAITING；
A:LEFT_UP_CENTER；
B:LEFT_UP_CENTER；
C：RIGHT_UP_CENTER；
D:RIGHT_DOWN_CENTER。
Fig. 6 is the schematic diagram that is defined of many sub-regions for the embodiment of the present invention, shows the example for many sub-regions being defined.As shown in fig. 6, can have the attribute of 16 per sub-regions.It is worth noting that, Fig. 4 to 6 only diagrammatically illustrate how to divide subregion and how definition region attribute；But the invention is not restricted to this, specific definition can also be determined according to actual conditions.
In a step 101, transport information can refer to the information that traffic lights (traffic lights) information or traffic-police manually command.The traffic lights information can be obtained from other equipment；It can for example be obtained by network connection traffic light systems.The information that traffic lights information or the traffic-police manually command can also be obtained from the video that camera is obtained.The present invention will be described by taking traffic lights information as an example below.
In the present embodiment, can be a signal period of traffic lights for a period of time；Such as one red light cycle or a green light cycle.Within a period of time, passing rules can be set to the monitor area for being divided into many sub-regions according to transport information.
For example, for the latter half of the monitor area shown in Fig. 5, if traffic lights information is " when red ", within the signal period, from region 6. to being 3. not allowed to D；If traffic lights information is " green light ", within the signal period, from region 6. to being 3. allowed to D.
Therefore, the passing rules in a period of time can be set in the monitor area according to transport information.These passing rules can be by hand set, these rule of communications can also be automatically generated.
In a step 102, destination object can be detected and followed the trail of based on the video obtained by camera.The destination object can be motor vehicles, such as bulky truck, vehicle for public transport, or the car of small volume, motorcycle etc.；The destination object can also be non power driven vehicle, for example manpower transportation's such as bicycle；In addition, the destination object can also be pedestrian, animal etc..Wherein, various destination objects have two states：It is static or mobile.
In the present embodiment, destination object can be detected using the method that background image is subtracted from present frame.
Fig. 7 is a schematic diagram of the destination object detection of the embodiment of the present invention, as shown in fig. 7, for example, by detecting frame by frame, can not only detect mobile object, and can detect static object；In addition, being capable of detecting when to come for bulky object or the object of small volume.On implementing for being subtracted each other using background image, correlation technique may be referred to.
Wherein, by being tracked to the same object in one section of video, the movement locus of destination object can be obtained.Movement locus of the destination object within described a period of time can be represented by following information：The mark for one or more subregions that the destination object is passed through within described a period of time.For example can be by a vector representation, the element in the vector is the mark of the one or more subregions passed through.
In the present embodiment, the destination object can have following one or more attributes：The identifying of the destination object, the movement locus of the destination object, the type of the destination object, the state of the destination object.
Fig. 8 is a schematic diagram of the attribute of the destination object of the embodiment of the present invention.As shown in figure 8, obj_ID represents the mark of the destination object；Vector obj_trajectory represent the movement locus of destination object, can be using a vector representation；Obj_type represents the type of destination object, e.g. motor vehicles or non power driven vehicle；Obj_status represents the state of destination object, is, for example, abnormal or normal, the obj_status can be updated after step 103.
For example, for some destination object in certain a period of time, its movement locus obj_trajectory can use following vector representation { 11,12,16 }；Represent that the destination object is moved to subregion 12 within this time from subregion 11, then move to subregion 16.
In step 103, determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus, can specifically include：In the case where one or more subregions that the destination object is passed through within described a period of time meet the passing rules, determine the destination object within described a period of time without generation traffic abnormity；In the case where one or more subregions that the destination object is passed through within described a period of time do not meet the passing rules, determine that within described a period of time traffic abnormity occurs for the destination object.
Still by taking the latter half of the monitor area shown in Fig. 5 as an example, if the passing rules set in a step 101 are：From region 7. to D being 3. to be not allowed to during traffic lights information " when red ", and the track of the destination object during this period of time obtained by step 102 is " 7. to 3. to D ", then can determining that the destination object is abnormal.
If the passing rules set in a step 101 are：From region 7. to 3. to being 9. not allowed to during traffic lights information " when red ", and the track of the destination object during this period of time obtained by step 102 is " 7. to 3. to 9. ", then can still determine that the destination object is abnormal.
If the passing rules set in a step 101 are：From region 7. to being 3. allowed to D when traffic lights information is " green light ", and the track of the destination object during this period of time obtained by step 102 is " 7. to D ", then can to determine that the destination object is normal to 3..
If the passing rules set in a step 101 are：Traffic lights information be " green light " when from region 7. to 3.
It is allowed to D, and the track of the destination object during this period of time obtained by step 102 is " 7. ", i.e., the destination object is static within this time or moving range very little, then can determine that the destination object is abnormal.
It is worth noting that, above only to how to determine that exception is schematically illustrated, but the invention is not restricted to this.Specific embodiment can be determined according to actual scene.
From above-described embodiment, monitor area is divided into many sub-regions, passing rules are set to monitor area according to transport information within a period of time；Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；And determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.Thereby, it is possible to suitable for more traffic scenes, and for more traffic abnormity types；In addition realize that algorithm is simple, can be used for monitoring in real time and with very high accuracy of detection.
Embodiment 2
The embodiment of the present invention provides a kind of accident detection device, and corresponding to the traffic abnormity monitoring method of embodiment 1, identical content is repeated no more.
Fig. 9 is a schematic diagram of the accident detection device of the embodiment of the present invention, as shown in figure 9, the accident detection device 900 includes：
Rule settings unit 901, passing rules are set within a period of time according to transport information to the monitor area for being divided into many sub-regions；
Detection and tracing unit 902, the video based on acquisition are detected and followed the trail of to destination object, obtain movement locus of the destination object within described a period of time；
As a result determining unit 903, determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.
Figure 10 is another schematic diagram of the accident detection device of the embodiment of the present invention, as shown in Figure 10, and the accident detection device 1000 includes：Rule settings unit 901, detection and tracing unit 902 and result determining unit 903, as described above.
As shown in Figure 10, the accident detection device 1000 can also include：
Area division unit 1001, many sub-regions are divided into by monitor area.
In the present embodiment, there can be following one or more attributes per sub-regions：The identifying of the subregion, the subregion are the location of in the monitor area, the subregion be car lane or bicycle lane,
The subregion is reversible lame or Through Lane.
In the present embodiment, the destination object can have following one or more attributes：The identifying of the destination object, the movement locus of the destination object, the type of the destination object, the state of the destination object.
In the present embodiment, movement locus of the destination object within described a period of time can be represented by following information：The mark for one or more subregions that the destination object is passed through within described a period of time.
Wherein, the result determining unit 903 specifically can be used for：In the case where one or more subregions that the destination object is passed through within described a period of time meet the passing rules, determine the destination object within described a period of time without generation traffic abnormity；In the case where one or more subregions that the destination object is passed through within described a period of time do not meet the passing rules, determine that within described a period of time traffic abnormity occurs for the destination object.
As shown in Figure 10, the accident detection device 1000 can also include：
Information acquisition unit 1002, obtains the transport information from other equipment, or obtains from the video transport information.
The embodiment of the present invention also provides a kind of picture control equipment, and the monitoring device includes accident detection device 900 or 1000 as described above.
Figure 11 is that the picture control equipment one of the embodiment of the present invention constitutes schematic diagram.As shown in figure 11, the picture control equipment 1100 can include：Central processing unit (CPU) 1101 and memory 1102；Memory 1102 is coupled to central processing unit 1101.Wherein the memory 1102 can store various data；And the program is performed under the control of central processing unit 1101.
In one embodiment, the function of above-mentioned accident detection device 900 or 1000 can be integrated into central processing unit 1101.Wherein, central processing unit 1101 can be configured as realizing accident detection method as described in Example 1.I.e. central processing unit 1101 can be configured for following control：Passing rules are set to the monitor area for being divided into many sub-regions according to transport information within a period of time；Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；Determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.
In another embodiment, above-mentioned accident detection device 900 or 1000 can be with the separate configuration of central processing unit 1101, above-mentioned accident detection device 900 or 1000 can be for example configured to the chip being connected with central processing unit 1101, the function of above-mentioned accident detection device 900 or 1000 is realized by the control of central processing unit 1101.
In addition, as shown in figure 11, picture control equipment 1100 can also include：Input/output unit 1103 and aobvious
Showing device 1104 etc.；Wherein, similarly to the prior art, here is omitted for the function of above-mentioned part.It is worth noting that, picture control equipment 1100 is also not necessary to include all parts shown in Figure 11；In addition, picture control equipment 1100 can also include the part being not shown in Figure 11, prior art may be referred to.
From above-described embodiment, monitor area is divided into many sub-regions, passing rules are set to monitor area according to transport information within a period of time；Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；And determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.Thereby, it is possible to suitable for more traffic scenes, and for more traffic abnormity types；In addition realize that algorithm is simple, can be used for monitoring in real time and with very high accuracy of detection.
Embodiment 3
The embodiment of the present invention provides a kind of frequency image monitoring system, and described image monitoring system includes：
Camera, obtains the video of monitor area；And
Accident detection device as described in Example 2.
The embodiment of the present invention also provides a kind of computer-readable program, wherein when performing described program in picture control equipment, described program causes computer to perform the accident detection method described in embodiment 1 in the monitoring device.
The embodiment of the present invention also provides a kind of storage medium for the computer-readable program that is stored with, wherein the computer-readable program causes computer to perform the accident detection method described in embodiment 1 in picture control equipment.
Apparatus and method more than of the invention can be realized by hardware, can also be realized by combination of hardware software.The present invention relates to such computer-readable program, when the program is performed by logical block, the logical block can be made to realize devices described above or component parts, or the logical block is realized various methods or step described above.The invention further relates to the storage medium for storing procedure above, such as hard disk, disk, CD, DVD, flash memory.
For one or more combinations of one or more of function box described in accompanying drawing and/or function box, it is possible to achieve be for performing the general processor of function described herein, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other PLDs, discrete gate or transistor logic, discrete hardware components or it is any appropriately combined.One or more combinations of one or more of function box described for accompanying drawing and/or function box, it is also implemented as the combination of computing device, for example, the combination of DSP and microprocessor, multi-microprocessor, communicate with DSP the one or more micro- places combined
Manage device or any other this configuration.
Above in association with specific embodiment, invention has been described, it will be appreciated by those skilled in the art that these descriptions are all exemplary, it is not limiting the scope of the invention.Those skilled in the art can make various variants and modifications to the present invention according to spirit and principles of the present invention, and these variants and modifications are also within the scope of the invention.
Claims (15)
- A kind of accident detection method, the accident detection method includes：Passing rules are set to the monitor area for being divided into many sub-regions according to transport information within a period of time；Video based on acquisition is detected and followed the trail of to destination object, obtains movement locus of the destination object within described a period of time；According to the passing rules and the movement locus, determine whether the destination object occurs traffic abnormity within described a period of time.
- According to the method described in claim 1, wherein, methods described also includes：The monitor area is divided into many sub-regions.
- Method according to claim 2, wherein, there are following one or more attributes per sub-regions：The identifying of the subregion, the subregion are the location of in the monitor area, the subregion is car lane or bicycle lane, the subregion are reversible lame or Through Lane.
- According to the method described in claim 1, wherein, the destination object has following one or more attributes：The identifying of the destination object, the movement locus of the destination object, the type of the destination object, the state of the destination object.
- According to the method described in claim 1, wherein, movement locus of the destination object within described a period of time is represented by following information：The mark for one or more subregions that the destination object is passed through within described a period of time.
- Method according to claim 5, wherein, determine whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus, including：In the case where one or more subregions that the destination object is passed through within described a period of time meet the passing rules, determine the destination object within described a period of time without generation traffic abnormity；In the case where one or more subregions that the destination object is passed through within described a period of time do not meet the passing rules, determine that within described a period of time traffic abnormity occurs for the destination object.
- According to the method described in claim 1, wherein, methods described also includes：The transport information is obtained from other equipment, or obtains from the video transport information.
- A kind of accident detection device, the accident detection device includes：Rule settings unit, sets within a period of time according to transport information to the monitor area for being divided into many sub-regions Determine passing rules；Detection and tracing unit, the video based on acquisition are detected and followed the trail of to destination object, obtain movement locus of the destination object within described a period of time；As a result determining unit, determines whether the destination object occurs traffic abnormity within described a period of time according to the passing rules and the movement locus.
- Device according to claim 8, wherein, the accident detection device also includes：Area division unit, many sub-regions are divided into by the monitor area.
- Device according to claim 9, wherein, there are following one or more attributes per sub-regions：The identifying of the subregion, the subregion are the location of in the monitor area, the subregion is car lane or bicycle lane, the subregion are reversible lame or Through Lane.
- Device according to claim 8, wherein, the destination object has following one or more attributes：The identifying of the destination object, the movement locus of the destination object, the type of the destination object, the state of the destination object.
- Device according to claim 8, wherein, movement locus of the destination object within described a period of time is represented by following information：The mark for one or more subregions that the destination object is passed through within described a period of time.
- Device according to claim 12, wherein, the result determining unit specifically for：In the case where one or more subregions that the destination object is passed through within described a period of time meet the passing rules, determine the destination object within described a period of time without generation traffic abnormity；In the case where one or more subregions that the destination object is passed through within described a period of time do not meet the passing rules, determine that within described a period of time traffic abnormity occurs for the destination object.
- Device according to claim 8, wherein, described device also includes：Information acquisition unit, obtains the transport information from other equipment, or obtains from the video transport information.
- A kind of frequency image monitoring system, including：Camera, obtains the video of monitor area；AndAccident detection device as claimed in claim 8.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/074449 WO2016145626A1 (en) | 2015-03-18 | 2015-03-18 | Traffic abnormity detection method and device, and image monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106796754A true CN106796754A (en) | 2017-05-31 |
Family
ID=56919571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201580055116.8A Pending CN106796754A (en) | 2015-03-18 | 2015-03-18 | Accident detection method, device and frequency image monitoring system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106796754A (en) |
| WO (1) | WO2016145626A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882907A (en) * | 2020-06-18 | 2020-11-03 | 北京骑胜科技有限公司 | Navigation early warning method, device, equipment and storage medium for vehicle |
| CN113221677A (en) * | 2021-04-26 | 2021-08-06 | 阿波罗智联(北京)科技有限公司 | Track abnormity detection method and device, road side equipment and cloud control platform |
| CN114216469A (en) * | 2021-02-19 | 2022-03-22 | 北京万集科技股份有限公司 | Method for updating high-precision map, intelligent base station and storage medium |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106507046B (en) * | 2016-11-07 | 2019-12-24 | 浙江大华技术股份有限公司 | Alarm information generation method and device |
| CN108922175B (en) * | 2018-06-22 | 2021-10-01 | 大连理工大学 | Method and device for recording illegal behaviors of multiple motor vehicles crossing solid line |
| CN110309735A (en) * | 2019-06-14 | 2019-10-08 | 平安科技（深圳）有限公司 | Exception detecting method, device, server and storage medium |
| CN111860190B (en) * | 2020-06-24 | 2024-04-12 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device, equipment and storage medium for target tracking |
| CN115797849B (en) * | 2023-02-03 | 2023-04-28 | 以萨技术股份有限公司 | Data processing system for determining abnormal behavior based on image |
| CN116092023B (en) * | 2023-02-03 | 2023-10-20 | 以萨技术股份有限公司 | Data processing system for determining abnormal behaviors |
| CN115797883B (en) * | 2023-02-06 | 2023-04-28 | 以萨技术股份有限公司 | Data processing system for determining abnormal event |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN101075376A (en) * | 2006-05-19 | 2007-11-21 | 北京微视新纪元科技有限公司 | Intelligent video traffic monitoring system based on multi-viewpoints and its method |
| CN102201165A (en) * | 2010-03-25 | 2011-09-28 | 北京汉王智通科技有限公司 | Monitoring system of vehicle traffic violation at crossing and method thereof |
| CN102902955A (en) * | 2012-08-30 | 2013-01-30 | 中国科学技术大学 | Method and system for intelligently analyzing vehicle behaviour |
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
| US20140211012A1 (en) * | 2012-08-06 | 2014-07-31 | Cloudparc, Inc. | Tracking Traffic Violations within an Intersection and Controlling Use of Parking Spaces Using Cameras |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971521B (en) * | 2014-05-19 | 2016-06-29 | 清华大学 | Road traffic anomalous event real-time detection method and device |
-
2015
- 2015-03-18 CN CN201580055116.8A patent/CN106796754A/en active Pending
- 2015-03-18 WO PCT/CN2015/074449 patent/WO2016145626A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075376A (en) * | 2006-05-19 | 2007-11-21 | 北京微视新纪元科技有限公司 | Intelligent video traffic monitoring system based on multi-viewpoints and its method |
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN102201165A (en) * | 2010-03-25 | 2011-09-28 | 北京汉王智通科技有限公司 | Monitoring system of vehicle traffic violation at crossing and method thereof |
| US20140211012A1 (en) * | 2012-08-06 | 2014-07-31 | Cloudparc, Inc. | Tracking Traffic Violations within an Intersection and Controlling Use of Parking Spaces Using Cameras |
| CN102902955A (en) * | 2012-08-30 | 2013-01-30 | 中国科学技术大学 | Method and system for intelligently analyzing vehicle behaviour |
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882907A (en) * | 2020-06-18 | 2020-11-03 | 北京骑胜科技有限公司 | Navigation early warning method, device, equipment and storage medium for vehicle |
| CN114216469A (en) * | 2021-02-19 | 2022-03-22 | 北京万集科技股份有限公司 | Method for updating high-precision map, intelligent base station and storage medium |
| CN113221677A (en) * | 2021-04-26 | 2021-08-06 | 阿波罗智联(北京)科技有限公司 | Track abnormity detection method and device, road side equipment and cloud control platform |
| CN113221677B (en) * | 2021-04-26 | 2024-04-16 | 阿波罗智联(北京)科技有限公司 | Track abnormality detection method and device, road side equipment and cloud control platform |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016145626A1 (en) | 2016-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106796754A (en) | Accident detection method, device and frequency image monitoring system | |
| US20200269874A1 (en) | Track prediction method and device for obstacle at junction | |
| US11273848B2 (en) | Method, device and apparatus for generating a defensive driving strategy, and storage medium | |
| CN109557904B (en) | Test method, device, equipment and medium | |
| CN103021186B (en) | Vehicle monitoring method and vehicle monitoring system | |
| CN104903915B (en) | Method for monitoring the method and apparatus of the ambient enviroment of vehicle and for implementing emergency braking | |
| JP7040374B2 (en) | Object detection device, vehicle control system, object detection method and computer program for object detection | |
| CN104376297A (en) | Detection method and device for linear indication signs on road | |
| CN109949594A (en) | Real-time traffic light recognition method | |
| US11610480B2 (en) | Road element sensors and identifiers | |
| WO2018140327A1 (en) | Computer-assisted or autonomous driving with region-of-interest determination for traffic light analysis | |
| CN109358627A (en) | Based on unpiloted driving assistance method, device, equipment, medium and vehicle | |
| CN109035831A (en) | Recognition methods, device, equipment, storage medium and the vehicle of traffic light | |
| Zyner et al. | ACFR five roundabouts dataset: Naturalistic driving at unsignalized intersections | |
| US11577756B2 (en) | Detecting out-of-model scenarios for an autonomous vehicle | |
| KR102493930B1 (en) | Apparatus and method for controlling traffic signal based on reinforcement learning | |
| CN110135377B (en) | Method and device for detecting motion state of object in vehicle-road cooperation and server | |
| KR102082254B1 (en) | a vehicle recognizing system | |
| CN111199088A (en) | Method and device for reproducing scene data | |
| Mukhopadhyay et al. | Comparing CNNs for non-conventional traffic participants | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| WO2020135880A1 (en) | Lane selection method for vehicle when self-driving, selection system, and vehicle | |
| WO2024098992A1 (en) | Vehicle reversing detection method and apparatus | |
| CN113971795A (en) | Violation inspection system and method based on self-driving visual sensing |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |