CN111932901A - Road vehicle tracking detection apparatus, method and storage medium - Google Patents
Road vehicle tracking detection apparatus, method and storage medium Download PDFInfo
- Publication number
- CN111932901A CN111932901A CN201910394469.0A CN201910394469A CN111932901A CN 111932901 A CN111932901 A CN 111932901A CN 201910394469 A CN201910394469 A CN 201910394469A CN 111932901 A CN111932901 A CN 111932901A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- tracking
- detection result
- acquisition devices
- 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.)
- Granted
Links
Images
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The present disclosure provides a road vehicle tracking detection apparatus, method and storage medium. A plurality of acquisition devices are provided to be able to acquire images of roads within a predetermined range; the image processing module is used for processing images acquired by the acquisition devices at corresponding moments or within corresponding time periods so as to determine vehicle detection results of vehicles in the images acquired by the acquisition devices; the vehicle tracking management module is used for tracking and managing the detected vehicles in the road within the preset range; the vehicle tracking management module is used for determining a vehicle detection result matched with the currently tracked vehicle according to the association degree and updating the state of the vehicle on the basis of the vehicle detection result matched with the currently tracked vehicle. Therefore, real-time continuous tracking detection of vehicles in the road can be realized.
Description
Technical Field
The disclosure relates to the technical field of internet of things, and in particular relates to a road vehicle tracking detection device, a road vehicle tracking detection method and a storage medium.
Background
The intelligent high speed drives the digitization and the intellectualization of the highway by comprehensively sensing, studying, judging and controlling the road, the environment and the vehicles in real time, ensures the safety and the smoothness of the highway, reduces the traffic accidents of the highway, improves the experience of the owner of the highway and supports the intellectualized evolution of the automobile.
Traditional road monitoring system, because there is the blind area between the camera, hardly carry out whole complete tracking to the vehicle. If a vehicle is to be tracked, the characteristics (license plate, color, brand, etc.) of the vehicle are usually manually identified, and then the same vehicle is searched in a downstream camera according to the motion track of the vehicle. If the vehicle stops for a long time in a blind area, and suddenly changes direction and the like, the difficulty of identifying the vehicle again at the downstream is increased.
Therefore, a solution is needed that enables real-time continuous tracking of vehicles in a roadway.
Disclosure of Invention
An object of the present disclosure is to provide a solution capable of providing technical support for real-time continuous tracking of vehicles in a road.
According to a first aspect of the present disclosure, there is provided a road vehicle tracking detection apparatus comprising: the system comprises a plurality of acquisition devices, a plurality of image acquisition devices and a display device, wherein the acquisition devices are arranged to be capable of acquiring images of roads in a predetermined range, one acquisition device is used for acquiring images of one road section in the roads in the predetermined range, and at least partial overlapping areas are formed between two adjacent road sections; the image processing module is used for processing images acquired by the acquisition devices at corresponding moments or within corresponding time periods so as to determine vehicle detection results of vehicles in the images acquired by the acquisition devices; the vehicle tracking management module is used for tracking and managing the detected vehicles in the road within the preset range; and the vehicle tracking management module also determines a vehicle detection result matched with the currently tracked vehicle according to the association degree, and updates the state of the vehicle on the basis of the vehicle detection result matched with the currently tracked vehicle.
Optionally, the association degree calculation module characterizes the association degree by calculating a similarity between the vehicle detection result and the state information of the vehicle currently tracked by the vehicle tracking management module.
Optionally, the vehicle detection result and the state information respectively include information of multiple dimensions, and the similarity is a sum of products of the similarity between the vehicle detection result and the state information in the multiple dimensions and corresponding weights.
Optionally, the information of the plurality of dimensions includes at least one of: a location; speed; direction; a vehicle detection frame; a vehicle color; the brand of the vehicle; a license plate; a vehicle attitude; and the lane information of the vehicle.
Optionally, for a vehicle without a vehicle detection result matching therewith, the vehicle tracking management module continues tracking management on the vehicle based on the motion trail and/or the state information of the vehicle, and ends the tracking management on the vehicle if no vehicle detection result matching therewith exists after a predetermined time threshold is exceeded.
Optionally, for a vehicle detection result of a vehicle that does not have a matching vehicle, the vehicle tracking management module further determines whether the vehicle detection result is reasonable, and if it is determined that the vehicle detection result is reasonable, the vehicle tracking management module further newly creates a vehicle corresponding to the vehicle detection result, and performs tracking management on the newly created vehicle.
Optionally, in a case that the vehicle detection result matched with the vehicle includes a plurality of vehicle detection results corresponding to different acquisition devices, the vehicle tracking management module updates the state of the vehicle according to the plurality of vehicle detection results.
Optionally, the plurality of capturing devices are disposed above the road, the plurality of capturing devices include a first capturing device for capturing an image of the road within a predetermined range directly below, a second capturing device for capturing an image of the road within a first predetermined distance range in the first direction, and a third capturing device for capturing an image of the road within a second predetermined range in the first direction, wherein the first predetermined distance range has an at least partial overlapping region with the predetermined range directly below, and the second predetermined distance range has an at least partial overlapping region with the first predetermined distance range.
Optionally, the plurality of acquisition devices further comprises: the image acquisition device comprises a fourth acquisition device and a fifth acquisition device, wherein the fourth acquisition device is used for acquiring an image of a road in a third preset distance range in a second direction opposite to the first direction, the fifth acquisition device is used for acquiring an image of a road in a fourth preset distance range in the second direction, the third preset distance range has an at least partial overlapping area with the preset range right below, and the fourth preset distance range has an at least partial overlapping area with the third preset distance range.
Optionally, the road vehicle tracking detection device further comprises: the first sending module is used for sending the detected state information of the vehicle to the vehicle and/or sending the detected state information of other vehicles around the vehicle to the vehicle; and/or a second sending module for sending the detected state information of the vehicle to the server.
Optionally, the road vehicle tracking detection device further comprises: the first early warning module is used for analyzing the state information of the detected vehicles in the road within the preset range and notifying the corresponding vehicles of the risk information under the condition that the risk of the traffic accident exists.
Optionally, the road vehicle tracking detection device further comprises: and the second early warning module is used for analyzing the state information of the detected vehicles in the road within the preset range and notifying the abnormal information to the rear vehicle under the condition that the traffic abnormality exists.
According to a second aspect of the present disclosure, there is also provided a road vehicle tracking detection apparatus, comprising: the system comprises a plurality of acquisition devices, a plurality of image acquisition devices and a display device, wherein the acquisition devices are arranged to be capable of acquiring images of successive roads in a predetermined range, one acquisition device is used for acquiring images of one road in the roads in the predetermined range, and at least partial overlapping areas are formed between two adjacent roads; the image processing module is used for processing images acquired by the acquisition devices at corresponding moments or within corresponding time periods so as to determine vehicle detection results of vehicles in the images acquired by the acquisition devices; the correlation degree calculation module is used for calculating the correlation degree between the vehicle detection results of different acquisition devices; and the vehicle tracking management module is used for determining vehicle detection results of different acquisition devices corresponding to the same vehicle according to the association degree and tracking and managing the detected vehicle.
Optionally, the image processing module is further configured to process images captured by the multiple capturing devices at a next time or within a next time period to determine a vehicle detection result of the vehicle in the image captured by each capturing device, the association degree calculation module is further configured to calculate an association degree between the vehicle detection results of different capturing devices and the vehicle currently tracked by the vehicle tracking management module, and the vehicle tracking management module is further configured to determine a vehicle detection result matched with the currently tracked vehicle according to the association degree and update the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
According to a third aspect of the present disclosure, there is also provided a road vehicle tracking detection method, including: tracking and managing vehicles in a road within a currently detected preset range; acquiring images of roads in a preset range by utilizing a plurality of acquisition devices, wherein one acquisition device is used for imaging one section of the roads in the preset range, and at least partial overlapping areas are formed between two adjacent sections of the roads; processing images acquired by a plurality of acquisition devices at corresponding moments or within corresponding time periods to determine vehicle detection results of vehicles in the images acquired by the acquisition devices; calculating the correlation degree between vehicles currently tracked by the vehicle detection results of different acquisition devices; and determining a vehicle detection result matched with the currently tracked vehicle according to the correlation degree, and updating the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
Optionally, the step of calculating the degree of association between vehicles in roads within a predetermined range currently tracked by the vehicle detection results of different collection devices comprises: and calculating the similarity between the vehicle detection result and the state information of the currently tracked vehicle to represent the correlation degree.
Optionally, the vehicle detection result and the state information respectively include information of multiple dimensions, and the similarity is a sum of products of the similarity between the vehicle detection result and the state information in the multiple dimensions and corresponding weights.
Optionally, the information of the plurality of dimensions includes at least one of: a location; speed; direction; a vehicle detection frame; a vehicle color; the brand of the vehicle; a license plate; a vehicle attitude; and the lane information of the vehicle.
Optionally, the method further comprises: and for the vehicle without the matched vehicle detection result, continuing tracking management on the basis of the motion trail and/or the state information of the vehicle, and finishing the tracking management on the vehicle when the matched vehicle detection result does not exist after the preset time threshold value is exceeded.
Optionally, the method further comprises: and judging whether the vehicle detection result is reasonable or not for the vehicle detection result without the matched vehicle, and if so, newly building a vehicle corresponding to the vehicle detection result and tracking and managing the newly built vehicle.
Optionally, the method further comprises: transmitting the detected state information of the vehicle to the vehicle; and/or transmitting detected state information of other vehicles located around the vehicle to the vehicle; and/or transmit the detected state information of the vehicle to the server.
Optionally, the method further comprises: the state information of the vehicles in the detected road within the predetermined range is analyzed, and in case of a risk of a traffic accident, the risk information is notified to the corresponding vehicle.
Optionally, the method further comprises: the state information of the vehicles in the road within the detected predetermined range is analyzed, and in the case where there is a traffic abnormality, the abnormality information is notified to the rear vehicle.
According to a fourth aspect of the present disclosure, there is also provided a road vehicle tracking detection method, including: imaging roads in a predetermined range in the predetermined range by using a plurality of acquisition devices, wherein each acquisition device is used for imaging a part of the roads in the predetermined range, and adjacent part of the roads have at least partial overlapping areas; processing images formed by a plurality of acquisition devices at the same time or within the same time period to determine a vehicle detection result of a vehicle in the image formed by each acquisition device; calculating the correlation degree between the vehicle detection results of different acquisition devices; and determining vehicle detection results of different acquisition devices corresponding to the same vehicle according to the association degree, and tracking and managing the detected vehicles.
Optionally, the method further comprises: processing images acquired by a plurality of acquisition devices at the next moment or in the next time period to determine a vehicle detection result of a vehicle in the image acquired by each acquisition device; calculating the correlation degree between the vehicle detection results of different acquisition devices and the currently tracked vehicle; and determining a vehicle detection result matched with the currently tracked vehicle according to the correlation degree, and updating the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
According to a fifth aspect of the present disclosure, there is also presented a computing device comprising: a processor; and a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform a method as set forth in the third or fourth aspect of the disclosure.
According to a sixth aspect of the present disclosure, there is also presented a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform a method as recited in the third or fourth aspect of the present disclosure.
The road vehicle real-time continuous tracking detection system can utilize a plurality of acquisition devices to realize real-time comprehensive perception of road conditions, and can realize real-time continuous tracking detection of road vehicles by fusing image data acquired by the plurality of acquisition devices.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in greater detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
Fig. 1 shows a top view of the coverage of three cameras.
Fig. 2 shows an overall flow chart of a road vehicle tracking detection method.
Fig. 3 shows a schematic block diagram of the structure of a road vehicle tracking detection apparatus according to an embodiment of the present disclosure.
FIG. 4 shows a schematic structural diagram of a computing device according to an embodiment of the present disclosure.
Detailed Description
Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The premise of real-time continuous tracking of vehicles in a road is real-time and comprehensive perception of road conditions. In this regard, the present disclosure proposes that a plurality of collecting devices may be arranged above the road, such as may be erected on a ram above the road. The present disclosure refers to a capturing device for capturing an image, such as but not limited to an image sensor (e.g., may be a camera). The plurality of acquisition devices may be configured to acquire images of roads within a predetermined range, wherein each acquisition device is configured to acquire an image of one road segment of the roads within the predetermined range, and two adjacent road segments have at least partial overlapping areas. Therefore, the plurality of acquisition devices can be responsible for acquiring current road condition information from different angles and/or directions, and the image data acquired by the plurality of acquisition devices are fused, so that the full coverage of roads in a preset range can be realized, and the real-time comprehensive perception of the road condition can be realized.
Taking the example of sensing a one-way road, the plurality of capturing devices may include a first capturing device, a second capturing device, and a third capturing device. The first acquisition device is used for acquiring images of roads in a preset range right below the first acquisition device, the second acquisition device is used for acquiring images of roads in a first preset distance range in the first direction, and the third acquisition device is used for acquiring images of roads in a second preset range in the first direction, wherein the first preset distance range and the preset range right below the first acquisition device have at least partial overlapping areas, and the second preset distance range and the first preset distance range have at least partial overlapping areas.
As an example, the first capture device may be a fisheye camera, the second capture device may be a near-end camera, and the third capture device may be a far-end camera. Fig. 1 shows a top view of the coverage of the three cameras. As shown in fig. 1, a road section right below can be covered by a fisheye camera, an area from a near end to a near end is a coverage area of the near end camera, an area from a far end to a far end is a coverage area of the far end camera, the fisheye camera and the near end camera have a certain overlapping area, and the near end camera and the far end camera have a certain overlapping area. Therefore, for different areas on the road, covered by different cameras, two cameras may coincide in a few areas.
In the case of sensing a bidirectional road, the plurality of capturing devices may include, in addition to the three capturing devices mentioned above, a fourth capturing device and a fifth capturing device that are symmetrically disposed with respect to the second capturing device and the third capturing device, respectively. The fourth acquisition device is used for acquiring images of roads in a third predetermined distance range in a second direction opposite to the first direction, and the fifth acquisition device is used for acquiring images of roads in a fourth predetermined distance range in the second direction, wherein the third predetermined distance range has an at least partial overlapping area with the predetermined range right below, and the fourth predetermined distance range has an at least partial overlapping area with the third predetermined distance range. The fourth acquisition device may be a near-end camera, and the fifth acquisition device may be a far-end camera. For the coverage of the near-end camera and the far-end camera, reference may be made to fig. 1 above, and details are not described here.
Based on the design of the above-mentioned many collection equipment, this disclosure provides a road vehicle tracking detection scheme of striding collection equipment.
In an initial situation, that is, when a vehicle in a road is detected for the first time, images acquired by a plurality of acquisition devices at corresponding times or within corresponding time periods may be processed to determine a vehicle detection result of the vehicle in an image formed by each acquisition device. For example, in the case where the plurality of capturing devices operate synchronously and the capturing frequency is the same, the images captured by the plurality of capturing devices at the same time or in the same time period may be processed to determine the vehicle detection result of the vehicle in the image captured by each capturing device.
And then calculating the degree of association between the vehicle detection results of different acquisition devices, and determining the vehicle detection results of different acquisition devices corresponding to the same vehicle according to the degree of association, so that the vehicle detection result of each vehicle in the road can be obtained, wherein one vehicle can correspond to one vehicle detection result and can also correspond to the vehicle detection results of a plurality of different acquisition devices. Tracking management can be performed for the detected vehicles.
In the subsequent tracking detection of the vehicles in the road, images acquired by a plurality of acquisition devices at the next time (the next corresponding time) or the next corresponding time period (the next corresponding time period) may be processed to determine the vehicle detection result of the vehicle in the image acquired by each acquisition device, and then the degree of association between the vehicle detection results of different acquisition devices and the currently tracked vehicle may be calculated. According to the degree of association, a vehicle detection result matching the currently tracked vehicle may be determined, and the state of the vehicle may be updated based on the vehicle detection result matching the currently tracked vehicle. Thus, real-time continuous tracking of vehicles in the road can be achieved.
Fig. 2 shows an overall flow chart of a road vehicle tracking detection method. Fig. 3 shows a schematic block diagram of the structure of a road vehicle tracking detection apparatus capable of executing the method shown in fig. 2.
The implementation flow of the present disclosure is exemplarily described below with reference to fig. 2 and fig. 3.
As shown in fig. 3, the road vehicle tracking detection apparatus includes a plurality of acquisition devices (10-1, 10-2 … 10-N shown in the drawing, where N is an integer greater than 1), an image processing module 20, a degree of association calculation module 30, and a vehicle tracking management module 40. The multiple acquisition devices may operate synchronously or asynchronously. For a plurality of acquisition devices, see the above description, and are not described herein again.
As shown in fig. 2, for the images formed by a plurality of capturing devices, the final vehicle tracking detection result can be obtained through the processes of vehicle identification, calculation of association degree, matching detection result, updating state, life cycle management and the like.
The following is an exemplary description of the implementation of the scheme in the initial case of vehicle detection and road vehicle continuous tracking, respectively.
Vehicle detection at initial conditions
1. Vehicle identification
Images taken by multiple capture devices at corresponding times or over corresponding time periods may be processed by the image processing module 20 to determine vehicle detection results for vehicles in the images taken by each capture device. In the case where the plurality of collection devices operate synchronously and the collection frequencies coincide, the corresponding time or the corresponding time period mentioned here may refer to the same time or the same time period, and may refer to, for example, an initial time or an initial time period when the detection of the vehicle in the road is just started.
The vehicle detection result refers to vehicle identification information that can characterize the vehicle in the image, and may include information in multiple dimensions. For example, the vehicle detection result may include, but is not limited to, information of multiple dimensions such as position, speed, direction, detection frame, license plate, vehicle color, vehicle brand, vehicle posture, lane information where the vehicle is located, and the like.
For dimension information such as detection frames, license plates, vehicle colors, vehicle brands, vehicle postures and information of lanes where vehicles are located, images collected by the collecting equipment can be directly processed through an image recognition technology to obtain the dimension information. The information of the dimensions such as position, speed, direction and the like can be obtained according to indirect calculation.
For example, for a location: the mapping relation between the coordinate system of the acquisition equipment and the coordinate system of the road surface can be obtained by calibrating the acquisition equipment in advance. Therefore, the position of the vehicle in the image can be obtained through the vehicle frame in the image formed by the acquisition equipment, and the position of the vehicle in the road coordinate system can be obtained based on the mapping relation between the coordinate system of the acquisition equipment and the road coordinate system. For the speed: the instantaneous speed v' can be calculated according to the position information of the two frames before and after, but because the instantaneous speed is severely jittered and is not suitable for correlation matching, a filtering algorithm can be preferably adopted to obtain the average speed v within a certain time interval, and the average speed is more stable than the instantaneous speed and is more reliable in the high-speed movement process of the vehicle. For the direction: similarly, the instantaneous direction d' is more jittered, and the average direction d over a certain time interval may preferably be used for correlation.
2. Calculating degree of association
The degree of correlation between the vehicle detection results of the different collection devices may be calculated by the degree of correlation calculation module 30. The degree of association can be characterized by the degree of similarity between the vehicle detection results of different acquisition devices. Therefore, the association degree calculation module 30 may calculate the degree of similarity between the vehicle detection results of different collection devices to characterize the association degree. The greater the similarity degree between the vehicle detection results of different acquisition devices, the higher the correlation degree.
As described above, the vehicle detection result includes information of multiple dimensions, and thus the association degree calculation module 30 may calculate the sum of the similarity between the vehicle detection results of different collection devices and the product of the corresponding weight to characterize the association degree.
For example, the similarity between the vehicle detection results of different collection devices may be denoted as D ═ a × D (p) + b × D (v) + c × D (D) + D (bbox) + e × D (platid) + f × D (color) + g × D (brand). Wherein D represents the total similarity, i.e., the degree of association, a-g is a coefficient (i.e., a weight) of each dimension, D () is a similarity calculation method (specifically adopted similarity calculation method, which is not described herein), p represents a position, v represents a speed, D represents a direction, bbox represents a license plate of a detection frame, color represents a color of a vehicle, and brand of the vehicle.
The specific values of the coefficients of different dimensions can be set according to actual conditions. As an example, the above-mentioned position, speed, direction may be considered local features, which may be kept globally consistent during the movement of the vehicle across the acquisition device. The detection frame, the license plate, the color, the brand and the like are characteristics related to the acquisition equipment, the change in the acquisition equipment at the same visual angle is small, and the change is large after the acquisition equipment is spanned, so that the coefficient of the unreliable characteristics can be reduced when the similarity between the vehicle detection results of the spanned acquisition equipment is calculated.
3. Match detection result
The vehicle tracking management module 40 may determine the vehicle detection results of different collection devices corresponding to the same vehicle according to the association degree. For example, the vehicle tracking management module 40 may determine that the vehicle detection results with the degree of association (e.g., the degree of similarity) greater than a predetermined threshold value correspond to the same vehicle, and thus may identify the same vehicle appearing in images from different capturing devices at the same time (or in the same time period).
For a detected vehicle, the vehicle tracking management module 40 may determine the state information of the vehicle according to the corresponding vehicle detection result (one or more). The state information here is equivalent to the above-mentioned vehicle detection result, and may also include information of multiple dimensions, such as, but not limited to, position, speed, direction, detection frame, license plate, vehicle color, vehicle brand, vehicle posture, information of lane where the vehicle is located, and the like.
The vehicle tracking management module 40 may perform tracking management on the detected vehicle. Tracking management here refers to managing the life cycle of a detected vehicle. As an example, the vehicle tracking management module 40 may create a vehicle tracker (tracker) for the detected vehicle, manage the life cycle of the vehicle tracker, and update the state of the vehicle tracker, so as to continuously track the vehicle.
Vehicle continuous tracking detection
For the detected vehicles in the road, continuous tracking detection can be performed on the vehicles according to image data subsequently acquired by the plurality of acquisition devices, that is, the state information of the vehicles is continuously updated.
1. Vehicle identification
Images captured by multiple capture devices at corresponding times or over corresponding time periods may be processed by the image processing module 20 to determine vehicle detection results for vehicles in the images captured by each capture device. The corresponding time or the corresponding time period may be a current time or a latest time period, and may be referred to as a next time or a next time period compared to the time or the time period in the vehicle detection process in the initial case. For the vehicle identification process, see the above description, and will not be described herein.
2. Calculating degree of association
The degree of association between the vehicle detection results of the different collection devices and the vehicle currently tracked by the vehicle tracking management module may be calculated by the degree of association calculation module 30. As an example, the association degree calculation module 30 may characterize the association degree by calculating a similarity between the vehicle detection result and the state information of the vehicle currently tracked by the vehicle tracking management module 40.
The vehicle detection result and the state information may respectively include information of multiple dimensions, which may include, but are not limited to, a position, a speed, a direction, a detection frame, a license plate, a vehicle color, a vehicle brand, a vehicle posture, lane information where the vehicle is located, and the like.
The association degree calculation module 30 may calculate the sum of the similarity between the vehicle detection results of different collection devices and the state information in multiple dimensions and the product of the corresponding weight to represent the association degree.
For example, the similarity between the vehicle detection result and the status information may be denoted as D ═ a × D (p) + b × D (v) + c × D (D) + D: (bbox) + e × D (platid) + f × D (color) + g × D (brand). Wherein D represents the total similarity, i.e., the degree of association, a-g is the coefficient of each dimension, D () is the similarity calculation method (specifically adopted similarity calculation method, which is not described herein), p represents the position, v represents the speed, D represents the direction, bbox represents the detection frame place id represents the license plate, color represents the color of the vehicle, and brand of the vehicle.
3. Match detection result
The vehicle detection result matching the currently tracked vehicle may be determined by the vehicle tracking management module 40 according to the degree of association. Specifically, there may be a plurality of matching methods. For example, the vehicle detection result with the degree of association greater than the predetermined threshold value and the vehicle may be used as a matching pair, and for example, the matching relationship between the vehicle detection result and the vehicle may also be obtained by using the hungarian algorithm. The hungarian algorithm is an existing mature algorithm, and details of a specific process of matching by the hungarian algorithm are not repeated in the disclosure.
After the matching relation between the vehicle detection result and the vehicle is obtained, unreasonable matching results can be filtered. For example, unreasonable matching results can be filtered out according to the upper limit of the possible displacement of the two frames of vehicles before and after the acquisition device, so that the final corresponding relation between the vehicle detection result and the vehicle can be obtained. The vehicle tracking management module 40 may match each vehicle currently tracked with one or more vehicle detection results, or zero or more vehicle detection results.
4. Updating a state
For a vehicle having a vehicle detection result that matches it, the status of the vehicle may be updated by the vehicle tracking management module 40 based on the vehicle detection result that matches the vehicle. Therefore, continuous tracking detection of vehicles in the road can be realized.
In the case where the vehicle detection result matched with the vehicle includes a plurality of vehicle detection results corresponding to different collection devices, the vehicle tracking management module 40 may update the state of the vehicle according to the plurality of vehicle detection results.
For example, for the motion state of the vehicle, Kalman (Kalman) filtering may be employed to update the operation attributes such as the position, speed, direction, etc. of the current vehicle by using a uniform motion model. Under the coverage range of different acquisition devices, the measurement errors are different, and the Kalman measurement noise coefficient of the vehicle can be updated according to the measurement errors obtained in the previous calibration link. The purpose of the method is to update the motion speed and position of the object under the world coordinate system to obtain a smooth motion track, stable motion speed and orientation.
For attributes such as license plates, colors and brands of vehicles, the attributes can be updated in a voting decision mode within a certain time window, so that individual inaccurate detection results can be effectively filtered.
5. Lifecycle management
Due to false detection, missed detection, false matching, and entrance and exit of vehicles, the vehicle detection result and the vehicle cannot be perfectly matched. And for the vehicle which is not matched, continuously predicting a period of time according to the original motion track, and ending the tracking detection of the vehicle when the period of time is exceeded or the matching is not successful. For the vehicle detection result which is not matched, firstly, the NMS (non-maximum suppression) is utilized to judge whether the vehicle distance meets the actual condition or not and whether the vehicle distance is false detection or not, and if the vehicle distance is not false detection, a new vehicle (namely a vehicle tracker) is created and is used as a new vehicle for tracking.
That is, for a vehicle for which there is no vehicle detection result matching therewith, tracking management may be continued by the vehicle tracking management module 40 based on the motion trajectory and/or the state information of the vehicle, and in a case where there is no vehicle detection result matching therewith after exceeding a predetermined time threshold, the tracking management of the vehicle may be ended. Therefore, vehicles which exit from the monitoring range of the road vehicle tracking detection equipment can be filtered in time.
For the vehicle detection result of the vehicle which does not have a matching vehicle, the vehicle tracking management module 40 can judge whether the vehicle detection result is reasonable, and if the vehicle detection result is judged to be reasonable, a vehicle corresponding to the vehicle detection result is newly built, and the newly built vehicle is tracked and managed. Therefore, vehicles entering the monitoring range of the road vehicle tracking and detecting equipment can be tracked and detected in time.
In the process of continuously tracking and detecting the vehicle, the process can be iteratively executed to update the state information of the vehicle in real time.
Application scenarios
The road vehicle tracking and detecting equipment can be used as a road side sensing unit (RSU) to be arranged at a preset position on a road, if the road side sensing unit (RSU) can be arranged on a ram above the road, the road side sensing unit (RSU) can utilize three cameras to complete the covering of a single-side road section, the RSU is symmetrical in the front and back directions, and five cameras can be utilized to complete the covering of a whole road section. The specific installation manner of the camera can be referred to the above related description. Each functional module in the above-mentioned road vehicle tracking and detecting device may be implemented by a computing platform (e.g. an edge computing platform) in a road side sensing unit (RSU). Also, the Roadside Sensing Unit (RSU) may further include a network communication module, a V2X module, a radar sensor module, and the like.
The method can be regarded as a vehicle continuous tracking scheme realized on the RSU, can accurately and continuously track all vehicles on a road in real time, and can output reliable information such as the position, the speed, the orientation and the vehicle attribute of the vehicles. The present disclosure may be applicable to a variety of upper layer application scenarios. There are two categories according to the data destination.
(1) Communicating with vehicle
The vehicle can be notified of its own position, relationship with surrounding vehicles by communicating with the vehicle through V2X.
360 degree circular viewing
The visual range of a vehicle is limited, and the RSU has a 'god view angle', so that the tracks of all vehicles on a road section can be obtained, and the surrounding environment can be accurately sensed. By communicating with the vehicle through the RSU, the field of view of the vehicle may be widened. The V2X is arranged on the vehicle, the accurate perception information of the RSU to the vehicle and other vehicles around is obtained, the 'restoration image' of the surrounding scene can be drawn on the vehicle, and the road condition of the blind area can be seen through the surrounding vehicles even if the field of vision of the driver is limited, so that the driver can make a prejudgment.
Therefore, the road vehicle tracking detection device may further optionally comprise a first transmitting module for transmitting the detected status information of the vehicle to the vehicle and/or transmitting the detected status information of other vehicles located around the vehicle to the vehicle.
Collision warning
The collision early warning can be realized by a vehicle loading radar early warning mode, but the radar can only cover a fixed direction, for example, a front radar can not early warn the collision of a vehicle coming from the side direction. The RSU can look around each vehicle by 360 degrees, so that collision scenes possibly occurring in various angles can be warned. For example, a vehicle turning left at an intersection and an oncoming vehicle traveling straight are prone to lateral collision, and the collision between the two vehicles can be early warned through information such as vehicle speed, position, orientation and the like.
Thus, the road vehicle tracking detection device may optionally further comprise a first warning module. The first early warning module is used for analyzing the detected state information of the vehicles in the continuous road and notifying the corresponding vehicles of the risk information under the condition that the risk of the traffic accident exists.
Early warning of abnormal road conditions
Due to abnormal road conditions caused by road repair, accidents, vehicle breakdown and the like, the vehicle can usually detect the abnormality only when the vehicle is driven nearby. The RSU of the present disclosure can help a driver avoid an abnormal road section by informing an abnormality of a road ahead in advance through communication with a vehicle. For example, a continuous collision accident caused by a sudden loss of the vehicle on the road is caused because the driver has no good anticipation for the abnormal situation in front and has no time to respond. The RSU can master the motion state of each vehicle, can analyze vehicles with abnormal motion, and can early warn vehicles coming behind in advance.
Thus, the road vehicle tracking detection device may optionally further comprise a second early warning module. The second early warning module is used for analyzing the detected state information of the vehicles in the continuous road and notifying the abnormal information to the rear vehicle under the condition that the traffic abnormality exists.
(2) Communicating with a server
The road vehicle tracking detection device may further optionally comprise a second transmitting module for transmitting the detected status information of the vehicle to the server. The server may refer to a cloud server, such as a cloud control platform.
The cloud control platform can use data sent by the road vehicle tracking detection equipment as a reliable input source for applications such as monitoring road conditions and predicting road congestion. By adopting the scheme of the common road side camera, the information such as the average traffic flow, the speed and the estimated vehicle number of the road section can be obtained. By utilizing the road vehicle tracking detection equipment disclosed by the invention, the accurate information such as the position, the speed, the direction and the like of each vehicle can be obtained, and more accurate input is provided for applications such as road congestion prediction, road condition judgment and the like on the cloud.
The road sensing capacity of different angles and directions can be provided through the synchronization and the fusion of the multi-path data acquired by the multi-acquisition equipment, the local information is spliced into a whole, and the real road full coverage is realized. Compared with the prior art, the multi-dimensional similarity calculation method can effectively distinguish different vehicles and guarantee the consistency of the vehicle cross-camera tracking. And the accurate path, speed, orientation and other attributes of the vehicle can be acquired, and the continuous accurate tracking of each vehicle is achieved. The whole process has no blind area, and errors such as vehicle tracking interruption and mismatching caused by the blind area can be effectively improved.
Fig. 4 shows a schematic structural diagram of a computing device that can be used to implement the above-mentioned road vehicle tracking detection method according to an embodiment of the present disclosure.
Referring to fig. 4, computing device 400 includes memory 410 and processor 420.
The processor 420 may be a multi-core processor or may include a plurality of processors. In some embodiments, processor 420 may include a general-purpose host processor and one or more special coprocessors such as a Graphics Processor (GPU), a Digital Signal Processor (DSP), or the like. In some embodiments, processor 420 may be implemented using custom circuits, such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA).
The memory 410 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are required by the processor 420 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 410 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 410 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 410 has stored thereon executable code that, when processed by the processor 420, may cause the processor 420 to perform the above-mentioned road vehicle tracking detection method.
The road vehicle tracking detection method according to the present disclosure has been described in detail above with reference to the accompanying drawings.
Furthermore, the method according to the present disclosure may also be implemented as a computer program or computer program product comprising computer program code instructions for performing the above-mentioned steps defined in the above-mentioned method of the present disclosure.
Alternatively, the present disclosure may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform the various steps of the above-described method according to the present disclosure.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (27)
1. A road vehicle tracking detection apparatus, comprising:
the system comprises a plurality of acquisition devices, a plurality of image acquisition devices and a display device, wherein the acquisition devices are arranged to be capable of acquiring images of roads in a predetermined range, one acquisition device is used for acquiring images of one road in the roads in the predetermined range, and two adjacent roads have at least partial overlapping areas;
the image processing module is used for processing the images acquired by the plurality of acquisition devices at corresponding moments or within corresponding time periods so as to determine vehicle detection results of the vehicles in the images acquired by the acquisition devices;
the vehicle tracking management module is used for tracking and managing the detected vehicles in the road within the preset range;
the association degree calculation module is used for calculating the association degree between the vehicle detection results of different acquisition devices and the vehicle currently tracked by the vehicle tracking management module,
the vehicle tracking management module also determines a vehicle detection result matched with the currently tracked vehicle according to the association degree, and updates the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
2. The road vehicle tracking detection device according to claim 1,
the association degree calculation module represents the association degree by calculating a similarity between the vehicle detection result and the state information of the vehicle currently tracked by the vehicle tracking management module.
3. The road vehicle tracking detection apparatus according to claim 2, characterized in that the vehicle detection result and the status information respectively include information of a plurality of dimensions,
the similarity is the sum of the product of the similarity between the vehicle detection result and the state information in the multiple dimensions and the corresponding weight.
4. The road vehicle tracking detection device of claim 3, wherein the information in the plurality of dimensions comprises at least one of:
a location;
speed;
direction;
a vehicle detection frame;
a vehicle color;
the brand of the vehicle;
a license plate;
a vehicle attitude;
and the lane information of the vehicle.
5. The road vehicle tracking detection device according to claim 1,
and for the vehicle without the matched vehicle detection result, the vehicle tracking management module continuously performs tracking management on the vehicle based on the motion trail and/or the state information of the vehicle, and ends the tracking management on the vehicle under the condition that the matched vehicle detection result does not exist after the preset time threshold value is exceeded.
6. The road vehicle tracking detection device according to claim 1,
and if the vehicle tracking management module judges that the vehicle detection result is reasonable, the vehicle tracking management module also newly builds a vehicle corresponding to the vehicle detection result and performs tracking management on the newly built vehicle.
7. The road vehicle tracking detection device according to claim 1,
and in the case that the vehicle detection result matched with the vehicle comprises a plurality of vehicle detection results corresponding to different acquisition devices, the vehicle tracking management module updates the state of the vehicle according to the plurality of vehicle detection results.
8. The road vehicle tracking detection device according to claim 1,
the plurality of acquisition devices are arranged above a road, and comprise a first acquisition device, a second acquisition device and a third acquisition device, wherein the first acquisition device is used for acquiring images of the road in a preset range right below, the second acquisition device is used for acquiring images of the road in a first preset distance range in the first direction, the third acquisition device is used for acquiring images of the road in a second preset range in the first direction, the first preset distance range and the preset range right below have at least partial overlapping areas, and the second preset distance range and the first preset distance range have at least partial overlapping areas.
9. The road vehicle tracking detection device of claim 8, wherein the plurality of acquisition devices further comprises:
the image acquisition device comprises a fourth acquisition device and a fifth acquisition device, wherein the fourth acquisition device is used for acquiring images of roads in a third preset distance range in a second direction opposite to the first direction, the fifth acquisition device is used for acquiring images of roads in a fourth preset distance range in the second direction, the third preset distance range has an at least partial overlapping area with the preset range right below, and the fourth preset distance range has an at least partial overlapping area with the third preset distance range.
10. The road vehicle tracking detection device of claim 1, further comprising:
the first sending module is used for sending the detected state information of the vehicle to the vehicle and/or sending the detected state information of other vehicles around the vehicle to the vehicle; and/or
And the second sending module is used for sending the detected state information of the vehicle to the server.
11. The road vehicle tracking detection device of claim 1, further comprising:
and the first early warning module is used for analyzing the detected state information of the vehicles on the road in the preset range and notifying the corresponding vehicles of the risk information under the condition that the risk of the traffic accident exists.
12. The road vehicle tracking detection device of claim 1, further comprising:
and the second early warning module is used for analyzing the detected state information of the vehicles in the road in the preset range and notifying the abnormal information to the rear vehicle under the condition that the traffic abnormality exists.
13. A road vehicle tracking detection apparatus, comprising:
the system comprises a plurality of acquisition devices, a plurality of image acquisition devices and a display device, wherein the acquisition devices are arranged to be capable of acquiring images of continuous roads in a preset range, one acquisition device is used for acquiring images of one road in the preset range, and at least partial overlapping areas exist between two adjacent roads;
the image processing module is used for processing the images acquired by the plurality of acquisition devices at corresponding moments or within corresponding time periods so as to determine vehicle detection results of the vehicles in the images acquired by the acquisition devices;
the correlation degree calculation module is used for calculating the correlation degree between the vehicle detection results of different acquisition devices;
and the vehicle tracking management module is used for determining vehicle detection results of different acquisition devices corresponding to the same vehicle according to the association degree and tracking and managing the detected vehicle.
14. The road vehicle tracking detection device according to claim 13,
the image processing module is further used for processing images acquired by the plurality of acquisition devices at the next moment or in the next time period so as to determine the vehicle detection result of the vehicle in the image acquired by each acquisition device,
the association degree calculation module also calculates the association degree between the vehicle detection results of different acquisition devices and the vehicle currently tracked by the vehicle tracking management module,
the vehicle tracking management module also determines a vehicle detection result matched with the currently tracked vehicle according to the association degree, and updates the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
15. A road vehicle tracking detection method, comprising:
tracking and managing vehicles in a road within a currently detected preset range;
acquiring images of roads in the preset range by utilizing a plurality of acquisition devices, wherein one acquisition device is used for imaging one section of the roads in the preset range, and adjacent two sections of the roads have at least partial overlapping areas;
processing images acquired by the plurality of acquisition devices at corresponding moments or within corresponding time periods to determine vehicle detection results of vehicles in the images acquired by the acquisition devices;
calculating the correlation degree between vehicles currently tracked by the vehicle detection results of different acquisition devices;
and determining a vehicle detection result matched with the currently tracked vehicle according to the correlation degree, and updating the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
16. The road vehicle tracking detection method according to claim 15, wherein the step of calculating the degree of association between vehicles in the road within the predetermined range currently tracked by the vehicle detection results of different acquisition devices comprises:
and calculating the similarity between the vehicle detection result and the state information of the currently tracked vehicle to represent the correlation degree.
17. The road vehicle tracking detection method according to claim 16, wherein the vehicle detection result and the state information respectively include information of a plurality of dimensions,
the similarity is the sum of the product of the similarity between the vehicle detection result and the state information in multiple dimensions and the corresponding weight.
18. The method of claim 15, wherein the information in the plurality of dimensions includes at least one of:
a location;
speed;
direction;
a vehicle detection frame;
a vehicle color;
the brand of the vehicle;
a license plate;
a vehicle attitude;
and the lane information of the vehicle.
19. The road vehicle tracking detection method of claim 15, further comprising:
and for the vehicle without the matched vehicle detection result, continuing tracking management on the basis of the motion trail and/or the state information of the vehicle, and finishing the tracking management on the vehicle when the matched vehicle detection result does not exist after the preset time threshold value is exceeded.
20. The road vehicle tracking detection method of claim 15, further comprising:
and judging whether the vehicle detection result is reasonable or not for the vehicle detection result without the matched vehicle, and if so, newly building a vehicle corresponding to the vehicle detection result and tracking and managing the newly built vehicle.
21. The road vehicle tracking detection method of claim 15, further comprising:
transmitting the detected state information of the vehicle to the vehicle; and/or
Transmitting the detected state information of other vehicles located around the vehicle to the vehicle; and/or
And sending the detected state information of the vehicle to a server.
22. The road vehicle tracking detection method of claim 15, further comprising:
and analyzing the detected state information of the vehicles in the road within the preset range, and notifying corresponding vehicles of the risk information under the condition that the risk of the traffic accident exists.
23. The road vehicle tracking detection method of claim 15, further comprising:
and analyzing the detected state information of the vehicles in the road in the predetermined range, and notifying the abnormal information to the rear vehicle when the traffic abnormality exists.
24. A road vehicle tracking detection method, comprising:
imaging roads in a predetermined range by using a plurality of acquisition devices, wherein each acquisition device is used for imaging part of the roads in the predetermined range, and adjacent part of the roads have at least partial overlapping areas;
processing images formed by the plurality of acquisition devices at the same time or within the same time period to determine a vehicle detection result of the vehicle in the image formed by each acquisition device;
calculating the correlation degree between the vehicle detection results of different acquisition devices;
and determining vehicle detection results of different acquisition devices corresponding to the same vehicle according to the association degree, and tracking and managing the detected vehicles.
25. The road vehicle tracking detection method of claim 24, further comprising:
processing images acquired by the plurality of acquisition devices at the next moment or in the next time period to determine a vehicle detection result of a vehicle in the image acquired by each acquisition device;
calculating the correlation degree between the vehicle detection results of different acquisition devices and the currently tracked vehicle;
and determining a vehicle detection result matched with the currently tracked vehicle according to the correlation degree, and updating the state of the vehicle based on the vehicle detection result matched with the currently tracked vehicle.
26. A computing device, comprising:
a processor; and
a memory having executable code stored thereon which, when executed by the processor, causes the processor to perform the method of any of claims 15 to 25.
27. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any of claims 15-25.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910394469.0A CN111932901B (en) | 2019-05-13 | 2019-05-13 | Road vehicle tracking detection apparatus, method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910394469.0A CN111932901B (en) | 2019-05-13 | 2019-05-13 | Road vehicle tracking detection apparatus, method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932901A true CN111932901A (en) | 2020-11-13 |
| CN111932901B CN111932901B (en) | 2022-08-09 |
Family
ID=73282670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910394469.0A Active CN111932901B (en) | 2019-05-13 | 2019-05-13 | Road vehicle tracking detection apparatus, method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932901B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396635A (en) * | 2020-11-30 | 2021-02-23 | 深圳职业技术学院 | Multi-target detection method based on multiple devices in complex environment |
| CN112861971A (en) * | 2021-02-07 | 2021-05-28 | 启迪云控(上海)汽车科技有限公司 | Cross-point road side perception target tracking method and system |
| CN112885097A (en) * | 2021-02-07 | 2021-06-01 | 启迪云控(上海)汽车科技有限公司 | Road side fusion management method and system based on cross-point location |
| CN113240939A (en) * | 2021-03-31 | 2021-08-10 | 浙江吉利控股集团有限公司 | Vehicle early warning method, device, equipment and storage medium |
| CN113593219A (en) * | 2021-06-30 | 2021-11-02 | 北京百度网讯科技有限公司 | Traffic flow statistical method and device, electronic equipment and storage medium |
| CN113657378A (en) * | 2021-07-28 | 2021-11-16 | 讯飞智元信息科技有限公司 | Vehicle tracking method, vehicle tracking system and computing device |
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
| CN115223374A (en) * | 2022-07-15 | 2022-10-21 | 北京精英路通科技有限公司 | Vehicle tracking method and device and electronic equipment |
| CN116844097A (en) * | 2023-07-04 | 2023-10-03 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
| CN113657378B (en) * | 2021-07-28 | 2024-04-26 | 讯飞智元信息科技有限公司 | Vehicle tracking method, vehicle tracking system and computing device |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101568018A (en) * | 2008-04-22 | 2009-10-28 | 中兴通讯股份有限公司 | Rotational-free panoramic photography device and monitoring system comprising same |
| CN101950426A (en) * | 2010-09-29 | 2011-01-19 | 北京航空航天大学 | Vehicle relay tracking method in multi-camera scene |
| CN102034355A (en) * | 2010-12-28 | 2011-04-27 | 丁天 | Feature point matching-based vehicle detecting and tracking method |
| CN102509457A (en) * | 2011-10-09 | 2012-06-20 | 青岛海信网络科技股份有限公司 | Vehicle tracking method and device |
| US20120287278A1 (en) * | 2011-05-15 | 2012-11-15 | Robert Danis | Traffic Violation Photo Enforcement System |
| CN104924988A (en) * | 2015-06-03 | 2015-09-23 | 奇瑞汽车股份有限公司 | Automatic car following system |
| CN104981377A (en) * | 2012-11-27 | 2015-10-14 | 克劳德帕克公司 | Controlling use of a single multi-vehicle parking space using multiple cameras |
| CN107195004A (en) * | 2017-05-17 | 2017-09-22 | 青岛国信胶州湾交通有限公司 | Three video camera Car license recognition toll collection systems and car plate precise recognition method |
| CN107274703A (en) * | 2016-04-07 | 2017-10-20 | 阿里巴巴集团控股有限公司 | Scaling method, the apparatus and system of vehicle location |
| CN107292277A (en) * | 2017-06-30 | 2017-10-24 | 深圳信路通智能技术有限公司 | A kind of double parking stall parking trackings of trackside |
| CN107305627A (en) * | 2016-04-22 | 2017-10-31 | 杭州海康威视数字技术股份有限公司 | A kind of automobile video frequency monitoring method, server and system |
| DE202017107397U1 (en) * | 2017-12-05 | 2017-12-20 | Hochschule Für Technik Und Wirtschaft Des Saarlandes | Device for warning a two-wheeled driver of a collision with another vehicle |
| CN207018785U (en) * | 2017-06-13 | 2018-02-16 | 浙江大华技术股份有限公司 | A kind of twin camera linkage support |
| CN107767673A (en) * | 2017-11-16 | 2018-03-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management method based on multiple-camera, apparatus and system |
| CN107909012A (en) * | 2017-10-30 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of real-time vehicle tracking detection method and device based on disparity map |
| CN108229475A (en) * | 2018-01-03 | 2018-06-29 | 深圳中兴网信科技有限公司 | Wireless vehicle tracking, system, computer equipment and readable storage medium storing program for executing |
| CN108235815A (en) * | 2017-04-07 | 2018-06-29 | 深圳市大疆创新科技有限公司 | Video camera controller, photographic device, camera system, moving body, camera shooting control method and program |
| CN108364480A (en) * | 2018-04-19 | 2018-08-03 | 智慧互通科技有限公司 | System is managed based on the united Roadside Parking of more ball machines |
| CN108510734A (en) * | 2018-03-30 | 2018-09-07 | 深圳市金溢科技股份有限公司 | A kind of information of vehicles matching process of roadside unit and a kind of roadside unit |
| CN108877234A (en) * | 2018-07-24 | 2018-11-23 | 河北德冠隆电子科技有限公司 | The rule-breaking vehicle road occupying tracing detection system and method for four-dimensional outdoor scene traffic simulation |
| CN108877269A (en) * | 2018-08-20 | 2018-11-23 | 清华大学 | A kind of detection of intersection vehicle-state and V2X broadcasting method |
| CN108919256A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | Four-dimensional outdoor scene traffic simulation overspeed of vehicle all-the-way tracking detection alarm system and method |
| CN109191856A (en) * | 2018-08-17 | 2019-01-11 | 江苏信息职业技术学院 | The method of vehicle tracking system and tracking vehicle based on big data |
| CN109302561A (en) * | 2017-07-25 | 2019-02-01 | 中兴通讯股份有限公司 | A kind of image capture method, terminal and storage medium |
-
2019
- 2019-05-13 CN CN201910394469.0A patent/CN111932901B/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101568018A (en) * | 2008-04-22 | 2009-10-28 | 中兴通讯股份有限公司 | Rotational-free panoramic photography device and monitoring system comprising same |
| CN101950426A (en) * | 2010-09-29 | 2011-01-19 | 北京航空航天大学 | Vehicle relay tracking method in multi-camera scene |
| CN102034355A (en) * | 2010-12-28 | 2011-04-27 | 丁天 | Feature point matching-based vehicle detecting and tracking method |
| US20120287278A1 (en) * | 2011-05-15 | 2012-11-15 | Robert Danis | Traffic Violation Photo Enforcement System |
| CN102509457A (en) * | 2011-10-09 | 2012-06-20 | 青岛海信网络科技股份有限公司 | Vehicle tracking method and device |
| CN104981377A (en) * | 2012-11-27 | 2015-10-14 | 克劳德帕克公司 | Controlling use of a single multi-vehicle parking space using multiple cameras |
| CN104924988A (en) * | 2015-06-03 | 2015-09-23 | 奇瑞汽车股份有限公司 | Automatic car following system |
| CN107274703A (en) * | 2016-04-07 | 2017-10-20 | 阿里巴巴集团控股有限公司 | Scaling method, the apparatus and system of vehicle location |
| CN107305627A (en) * | 2016-04-22 | 2017-10-31 | 杭州海康威视数字技术股份有限公司 | A kind of automobile video frequency monitoring method, server and system |
| CN108235815A (en) * | 2017-04-07 | 2018-06-29 | 深圳市大疆创新科技有限公司 | Video camera controller, photographic device, camera system, moving body, camera shooting control method and program |
| CN107195004A (en) * | 2017-05-17 | 2017-09-22 | 青岛国信胶州湾交通有限公司 | Three video camera Car license recognition toll collection systems and car plate precise recognition method |
| CN207018785U (en) * | 2017-06-13 | 2018-02-16 | 浙江大华技术股份有限公司 | A kind of twin camera linkage support |
| CN107292277A (en) * | 2017-06-30 | 2017-10-24 | 深圳信路通智能技术有限公司 | A kind of double parking stall parking trackings of trackside |
| CN109302561A (en) * | 2017-07-25 | 2019-02-01 | 中兴通讯股份有限公司 | A kind of image capture method, terminal and storage medium |
| CN107909012A (en) * | 2017-10-30 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of real-time vehicle tracking detection method and device based on disparity map |
| CN107767673A (en) * | 2017-11-16 | 2018-03-06 | 智慧互通科技有限公司 | A kind of Roadside Parking management method based on multiple-camera, apparatus and system |
| DE202017107397U1 (en) * | 2017-12-05 | 2017-12-20 | Hochschule Für Technik Und Wirtschaft Des Saarlandes | Device for warning a two-wheeled driver of a collision with another vehicle |
| CN108229475A (en) * | 2018-01-03 | 2018-06-29 | 深圳中兴网信科技有限公司 | Wireless vehicle tracking, system, computer equipment and readable storage medium storing program for executing |
| CN108510734A (en) * | 2018-03-30 | 2018-09-07 | 深圳市金溢科技股份有限公司 | A kind of information of vehicles matching process of roadside unit and a kind of roadside unit |
| CN108364480A (en) * | 2018-04-19 | 2018-08-03 | 智慧互通科技有限公司 | System is managed based on the united Roadside Parking of more ball machines |
| CN108877234A (en) * | 2018-07-24 | 2018-11-23 | 河北德冠隆电子科技有限公司 | The rule-breaking vehicle road occupying tracing detection system and method for four-dimensional outdoor scene traffic simulation |
| CN108919256A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | Four-dimensional outdoor scene traffic simulation overspeed of vehicle all-the-way tracking detection alarm system and method |
| CN109191856A (en) * | 2018-08-17 | 2019-01-11 | 江苏信息职业技术学院 | The method of vehicle tracking system and tracking vehicle based on big data |
| CN108877269A (en) * | 2018-08-20 | 2018-11-23 | 清华大学 | A kind of detection of intersection vehicle-state and V2X broadcasting method |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
| CN112396635B (en) * | 2020-11-30 | 2021-07-06 | 深圳职业技术学院 | Multi-target detection method based on multiple devices in complex environment |
| CN112396635A (en) * | 2020-11-30 | 2021-02-23 | 深圳职业技术学院 | Multi-target detection method based on multiple devices in complex environment |
| CN112885097B (en) * | 2021-02-07 | 2023-01-10 | 云控智行(上海)汽车科技有限公司 | Road side fusion management method and system based on cross-point location |
| CN112885097A (en) * | 2021-02-07 | 2021-06-01 | 启迪云控(上海)汽车科技有限公司 | Road side fusion management method and system based on cross-point location |
| CN112861971A (en) * | 2021-02-07 | 2021-05-28 | 启迪云控(上海)汽车科技有限公司 | Cross-point road side perception target tracking method and system |
| CN113240939A (en) * | 2021-03-31 | 2021-08-10 | 浙江吉利控股集团有限公司 | Vehicle early warning method, device, equipment and storage medium |
| CN113593219A (en) * | 2021-06-30 | 2021-11-02 | 北京百度网讯科技有限公司 | Traffic flow statistical method and device, electronic equipment and storage medium |
| CN113593219B (en) * | 2021-06-30 | 2023-02-28 | 北京百度网讯科技有限公司 | Traffic flow statistical method and device, electronic equipment and storage medium |
| CN113657378A (en) * | 2021-07-28 | 2021-11-16 | 讯飞智元信息科技有限公司 | Vehicle tracking method, vehicle tracking system and computing device |
| CN113657378B (en) * | 2021-07-28 | 2024-04-26 | 讯飞智元信息科技有限公司 | Vehicle tracking method, vehicle tracking system and computing device |
| CN115223374A (en) * | 2022-07-15 | 2022-10-21 | 北京精英路通科技有限公司 | Vehicle tracking method and device and electronic equipment |
| CN116844097A (en) * | 2023-07-04 | 2023-10-03 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
| CN116844097B (en) * | 2023-07-04 | 2024-01-23 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932901B (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932901B (en) | Road vehicle tracking detection apparatus, method and storage medium | |
| US10753758B2 (en) | Top-down refinement in lane marking navigation | |
| US10696227B2 (en) | Determining a road surface characteristic | |
| CN106485233B (en) | Method and device for detecting travelable area and electronic equipment | |
| CN106611512B (en) | Method, device and system for processing starting of front vehicle | |
| US11380105B2 (en) | Identification and classification of traffic conflicts | |
| CN102542843A (en) | Early warning method for preventing vehicle collision and device | |
| CN108645375B (en) | Rapid vehicle distance measurement optimization method for vehicle-mounted binocular system | |
| JP2021099793A (en) | Intelligent traffic control system and control method for the same | |
| RU2769921C2 (en) | Methods and systems for automated detection of the presence of objects | |
| CN111094095A (en) | Automatically receiving a travel signal | |
| EP3364336B1 (en) | A method and apparatus for estimating a range of a moving object | |
| CN115470884A (en) | Platform for perception system development of an autopilot system | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN113177976A (en) | Depth estimation method and device, electronic equipment and storage medium | |
| CN104931024B (en) | Obstacle detector | |
| US20220101025A1 (en) | Temporary stop detection device, temporary stop detection system, and recording medium | |
| JP2020201746A (en) | Distance estimation device, distance estimation method, and distance estimation computer program | |
| CN112990117B (en) | Installation data processing method and device based on intelligent driving system | |
| KR102418344B1 (en) | Traffic information analysis apparatus and method | |
| CN114084129A (en) | Fusion-based vehicle automatic driving control method and system | |
| JP2000149181A (en) | Traffic stream measurement system | |
| CN115953328B (en) | Target correction method and system and electronic equipment | |
| WO2022230281A1 (en) | Outside environment recognition device and outside environment recognition system | |
| WO2023178510A1 (en) | Image processing method, device, and system and movable platform |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201119 Address after: Room 603, 6 / F, Roche Plaza, 788 Cheung Sha Wan Road, Kowloon, China Applicant after: Zebra smart travel network (Hong Kong) Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |