CN111325178A - Warning object detection result acquisition method and device, computer equipment and storage medium - Google Patents
Warning object detection result acquisition method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111325178A CN111325178A CN202010145530.0A CN202010145530A CN111325178A CN 111325178 A CN111325178 A CN 111325178A CN 202010145530 A CN202010145530 A CN 202010145530A CN 111325178 A CN111325178 A CN 111325178A
- Authority
- CN
- China
- Prior art keywords
- detection
- target
- vehicle
- target vehicle
- rectangular frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a method and a device for acquiring a detection result of an alarm object, computer equipment and a storage medium. The method comprises the following steps: acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one; if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period; and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object. By adopting the method, the detection efficiency of whether the warning object is placed during parking can be improved.
Description
Technical Field
The present application relates to the field of intelligent transportation technologies, and in particular, to a method and an apparatus for obtaining a detection result of an alert object, a computer device, and a storage medium.
Background
With the development of society and the improvement of living standard of people, the number of vehicles is more and more, so that the safety of driving is more and more important.
Generally, in order to ensure traffic safety, people need to monitor the behavior of a vehicle parked on a road without placing a tripod, so as to reduce the occurrence of traffic accidents. The traditional method is that a monitoring device is arranged on a road to shoot traffic videos, and then behaviors that no tripod is placed in a parking process are screened out through a manual sorting method.
However, the conventional manual sorting method is labor-intensive and time-consuming, and thus the detection efficiency is low and labor is wasted.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for efficiently obtaining a detection result of an alert object.
A warning object detection result acquisition method, comprising:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
In one embodiment, the acquiring the motion trail of the target vehicle in the plurality of frame images in the traffic video includes:
performing target detection on an initial frame image in the plurality of frame images by adopting a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image;
carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on a time sequence and obtained by predicting the position of each target vehicle;
screening out a plurality of detection frame images from the plurality of frame images according to a preset target detection period;
performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image;
and correcting the tracking sequence according to the detection rectangular frame to obtain the motion track of the target vehicle.
In one embodiment, the modifying the tracking sequence according to the detection rectangular frame to obtain the motion trajectory of the target vehicle includes:
judging whether the detected vehicle rectangular frame is matched with the tracking rectangular frame corresponding to the moment;
if so, replacing the tracking rectangular frame matched with the detection vehicle rectangular frame in the tracking sequence by the detection vehicle rectangular frame to obtain the motion track of the target vehicle;
and if not, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
In one embodiment, the determining whether the detected vehicle rectangular frame matches the tracking rectangular frame at the corresponding time includes:
acquiring the intersection ratio of the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding moment;
if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame;
and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment.
In one embodiment, the obtaining whether the warning object exists in the detection area in the rear direction of the target vehicle to obtain the detection result of the warning object includes:
identifying a target vehicle in the target frame image by adopting a preset identification model to obtain the tail direction of the target vehicle;
acquiring areas within the lengths of the three vehicle bodies in the tail direction of the vehicle as detection areas;
and carrying out target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
In one embodiment, the performing, by using the detection algorithm, the target detection in the detection area to obtain the detection result of the warning object includes:
identifying whether a warning object exists in the detection area by adopting the detection algorithm;
if so, determining that the detection result of the warning object is that the warning object is placed for parking;
if not, determining that the detection result of the warning object is that no warning object is placed when the vehicle is parked.
In one embodiment, the method further comprises:
and if the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold value and the running speed of the target vehicles is less than or equal to a preset speed threshold value, determining that the current traffic is in a congestion state.
An alarm detection result acquisition device, the device comprising:
the acquisition module is used for acquiring the motion trail of the target vehicle in a plurality of frame images in the traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
the processing module is used for determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period when the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, and acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle or not when the running speed of the target vehicle is smaller than or equal to the preset speed threshold and is larger than or equal to the preset number threshold, so as to obtain a warning object detection result.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
According to the method and the device for acquiring the detection result of the warning object, the computer equipment acquires the motion trail of the target vehicle in the plurality of frame images in the traffic video, and if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than the preset number threshold, the running speed of each target vehicle in each speed detection period is determined according to the motion trail of the target vehicle in each speed detection period. And then when the number of times that the running speed of the target vehicle is smaller than the preset speed threshold value is larger than or equal to the preset number of times threshold value, the computer equipment determines that the current vehicle is in a parking state and is not parked due to congestion, and the computer equipment acquires whether the warning object exists in a detection area in the tail direction of the target vehicle or not to obtain a detection result of the warning object. According to the method, the movement track of the target vehicle is automatically acquired through computer equipment, whether the warning object exists in the detection area or not is automatically acquired when the vehicle is in a parking state caused by non-congestion, and the detection result of the warning object is obtained, so that the detection result of the warning object for automatically identifying whether the vehicle is parked or not in a traffic video is realized, the situations of wrong detection, missing detection and the like caused by the traditional manual sorting mode are avoided, and the problems of low efficiency and manpower waste caused by manual sorting are solved. Through the more accurate relevance ratio, the driving behavior is further normalized by people, and the occurrence probability of traffic accidents is further reduced.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for obtaining a detection result of an alarm according to an embodiment;
FIG. 2 is a schematic flow chart illustrating a method for obtaining an alarm detection result according to yet another embodiment;
FIG. 3 is a schematic flow chart illustrating a method for obtaining an alarm detection result according to yet another embodiment;
FIG. 4 is a schematic flowchart of a method for obtaining an alarm detection result according to yet another embodiment;
FIG. 5 is a block diagram of an apparatus for obtaining a detection result of an alarm in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
It should be noted that the execution subject of the following method embodiments may be an alarm detection result obtaining device, which may be implemented by software, hardware, or a combination of software and hardware as part or all of the above computer device. The following method embodiments are described by taking the execution subject as the computer device as an example.
Fig. 1 is a schematic flow chart of a method for obtaining a detection result of an alert object according to an embodiment. The computer equipment related to the embodiment automatically identifies the traffic video to obtain the specific process of the detection result of the warning object. As shown in fig. 1, includes:
s10, obtaining the motion trail of the target vehicle in the plurality of frame images in the traffic video; the plurality of frame images are images with time sequence, and the number of the target vehicles is at least one.
Specifically, the computer device may obtain the traffic video from the memory, and may also receive the traffic video shot by the monitoring device, which is not limited in this embodiment. The computer device can identify a plurality of frame images in the traffic video, so as to identify the target vehicles appearing in the video, and acquire the positions of the target vehicles in each frame image. Alternatively, the number of the target vehicles may be one or two or more, when there are a plurality of target vehicles, each target vehicle needs to acquire the detection result of the warning object, and the processing manner of each target vehicle may be the same. Alternatively, the position of each vehicle may be represented by a position frame, for example, a rectangular frame, and since the frame image may be a plurality of images arranged in time sequence, the computer device may be capable of forming a respective movement track of each target vehicle according to the position frame in each frame image. For example, the computer device may perform target detection on a plurality of time-continuous frame images to obtain position frames representing positions of vehicles in each frame image, then perform pairwise correlation determination on the position frames detected by two frame images adjacent to each other at a time, and use the two position frames with the strongest correlation as different positions of the same target vehicle at two adjacent times, and so on to obtain position frames of the same target vehicle in different frame images, thereby forming a motion trajectory of each target vehicle. Optionally, the computer device may also predict the position of each target vehicle by using a tracking algorithm, so as to obtain the motion trajectory of the target vehicle; optionally, the computer device may also determine the moving track of the target vehicle by using a combination of detection and tracking, which is not limited in this embodiment.
And S20, if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period.
Specifically, the computer device may screen a target frame image from the plurality of frame images, where the target frame image may be selected arbitrarily, or may use a last frame of the plurality of frame images as a target frame image, and this embodiment does not limit this. And then the computer device judges whether the number of the target vehicles in the target frame image is smaller than a preset number threshold, if so, the computer device determines the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period, for example, the computer device determines the displacement of the target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period, and then calculates the running speed of the target vehicle in the current speed detection period according to the ratio of the displacement to the speed detection period. Optionally, the setting of the number threshold may be set empirically, and may also be adjusted according to a shooting range of a camera of the monitoring device, where if the shooting range of the camera is large, the number threshold may be set to be large, and if the shooting range of the camera is small, the number threshold may be set to be small.
S30, when the number of times that the running speed of the target vehicle is smaller than or equal to the preset speed threshold value is larger than or equal to the preset number threshold value, whether a warning object exists in the detection area in the tail direction of the target vehicle or not is obtained, and a warning object detection result is obtained.
Specifically, the computer device performs, for each target vehicle, an operation of acquiring a travel speed of the target vehicle at each speed detection period, and determining whether a current travel speed is less than a preset speed threshold, and if the current travel speed is less than the preset speed threshold, recording that the travel speed is less than the preset speed threshold once, and if the current travel speed is greater than or equal to the preset speed threshold, not recording. The preset speed threshold may be a smaller speed value, for example, 0 km/h or 0.01 km/h, which is not limited in this embodiment, and since the speed per hour of 0.01 km may be caused by an error, the preset speed threshold may be any value as long as it can represent that the vehicle is parked. When the number of times that the running speed of the same target vehicle in different speed detection periods is smaller than or equal to the preset speed threshold is greater than or equal to the number threshold, for example, greater than five times, the computer device determines that the current vehicle is in a parking state, and meanwhile, whether the current vehicle is parked due to traffic jam or not can be determined because whether the number of the target vehicles in the target frame image is smaller than the preset number threshold or not, and whether an abnormal running condition exists or not and therefore parking is needed can be determined, whether a driver correctly places a warning object needs to be detected at the time, and therefore the computer device obtains whether the warning object exists in a detection area in the tail direction of the target vehicle or not, and obtains a warning object detection result. Alternatively, the warning object may be a tripod or other form of warning object, such as a colorful warning board, as long as the warning object can play a warning role.
In this embodiment, the computer device determines, by acquiring the motion trajectory of the target vehicle in the plurality of frame images in the traffic video, if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than the preset number threshold, the running speed of each target vehicle in each speed detection period according to the motion trajectory of the target vehicle in each speed detection period. And then when the number of times that the running speed of the target vehicle is smaller than the preset speed threshold value is larger than or equal to the preset number of times threshold value, the computer equipment determines that the current vehicle is in a parking state and is not parked due to congestion, and the computer equipment acquires whether the warning object exists in a detection area in the tail direction of the target vehicle or not to obtain a detection result of the warning object. According to the method, the movement track of the target vehicle is automatically acquired through computer equipment, whether the warning object exists in the detection area or not is automatically acquired when the vehicle is in a parking state caused by non-congestion, and the detection result of the warning object is obtained, so that the detection result of the warning object for automatically identifying whether the vehicle is parked or not in a traffic video is realized, the situations of wrong detection, missing detection and the like caused by the traditional manual sorting mode are avoided, and the problems of low efficiency and manpower waste caused by manual sorting are solved. Through the more accurate relevance ratio, the driving behavior is further normalized by people, and the occurrence probability of traffic accidents is further reduced.
Optionally, when the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold, and the running speed of the target vehicle is less than or equal to a preset speed threshold, it is determined that the current traffic is in a congestion state. The computer device determines that the number of the target vehicles in the target frame image is greater than or equal to the number threshold, and the running speed of the target vehicles is less than or equal to a preset speed threshold, the computer device determines that the current traffic is in a congestion state, the target vehicles run at a low speed, for example, the speed of time is 0 kilometer, but the number of the target vehicles in the target frame image exceeds the number threshold, and it is determined that the plurality of vehicles are all in a parking state, and it can be determined that the plurality of vehicles are parked due to congestion, and the computer device does not perform a subsequent acquisition process of the detection result of the warning object. According to the method, the computer equipment can determine that the current traffic is in a congestion state by determining that the number of the target vehicles in the target frame image is greater than or equal to the number threshold and the running speed of the target vehicles is less than a preset speed threshold, so that the subsequent process of acquiring the detection result of the warning object does not need to be continuously executed, the processing steps are reduced, and the resources of the computer equipment are saved.
Optionally, on the basis of the foregoing embodiment, a possible implementation manner of the foregoing step S10 may also be as shown in fig. 2, and includes:
s11, performing target detection on the initial frame image in the plurality of frame images by adopting a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image.
Specifically, the computer device screens out an initial frame image from the plurality of frame images, where the initial frame image may be a first image of the plurality of frame images, or may be a first image of a target vehicle appearing at the beginning, so as to avoid invalid detection, or an image arbitrarily selected from a section of traffic video is used as the initial frame image, which is not limited in this embodiment. And the computer equipment adopts a preset detection algorithm to carry out target detection on a plurality of initial frame images, so as to obtain an initial rectangular frame of at least one target vehicle in the initial frame images. Optionally, the detection algorithm may be a Youonly look once algorithm, abbreviated as YOLO algorithm, or a Single Shot Multi Box Detector, abbreviated as SSD, or other target detection algorithm, as long as an initial rectangular frame representing the position of the target vehicle can be detected, which is not limited in this embodiment. The position of the initial rectangular frame obtained by detection can be more accurate and efficient by adopting the YOLO algorithm.
S12, carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on time sequence obtained by performing position prediction on each target vehicle.
Specifically, the computer device performs target tracking processing based on the initial rectangular frame of the target vehicle, that is, estimates the position of each subsequent target vehicle based on the initial rectangular frame, thereby obtaining a tracking rectangular frame of each target vehicle at a plurality of subsequent times, and each initial rectangular frame and the tracking rectangular frame estimated based on the initial rectangular frame form a tracking sequence representing the target vehicle in time order. Alternatively, the computer device tracks the target, and may input an initial rectangular box of each target vehicle into a preset tracking model, so as to calculate a tracking sequence of each target vehicle. It should be noted that the tracking model may be implemented based on a tracking algorithm, such as a kernel correlation filtering algorithm, or may be implemented by other tracking algorithms, which is not limited in this embodiment of the present application.
And S13, screening a plurality of detection frame images from the plurality of frame images according to a preset target detection period.
Specifically, the computer device screens, according to a preset target detection period T, frame images corresponding to the time of each target vehicle inspection period from the plurality of frame images as the plurality of detection frame images. Alternatively, the computer device may number the frame images in a chronological order, for example, starting from 0, adding 1 to the number of each frame image, numbering the frame images in a chronological order by integers of 0, 1, 2, 3, 4, 5, 6.
And S14, performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image.
Specifically, the computer device performs target detection on each detection frame image by using a detection algorithm to obtain a detection rectangular frame of the vehicle in each detection frame image. It should be noted that the detection algorithm may be as described above, and is not described herein again. Alternatively, since the vehicle may join the field of view of the image pickup apparatus at any time, the number of detected rectangular frames obtained in the detection frame image may be greater than that of the preceding target vehicle, while there is also a field of view where the vehicle leaves the image pickup apparatus at any time, and thus the number of detected rectangular frames may be less than that of the preceding target vehicle. Of course, there may be a case where the number of detected rectangular frames is the same as that of the target vehicle, but the same object is not represented, and in this case, the determination of the correlation between the rectangular frames at adjacent times may be used to determine whether the rectangular frames at adjacent times are the same vehicle object.
And S15, correcting the tracking sequence according to the detection rectangular frame to obtain the motion trail of the target vehicle.
Specifically, the computer device may modify the tracking sequence based on the detected rectangular frame, and optionally, may replace the tracking rectangular frame corresponding to the detected rectangular frame at the time, as in the embodiment shown in fig. 3 below; naturally, the tracking algorithm may be continuously adopted to re-estimate the tracking rectangular frame at a subsequent time based on the replaced detection rectangular frame, and the tracking sequence is further replaced based on a re-estimation result, so that the tracking sequence can be periodically corrected, and the obtained motion trajectory of the target vehicle is more accurate.
Optionally, one possible implementation manner of this step S15 may also be as shown in fig. 3, including:
and S151, judging whether the detected vehicle rectangular frame is matched with the tracking rectangular frame corresponding to the moment. If yes, go to S152A; if not, go to S152B.
S152A, replacing the tracking rectangular frame matched with the detected vehicle rectangular frame in the tracking sequence with the detected vehicle rectangular frame to obtain the motion trail of the target vehicle.
S152B, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
Specifically, the computer device may determine one by one whether any of the detected vehicle rectangular frames matches any of the tracked rectangular frames at the corresponding time. That is, when the number of the detected vehicle rectangular frame and the number of the tracking rectangular frames at the corresponding time are not unique, it may be determined whether any detected vehicle rectangular frame and any tracking rectangular frame are matched pairwise.
If the two are matched, the two are the same target vehicle, then the step S152A is executed, that is, the detected vehicle rectangular frame is used to replace the matched tracking rectangular frame in the tracking sequence, so as to modify the tracking sequence and obtain the motion track of the target vehicle, and the detected vehicle rectangular frame is used to replace the matched tracking rectangular frame in the tracking sequence, so as to periodically modify the motion track of the target vehicle, thereby making the motion track more accurate.
If the target vehicle represented by the tracking rectangular frame does not exceed the visual field of the camera device, that is, the target vehicle is not required to be detected, the step S152B is executed, that is, the motion track of the target vehicle corresponding to the tracking rectangular frame is discarded, and recording and operation are not performed, so that the operation of an invalid object is avoided, and the operation resource is saved. Meanwhile, the computer device confirms that the detected vehicle rectangular frame is a newly added vehicle, namely, the vehicle enters the visual field of the camera device at the moment, the newly added vehicle appears in the detected frame image, therefore, the detected vehicle rectangular frame of the vehicle is added in the detected vehicle rectangular frame, however, the newly added vehicle is not tracked in the tracking sequence, therefore, the estimated tracking rectangular frame of the vehicle is not available in the tracking rectangular frame at the moment, the computer device can regard the detected vehicle rectangular frame as the new target vehicle, and generate the motion trail of the new target vehicle based on the detected vehicle rectangular frame, thereby realizing the detection of the newly added target vehicle in combination with the actual condition of traffic, avoiding the omission of the newly added vehicle, and further, the object selection of the detected target vehicle is in accordance with the actual road condition, so that the method is more accurate. The description of the motion trajectories of other target vehicles in the above embodiments may be adopted for the manner of acquiring the motion trajectories of the newly added target vehicles, and details are not described here.
Optionally, determining whether the two rectangular boxes match may include: acquiring the intersection ratio of the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding moment; if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame; and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment. Specifically, the computer device obtains an intersection and union ratio (IOU) of any one of the detection frame images and any one of the tracking rectangular frames corresponding to the time, that is, a ratio of an intersection area (an overlapping portion) of the two and a union area (all areas of the two). When the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame, namely the detected vehicle rectangular frame and the tracking rectangular frame are related and are position frames of the same target vehicle; and when the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment, namely that the correlation between the detected vehicle rectangular frame and the tracking rectangular frame is low, and the detected vehicle rectangular frame and the tracking rectangular frame are not the position frames of the same target vehicle. The method can determine whether the two rectangular frames are matched or not based on the intersection ratio of the two rectangular frames, so that the method is simple to implement and high in accuracy. Alternatively, the cross-over ratio threshold may be set to seventy to ninety percent, or other values as desired, to ensure that the degree of correlation between the two is within the desired range. Optionally, when the intersection ratio is eighty percent of the threshold, the obtained judgment on the degree of correlation is more reasonable, so that the obtained motion trajectory is more accurate.
In this embodiment, the computer device performs target detection on an initial frame image in the plurality of frame images by using a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image, and then performs target tracking processing on the initial rectangular frame of each target vehicle by using a preset tracking model to obtain a tracking sequence of each target vehicle, so that a tracking sequence representing an estimated position of the vehicle can be estimated. The computer equipment screens a plurality of detection frame images from a plurality of frame images according to a preset target detection period, target detection is carried out on the plurality of detection frame images by adopting a detection algorithm to obtain a detection rectangular frame in each detection frame image, and then the tracking sequence is corrected according to the detection rectangular frame to obtain the motion track of a target vehicle. Meanwhile, the efficiency and the accuracy can be adjusted by setting different target detection periods, so that the application scene is richer.
Optionally, on the basis of the foregoing embodiment, step S30 may also include, as shown in fig. 4:
and S31, recognizing the target vehicle in the target frame image by adopting a preset recognition model to obtain the tail direction of the target vehicle.
Specifically, the computer device may determine whether to detect placement of the warning object when it is determined that the vehicle is parked due to non-traffic congestion. And the computer equipment identifies the target vehicle in the target frame image by adopting a preset identification model so as to obtain the tail direction of the target vehicle. When the number of the target vehicles is multiple, the tail direction of each target vehicle is identified. Optionally, the recognition model may be a neural network model obtained by training a plurality of training images labeled with images of the head and the tail of the vehicle.
And S32, acquiring areas within the three vehicle body lengths in the vehicle tail direction as detection areas.
Specifically, the computer device may recognize the vehicle body length, and may also receive a set value of the vehicle body length input by the user. Then, the area within three vehicle body lengths in the vehicle rear direction is used as a detection area. The detection area represents an area where warning objects need to be reasonably placed when parking occurs in an abnormal condition.
And S33, performing target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
Specifically, the computer device may perform target detection on the warning object in the detection area by using a detection algorithm to obtain a detection result of the warning object. Optionally, a detection algorithm may be adopted to identify whether an alert exists in the detection area, for example, whether a tripod exists in the detection area, and if so, it is determined that the detection result of the alert is a parking placement alert; and if the warning object does not exist, determining that the warning object is not placed when the vehicle is parked according to the detection result of the warning object. Optionally, when the detection result of the warning object indicates that the warning object is not placed during parking, prompt information or warning for the target vehicle can be output, so that the image and the vehicle representing the violation are automatically sorted out, and people can conveniently recognize the image and the vehicle. For the description of the detection algorithm, reference is made to the foregoing description, which is not repeated herein.
In the embodiment, the computer device adopts a preset recognition model to recognize the target vehicle in the target frame image to obtain the tail direction of the target vehicle, obtains the regions within three vehicle body lengths of the tail direction as the detection regions, and adopts a preset detection algorithm to detect the target in the detection regions, thereby realizing automatic judgment of whether the warning object exists in a reasonable area, realizing the detection result of the warning object for automatically identifying whether the warning object is placed when the vehicle stops in the traffic video, avoiding the conditions of wrong detection, missing detection and the like caused by the traditional manual sorting mode and the problems of low efficiency and manpower waste caused by the manual sorting, the method can greatly improve the accuracy of the detection result of the warning object, further improve the detection rate, and the efficiency of obtaining of warning thing testing result that can be very big improvement, practiced thrift manpower and time. Through the more accurate relevance ratio, the driving behavior is further normalized by people, and the occurrence probability of traffic accidents is further reduced.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 5, there is provided an alarm detection result obtaining apparatus, including:
the acquisition module 100 is configured to acquire a motion trajectory of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
the processing module 200 is configured to determine, in each speed detection period, a travel speed of each target vehicle in each speed detection period according to a motion trajectory of the target vehicle when the number of the target vehicles in a target frame image of the plurality of frame images is smaller than a preset number threshold, and obtain whether a warning object exists in a detection area in a tail direction of the target vehicle when the travel speed of the target vehicle is smaller than or equal to the preset speed threshold for a number of times that is greater than or equal to the preset number threshold, so as to obtain a warning object detection result.
In an embodiment, the processing module 200 is specifically configured to perform target detection on an initial frame image in the plurality of frame images by using a preset detection algorithm, so as to obtain an initial rectangular frame of at least one target vehicle in the initial frame image; carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on a time sequence and obtained by predicting the position of each target vehicle; screening out a plurality of detection frame images from the plurality of frame images according to a preset target detection period; performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image; and correcting the tracking sequence according to the detection rectangular frame to obtain the motion track of the target vehicle.
In an embodiment, the processing module 200 is specifically configured to determine whether the detected vehicle rectangular frame matches the tracking rectangular frame corresponding to the time; if so, replacing the tracking rectangular frame matched with the detection vehicle rectangular frame in the tracking sequence by the detection vehicle rectangular frame to obtain the motion track of the target vehicle; and if not, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
In one embodiment, the processing module 200 is specifically configured to obtain an intersection ratio between the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding time; if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame; and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment.
In an embodiment, the processing module 200 is specifically configured to identify a target vehicle in the target frame image by using a preset identification model, so as to obtain a tail direction of the target vehicle; acquiring areas within the lengths of the three vehicle bodies in the tail direction of the vehicle as detection areas; and carrying out target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
In one embodiment, the processing module 200 is specifically configured to identify whether an alert exists in the detection area using the detection algorithm; if so, determining that the detection result of the warning object is that the warning object is placed for parking; if not, determining that the detection result of the warning object is that no warning object is placed when the vehicle is parked.
In one embodiment, the processing module 200 is further configured to determine that the current traffic is in a congested state when the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold and the running speed of the target vehicle is less than or equal to a preset speed threshold.
For the specific limitation of the warning object detection result obtaining device, reference may be made to the above limitation on the warning object detection result obtaining method, and details are not repeated here. All modules in the warning object detection result acquisition device can be completely or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is for storing a plurality of frame images. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for obtaining the detection result of the warning object.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
performing target detection on an initial frame image in the plurality of frame images by adopting a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image;
carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on a time sequence and obtained by predicting the position of each target vehicle;
screening out a plurality of detection frame images from the plurality of frame images according to a preset target detection period;
performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image;
and correcting the tracking sequence according to the detection rectangular frame to obtain the motion track of the target vehicle.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
judging whether the detected vehicle rectangular frame is matched with the tracking rectangular frame corresponding to the moment;
if so, replacing the tracking rectangular frame matched with the detection vehicle rectangular frame in the tracking sequence by the detection vehicle rectangular frame to obtain the motion track of the target vehicle;
and if not, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the intersection ratio of the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding moment;
if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame;
and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
identifying a target vehicle in the target frame image by adopting a preset identification model to obtain the tail direction of the target vehicle;
acquiring areas within the lengths of the three vehicle bodies in the tail direction of the vehicle as detection areas;
and carrying out target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
identifying whether a warning object exists in the detection area by adopting the detection algorithm;
if so, determining that the detection result of the warning object is that the warning object is placed for parking;
if not, determining that the detection result of the warning object is that no warning object is placed when the vehicle is parked.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and if the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold value and the running speed of the target vehicles is less than or equal to a preset speed threshold value, determining that the current traffic is in a congestion state.
It should be clear that, in the embodiments of the present application, the process of executing the computer program by the processor is consistent with the process of executing the steps in the above method, and specific reference may be made to the description above.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing target detection on an initial frame image in the plurality of frame images by adopting a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image;
carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on a time sequence and obtained by predicting the position of each target vehicle;
screening out a plurality of detection frame images from the plurality of frame images according to a preset target detection period;
performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image;
and correcting the tracking sequence according to the detection rectangular frame to obtain the motion track of the target vehicle.
In one embodiment, the computer program when executed by the processor further performs the steps of:
judging whether the detected vehicle rectangular frame is matched with the tracking rectangular frame corresponding to the moment;
if so, replacing the tracking rectangular frame matched with the detection vehicle rectangular frame in the tracking sequence by the detection vehicle rectangular frame to obtain the motion track of the target vehicle;
and if not, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the intersection ratio of the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding moment;
if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame;
and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying a target vehicle in the target frame image by adopting a preset identification model to obtain the tail direction of the target vehicle;
acquiring areas within the lengths of the three vehicle bodies in the tail direction of the vehicle as detection areas;
and carrying out target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying whether a warning object exists in the detection area by adopting the detection algorithm;
if so, determining that the detection result of the warning object is that the warning object is placed for parking;
if not, determining that the detection result of the warning object is that no warning object is placed when the vehicle is parked.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and if the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold value and the running speed of the target vehicles is less than or equal to a preset speed threshold value, determining that the current traffic is in a congestion state.
It should be clear that, in the embodiments of the present application, the process executed by the processor by the computer program is consistent with the execution process of each step in the above method, and specific reference may be made to the description above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for obtaining a detection result of an alarm, the method comprising:
acquiring the motion trail of a target vehicle in a plurality of frame images in a traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
if the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period;
and when the running speed of the target vehicle is less than or equal to the preset speed threshold value for more than or equal to the preset time threshold value, acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle, and acquiring a detection result of the warning object.
2. The method of claim 1, wherein the obtaining the motion trajectory of the target vehicle in the plurality of frame images in the traffic video comprises:
performing target detection on an initial frame image in the plurality of frame images by adopting a preset detection algorithm to obtain an initial rectangular frame of at least one target vehicle in the initial frame image;
carrying out target tracking processing on the initial rectangular frame of each target vehicle by adopting a preset tracking model to obtain a tracking sequence of each target vehicle; the tracking sequence is a tracking rectangular frame based on a time sequence and obtained by predicting the position of each target vehicle;
screening out a plurality of detection frame images from the plurality of frame images according to a preset target detection period;
performing target detection on the detection frame images by adopting the detection algorithm to obtain a detection rectangular frame in each detection frame image;
and correcting the tracking sequence according to the detection rectangular frame to obtain the motion track of the target vehicle.
3. The method according to claim 2, wherein the modifying the tracking sequence according to the detection rectangular frame to obtain the motion trail of the target vehicle comprises:
judging whether the detected vehicle rectangular frame is matched with the tracking rectangular frame corresponding to the moment;
if so, replacing the tracking rectangular frame matched with the detection vehicle rectangular frame in the tracking sequence by the detection vehicle rectangular frame to obtain the motion track of the target vehicle;
and if not, discarding the motion trail of the target vehicle corresponding to the tracking rectangular frame, taking the detected vehicle rectangular frame as a new target vehicle, and generating the motion trail of the new target vehicle based on the detected vehicle rectangular frame.
4. The method of claim 3, wherein the determining whether the detected vehicle rectangular frame matches the tracking rectangular frame at the corresponding time comprises:
acquiring the intersection ratio of the detected vehicle rectangular frame and the tracking rectangular frame at the corresponding moment;
if the intersection ratio is larger than or equal to a preset intersection ratio threshold value, determining that the detected vehicle rectangular frame is matched with the tracking rectangular frame;
and if the intersection ratio is smaller than the intersection ratio threshold value, determining that the detected vehicle rectangular frame is not matched with the tracking rectangular frame at the corresponding moment.
5. The method according to claim 1, wherein the obtaining whether the warning object exists in the detection area of the tail direction of the target vehicle to obtain the detection result of the warning object comprises:
identifying a target vehicle in the target frame image by adopting a preset identification model to obtain the tail direction of the target vehicle;
acquiring areas within the lengths of the three vehicle bodies in the tail direction of the vehicle as detection areas;
and carrying out target detection in the detection area by adopting a preset detection algorithm to obtain the detection result of the warning object.
6. The method of claim 5, wherein said detecting the target in the detection area using the detection algorithm to obtain the detection result of the warning object comprises:
identifying whether a warning object exists in the detection area by adopting the detection algorithm;
if so, determining that the detection result of the warning object is that the warning object is placed for parking;
if not, determining that the detection result of the warning object is that no warning object is placed when the vehicle is parked.
7. The method according to any one of claims 1 to 6, further comprising:
and if the number of the target vehicles in the target frame image is greater than or equal to a preset number threshold value and the running speed of the target vehicles is less than or equal to a preset speed threshold value, determining that the current traffic is in a congestion state.
8. An alarm detection result acquisition device, characterized in that the device comprises:
the acquisition module is used for acquiring the motion trail of the target vehicle in a plurality of frame images in the traffic video; the frame images are images with time sequence, and the number of the target vehicles is at least one;
the processing module is used for determining the running speed of each target vehicle in each speed detection period according to the motion track of the target vehicle in each speed detection period when the number of the target vehicles in the target frame images in the plurality of frame images is smaller than a preset number threshold, and acquiring whether a warning object exists in a detection area in the tail direction of the target vehicle or not when the running speed of the target vehicle is smaller than or equal to the preset speed threshold and is larger than or equal to the preset number threshold, so as to obtain a warning object detection result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010145530.0A CN111325178A (en) | 2020-03-05 | 2020-03-05 | Warning object detection result acquisition method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010145530.0A CN111325178A (en) | 2020-03-05 | 2020-03-05 | Warning object detection result acquisition method and device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111325178A true CN111325178A (en) | 2020-06-23 |
Family
ID=71169168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010145530.0A Pending CN111325178A (en) | 2020-03-05 | 2020-03-05 | Warning object detection result acquisition method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111325178A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112053382A (en) * | 2020-08-04 | 2020-12-08 | 浙江大华技术股份有限公司 | Access & exit monitoring method, equipment and computer readable storage medium |
CN112560664A (en) * | 2020-12-11 | 2021-03-26 | 清华大学苏州汽车研究院(吴江) | Method, device, medium and electronic equipment for detecting intrusion of forbidden region |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101488290A (en) * | 2009-02-27 | 2009-07-22 | 清华大学 | Pre-alarm method for preventing rear-end collision by following car |
CN106120604A (en) * | 2016-07-11 | 2016-11-16 | 无锡信大气象传感网科技有限公司 | A kind of anti-slip Smartway alarming device |
CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
CN107499229A (en) * | 2017-09-25 | 2017-12-22 | 许昌学院 | Traffic warning mark |
US20180096595A1 (en) * | 2016-10-04 | 2018-04-05 | Street Simplified, LLC | Traffic Control Systems and Methods |
CN110110590A (en) * | 2019-03-25 | 2019-08-09 | 费今歌 | The determination method and Related product in congestion lane |
CN110598511A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Method, device, electronic equipment and system for detecting green light running event |
CN110689729A (en) * | 2018-07-05 | 2020-01-14 | 深圳市以捷智慧交通科技有限公司 | Fault emergency processing system and method for adjacent traffic lanes |
-
2020
- 2020-03-05 CN CN202010145530.0A patent/CN111325178A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101488290A (en) * | 2009-02-27 | 2009-07-22 | 清华大学 | Pre-alarm method for preventing rear-end collision by following car |
CN106327863A (en) * | 2015-07-06 | 2017-01-11 | 北京文安智能技术股份有限公司 | Method, device and system for detection and early warning of vehicle congestion |
CN106120604A (en) * | 2016-07-11 | 2016-11-16 | 无锡信大气象传感网科技有限公司 | A kind of anti-slip Smartway alarming device |
US20180096595A1 (en) * | 2016-10-04 | 2018-04-05 | Street Simplified, LLC | Traffic Control Systems and Methods |
CN107499229A (en) * | 2017-09-25 | 2017-12-22 | 许昌学院 | Traffic warning mark |
CN110598511A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Method, device, electronic equipment and system for detecting green light running event |
CN110689729A (en) * | 2018-07-05 | 2020-01-14 | 深圳市以捷智慧交通科技有限公司 | Fault emergency processing system and method for adjacent traffic lanes |
CN110110590A (en) * | 2019-03-25 | 2019-08-09 | 费今歌 | The determination method and Related product in congestion lane |
Non-Patent Citations (2)
Title |
---|
JACK G ET AL: "《Real-Time Detection and Recognition of Road Traffic Signs》" * |
范磊: "《面向城市道路场景的语义分割模型研究》" * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112053382A (en) * | 2020-08-04 | 2020-12-08 | 浙江大华技术股份有限公司 | Access & exit monitoring method, equipment and computer readable storage medium |
CN112560664A (en) * | 2020-12-11 | 2021-03-26 | 清华大学苏州汽车研究院(吴江) | Method, device, medium and electronic equipment for detecting intrusion of forbidden region |
CN112560664B (en) * | 2020-12-11 | 2023-08-01 | 清华大学苏州汽车研究院(吴江) | Method, device, medium and electronic equipment for intrusion detection in forbidden area |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8199971B2 (en) | Object detection system with improved object detection accuracy | |
CN110889328B (en) | Method, device, electronic equipment and storage medium for detecting road traffic condition | |
WO2020047907A1 (en) | License plate failed-detection estimation method and processing terminal | |
CN109766867B (en) | Vehicle running state determination method and device, computer equipment and storage medium | |
CN112799826B (en) | Intelligent analysis algorithm selection method, device and system and electronic equipment | |
CN111325178A (en) | Warning object detection result acquisition method and device, computer equipment and storage medium | |
CN110225236B (en) | Method and device for configuring parameters for video monitoring system and video monitoring system | |
CN109948436B (en) | Method and device for monitoring vehicles on road | |
CN114495025A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
CN114040094B (en) | Preset position adjusting method and device based on cradle head camera | |
CN111724607B (en) | Steering lamp use detection method and device, computer equipment and storage medium | |
CN112560546A (en) | Throwing behavior detection method and device and storage medium | |
CN113361299B (en) | Abnormal parking detection method and device, storage medium and electronic equipment | |
CN112906428B (en) | Image detection region acquisition method and space use condition judgment method | |
CN113160272A (en) | Target tracking method and device, electronic equipment and storage medium | |
CN112580565A (en) | Lane line detection method, lane line detection device, computer device, and storage medium | |
CN117115752A (en) | Expressway video monitoring method and system | |
CN111526475A (en) | Target vehicle tracking method and device, electronic equipment and storage medium | |
CN114882709A (en) | Vehicle congestion detection method and device and computer storage medium | |
CN112906495B (en) | Target detection method and device, electronic equipment and storage medium | |
CN109740518B (en) | Method and device for determining object in video | |
CN111540217B (en) | Mask matrix-based intelligent average vehicle speed monitoring method and system | |
CN114373081A (en) | Image processing method and device, electronic device and storage medium | |
Bertozzi et al. | Fast vision-based road tunnel detection | |
CN114049771A (en) | Bimodal-based traffic anomaly detection method and system and storage medium |
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 |