CN113561896A - Method and device for determining abnormality of brake lamp of vehicle - Google Patents
Method and device for determining abnormality of brake lamp of vehicle Download PDFInfo
- Publication number
- CN113561896A CN113561896A CN202110806639.9A CN202110806639A CN113561896A CN 113561896 A CN113561896 A CN 113561896A CN 202110806639 A CN202110806639 A CN 202110806639A CN 113561896 A CN113561896 A CN 113561896A
- Authority
- CN
- China
- Prior art keywords
- brake
- vehicle
- lamp
- target vehicle
- state
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000005856 abnormality Effects 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 70
- 238000012544 monitoring process Methods 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012216 screening Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q11/00—Arrangement of monitoring devices for devices provided for in groups B60Q1/00 - B60Q9/00
- B60Q11/005—Arrangement of monitoring devices for devices provided for in groups B60Q1/00 - B60Q9/00 for lighting devices, e.g. indicating if lamps are burning or not
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Lighting Device Outwards From Vehicle And Optical Signal (AREA)
Abstract
The present application relates to a brake lamp abnormality determination method and a brake lamp abnormality determination apparatus for a vehicle, wherein the method includes: acquiring a monitoring video containing at least one vehicle to be processed; determining a sequence of video frames to be processed of a target vehicle based on the monitoring video; the video frame sequence to be processed comprises at least two brake lamps of the target vehicle, and the target vehicle comprises at least one vehicle in the vehicle to be processed; determining that the target vehicle is in a braking state within a collection time period of the surveillance video; and determining the vehicle lamp states of at least two brake lamps based on the video frame sequence to be processed, and determining whether at least two brake lamps are abnormal or not based on the vehicle lamp states of at least two brake lamps. Through the method and the device, the problem that whether the brake lamp of the vehicle on the driving road is abnormal or not can not be automatically identified is solved, and the technical effect of automatically identifying the abnormal vehicle on the brake lamp on the driving road is achieved.
Description
Technical Field
The present invention relates to the field of intelligent traffic technologies, and in particular, to a brake light abnormality determination method and a brake light abnormality determination apparatus for a vehicle.
Background
With the development of society, the quantity of vehicles kept by everyone is gradually increased, and safe driving of vehicles on urban roads is more and more important. The brake lamp is used as an important warning sign in the driving process, if a fault occurs, the brake lamp is not repaired in time, the brake lamp cannot effectively provide a warning effect for a rear vehicle in the driving process of a road, accidents such as rear-end collision and the like are easy to happen, and economic loss and even casualties are caused. In order to ensure the daily driving safety of the vehicle, it is necessary to monitor the brake lamp state of the vehicle on the road. The existing monitoring method still mainly depends on manual means such as law enforcement personnel crossing supervision, monitoring video screening and the like for screening, and the investment for screening small-probability events such as brake lamp abnormity is huge and is easy to miss.
In the prior art, by extracting the color characteristics, shape characteristics and structural characteristics of the brake lamp in the area of the vehicle body, the state information of the brake lamp of the front vehicle is accurately output in real time, and the method comprises the following specific operation steps: cutting the image to generate a region of interest ROI; accurately positioning a front vehicle area; identifying the state of a brake lamp in the positioned vehicle area; and outputting the brake lamp state information. The main disadvantage of the prior art is that only a local vehicle area can be located, then the brake lamp state identification is carried out on the located vehicle area, and the brake lamp state information can be output, but the judgment on whether the brake lamp of the vehicle on a traffic road is abnormal or not cannot be made.
Aiming at the problem that whether the brake lamp of the vehicle on the driving road is abnormal or not can not be automatically identified only through manual screening in the related technology, no effective solution is provided at present.
Disclosure of Invention
In the present embodiment, a brake lamp abnormality determination method and a brake lamp abnormality determination apparatus for a vehicle are provided to solve the problem in the related art that it is not possible to automatically identify whether there is an abnormality in a brake lamp of a vehicle on a travel lane.
In a first aspect, in the present embodiment, there is provided a brake lamp abnormality determination method for a vehicle, including:
acquiring a monitoring video containing at least one vehicle to be processed;
determining a sequence of video frames to be processed of a target vehicle based on the monitoring video; the video frame sequence to be processed comprises at least two brake lamps of the target vehicle, and the target vehicle comprises at least one vehicle in the vehicle to be processed;
determining that the target vehicle is in a braking state within a collection time period of the surveillance video; and
and determining the vehicle lamp states of at least two brake lamps based on the video frame sequence to be processed, and determining whether at least two brake lamps are abnormal or not based on the vehicle lamp states of at least two brake lamps.
In some embodiments, determining whether at least two of the brake lights are abnormal based on a lamp status of the at least two brake lights comprises:
and if the states of the vehicle lamps of the at least two brake lamps are not consistent, determining that at least one brake lamp in the at least two brake lamps is abnormal.
In some embodiments, if it is determined that the lamp states of at least two of the brake lamps are not consistent, determining that at least one of the at least two brake lamps is abnormal includes:
the vehicle lamp states at least comprise a bright state and a dead state, and if it is determined that a high-order brake lamp exists in at least two brake lamps, the state of the high-order brake lamp is determined to be the bright state, and the state of at least one brake lamp in the rest brake lamps is determined to be the dead state, at least one brake lamp in the at least two brake lamps is determined to be abnormal; the rest brake lamps comprise at least two brake lamps except the high-position brake lamp; or
And if it is determined that the high-order brake lamp does not exist in the at least two brake lamps, and it is determined that the on state and the off state exist in the vehicle lamp states of the at least two brake lamps, it is determined that at least one brake lamp in the at least two brake lamps is abnormal.
In some embodiments, if it is determined that the lamp states of at least two of the brake lamps are not consistent, determining that at least one of the at least two brake lamps is abnormal includes:
the vehicle lamp state comprises a bright state and a non-bright state; if it is determined that a high-order brake lamp exists in at least two brake lamps, the state of the high-order brake lamp is determined to be the bright state, and the state of at least one brake lamp in the rest brake lamps is determined to be the non-bright state, determining that at least one brake lamp in the at least two brake lamps is abnormal; and the rest of the brake lights comprise at least two brake lights except the high-position brake light.
In some embodiments, if it is determined that the lamp states of at least two of the brake lamps are not consistent, determining that at least one of the at least two brake lamps is abnormal includes:
and if the fact that the deceleration amplitude of the target vehicle in the unit time in the acquisition time period is larger than the speed threshold value is determined, and the fact that the brake lamp with the lamp state being in the off state exists in the at least two brake lamps is determined, it is determined that at least one of the at least two brake lamps is abnormal.
In some embodiments, after determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent, the method further includes: and capturing the target vehicle.
In some of these embodiments, determining that the target vehicle is in a braking state for the acquisition period of the surveillance video includes:
determining that the target vehicle is in a braking state within the acquisition time period of the monitoring video based on the speed information of the target vehicle measured by a speed measuring instrument within the acquisition time period; or
And determining that the target vehicle is in a braking state in the acquisition time period of the monitoring video based on the position information of the target vehicle in each video frame of the monitoring video.
In some of these embodiments, determining that the target vehicle is in a braking state during the acquisition period of the surveillance video based on the position information of the target vehicle in each video frame of the surveillance video includes:
the method comprises the steps of acquiring position information of a target vehicle in each video frame of a surveillance video respectively due to the fact that the time intervals of the video frames of the surveillance video are consistent, determining a displacement difference value of each video frame of the surveillance video, acquiring a deceleration amplitude of the target vehicle in unit time according to the displacement difference value and the time intervals, judging whether the deceleration amplitude in unit time is larger than a speed threshold value or not, and if the deceleration amplitude in unit time is larger than the speed threshold value, determining that the target vehicle is in a braking state in a collection time period of the surveillance video.
In some of these embodiments, after snapping the target vehicle, the method further comprises:
and marking abnormal brake lamps on the captured vehicle image.
In a second aspect, there is provided in the present embodiment a brake lamp abnormality determination apparatus for a vehicle, comprising:
the first acquisition module is used for acquiring a monitoring video of a vehicle to be processed;
the second acquisition module is used for acquiring the video frame sequence to be processed of the target vehicle based on the first acquisition module;
the first judgment module is used for judging whether the target vehicle is in a braking state within the acquisition time period of the monitoring video;
the detection module is used for detecting the vehicle lamp states of at least two brake lamps according to the video frame sequence to be processed;
and the second judgment module is used for judging whether at least two brake lamps of the target vehicle are abnormal or not.
In a third aspect, in the present embodiment, there is provided an electronic device, including a processing terminal, in which a computer program is stored, and the processing terminal is configured to execute the computer program to execute a vehicle capture method according to the first aspect.
In a fourth aspect, in the present embodiment, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a vehicle capture method as described in the first aspect above.
Compared with the related art, the brake lamp abnormality determining method and the brake lamp abnormality determining device for the vehicle provided in the embodiment determine that the target vehicle is in a braking state in the acquisition time period of the monitoring video; and determining the lamp states of at least two brake lamps based on the video frame sequence to be processed, and determining whether the at least two brake lamps are abnormal or not based on the lamp states of the at least two brake lamps, so that the problem that whether the brake lamps of the vehicles on the driving road are abnormal or not can not be automatically identified is solved, the technical effect of automatically identifying the vehicles with the abnormal brake lamps on the driving road is realized, and the workload of manual screening is effectively reduced.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a vehicle capture method of the present embodiment.
Fig. 2 is a flowchart of a vehicle capturing method of the present preferred embodiment.
Fig. 3 is a flowchart of step S303 in fig. 2.
Fig. 4 is a flowchart of step S304 in fig. 2.
Fig. 5 is a structural view of the vehicle capturing apparatus of the present embodiment.
Fig. 6 is a configuration diagram of the vehicle capturing apparatus of the present preferred embodiment.
Detailed Description
For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.
Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of this application do not denote a limitation of quantity, either in the singular or the plural. The terms "comprises," "comprising," "has," "having," and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference throughout this application to "connected," "coupled," and the like is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.
The embodiment provides a method for determining abnormality of a brake lamp of a vehicle, which can be applied to various monitoring devices such as intersections, entrances and exits. Fig. 1 is a flowchart of a brake lamp abnormality determination method of a vehicle of the present embodiment, as shown in fig. 1, the flowchart including the steps of:
s100: a surveillance video including at least one vehicle to be processed is obtained.
A section of monitoring video is intercepted from the video collected by the video monitoring equipment, and the intercepted section of monitoring video comprises the monitoring video of one or more vehicles to be processed.
S101: determining a video frame sequence to be processed of the target vehicle based on the monitoring video; the sequence of video frames to be processed comprises at least two brake lights of a target vehicle, and the target vehicle comprises a vehicle in at least one vehicle to be processed.
The target vehicle is one or more vehicles in the to-be-processed vehicles in the monitoring video, the to-be-processed video frame sequence is a video frame sequence including at least two brake lamps of the target vehicle in the monitoring video frame sequence, and the to-be-processed video frame sequence including the at least two brake lamps of the target vehicle is determined through the monitoring video.
S102: determining that the target vehicle is in a braking state in the acquisition time period of the monitoring video; and determining the vehicle lamp states of the at least two brake lamps based on the video frame sequence to be processed, and determining whether the at least two brake lamps are abnormal or not based on the vehicle lamp states of the at least two brake lamps.
Determining that the target vehicle is in a braking state in the acquisition time period of the monitoring video, identifying the lamp states of at least two brake lamps of the target vehicle through the to-be-processed video frame sequence of the target vehicle, and identifying whether the at least two brake lamps of the target vehicle are abnormal or not through the lamp states of the at least two brake lamps of the target vehicle.
Through the steps, the brake lamp abnormity determining method of the vehicle obtains the monitoring video containing at least one vehicle to be processed; determining a sequence of video frames to be processed of a target vehicle based on the monitoring video; the video frame sequence to be processed comprises at least two brake lamps of the target vehicle, and the target vehicle comprises at least one vehicle in the vehicle to be processed; determining that the target vehicle is in a braking state within a collection time period of the surveillance video; and determining the vehicle lamp states of at least two brake lamps based on the video frame sequence to be processed, and determining whether at least two brake lamps are abnormal or not based on the vehicle lamp states of at least two brake lamps. The problem of whether the brake lamp of the vehicle on the trip lane can not be automatically identified in the correlation technique has abnormity is solved, the technical effect of automatic identification of the vehicle with the abnormal brake lamp on the trip lane is realized, the vehicle owner can be timely reminded to timely maintain the abnormal brake lamp, and the driving safety of the driving road is effectively guaranteed.
In some embodiments, determining whether the at least two brake lights are abnormal based on the lamp states of the at least two brake lights comprises: and if the states of the lamps of the at least two brake lamps are not consistent, determining that at least one brake lamp of the at least two brake lamps is abnormal.
When the vehicle is in a braking state, all the brake lamps of the vehicle are in a lighted state under the condition that the brake lamps are not abnormal, and if the two or more than two brake lamps of the vehicle, which are shot by the video monitoring equipment, are in inconsistent states, at least one of the at least two brake lamps of the vehicle can be determined to be abnormal. The method for identifying the brake lamp abnormity in the machine vision-based mode is provided.
In some embodiments, if it is determined that the lamp states of the at least two brake lamps are inconsistent, determining that at least one brake lamp of the at least two brake lamps is abnormal comprises: the vehicle lamp states at least comprise a bright state and a dead state, and if it is determined that a high-order brake lamp exists in at least two brake lamps, the state of the high-order brake lamp is determined to be the bright state, and the state of at least one brake lamp in the rest brake lamps is the dead state, at least one brake lamp in the at least two brake lamps is determined to be abnormal; the rest brake lamps comprise brake lamps except the high-position brake lamp in the at least two brake lamps, or if the high-position brake lamp does not exist in the at least two brake lamps and the on state and the off state exist in the lamp states of the at least two brake lamps, at least one brake lamp in the at least two brake lamps is determined to be abnormal.
When the high-mount stop lamp exists in the vehicle, the on-off state of the high-mount stop lamp of the vehicle is determined firstly, because there is basically no interference around the high-mount stop lamp, it is relatively easy to identify the state of the lamp of the stop lamp, if the video monitoring equipment identifies that the state of the high-mount stop lamp is the on state, the states of the rest stop lamps except the high-mount stop lamp are identified, if at least one of the stop lamps except the high-mount stop lamp exists in the video frame shot by the video monitoring equipment is the off state, it is determined that at least one of the stop lamps of the vehicle is abnormal, in this embodiment, the stop lamp in the off state is the abnormal stop lamp.
When the high-order brake lights do not exist in the brake lights of the vehicle, by identifying the brake light states of the vehicle in the video frame shot by the video monitoring device, if it is identified that the lamp states of at least two brake lights of the vehicle have the on state and the off state, it is determined that at least one brake light of the at least two brake lights of the vehicle is abnormal, that is, in this embodiment, the brake light in the off state is the abnormal brake light.
In some embodiments, if it is determined that the lamp states of the at least two brake lamps are inconsistent, determining that at least one brake lamp of the at least two brake lamps is abnormal comprises: the vehicle lamp state comprises a bright state and a non-bright state; if it is determined that the at least two brake lamps have the high-order brake lamp, the state of the high-order brake lamp is determined to be a bright state, and the state of at least one brake lamp in the rest brake lamps is determined to be a non-bright state, determining that at least one brake lamp in the at least two brake lamps is abnormal; wherein, the rest brake lamps comprise at least two brake lamps except the high-position brake lamp.
If the lamp state of the brake lamp of the vehicle includes a bright state and a non-bright state, in this embodiment, the bright state refers to a state that the lamp state is recognized as a bright state in a video frame sequence acquired by the video acquisition device; the non-bright state refers to a state in which the state of the headlight in the sequence of video frames captured by the video capture device is off or the state of the headlight cannot be recognized as being on. Through the identification of the states of the brake lights of the vehicle in the video frame shot by the video monitoring equipment, when the high-order brake lights exist in at least two brake lights of the vehicle, the states of the high-order brake lights are also determined firstly, when the states of the high-order brake lights are identified to be bright states, other brake lights except the high-order brake lights are judged, and if the brake lights except the high-order brake lights are identified to be in the non-bright states, at least one of the brake lights in the target vehicle is determined to be abnormal. The brake lamp in the non-bright state comprises the brake lamp in the off state and the brake lamp in the bright state which cannot be identified.
In some embodiments, if it is determined that the lamp states of the at least two brake lamps are inconsistent, determining that at least one brake lamp of the at least two brake lamps is abnormal comprises: and if the deceleration amplitude of the target vehicle in unit time in the acquisition time period is larger than the speed threshold value and the brake lamp with the lamp state being in the off state exists in the at least two brake lamps, determining that at least one of the at least two brake lamps is abnormal.
In the video collecting time period, if the deceleration amplitude of the vehicle in unit time is greater than a speed threshold, for example, in unit time, the speed of the vehicle is reduced from 80m/s to 50m/s, the speed threshold is set to 25m/s, the deceleration amplitude of the vehicle is 30m/s, and the deceleration amplitude of the vehicle is greater than the speed threshold, it is indicated that the vehicle is in a braking state.
In some embodiments, after determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent, the brake light abnormality determination method for a vehicle further includes: and carrying out snapshot on the target vehicle.
When at least one brake lamp of at least two brake lamps of the target vehicle is determined to be abnormal, the video monitoring equipment takes a snapshot of the target vehicle.
In some of these embodiments, determining that the target vehicle is in a braking state during the acquisition period of the surveillance video includes: and determining that the target vehicle is in a braking state in the acquisition time period of the monitoring video based on the speed information of the target vehicle measured by the speed measuring instrument in the acquisition time period.
In this embodiment, it is determined that the target vehicle is in a braking state in the acquisition time period of the surveillance video, the speed information of the target vehicle can be measured by a speed measuring instrument installed at the intersection or the entrance, and then the speed information is judged, and when the deceleration amplitude is greater than the speed threshold value in unit time, the target vehicle is determined to be in the braking state in the acquisition time period of the surveillance video. The existing equipment such as the existing radar speed measuring instrument or the existing ultrasonic speed measuring instrument which is installed at the intersection or the entrance and exit is used for identifying whether the vehicle is in a braking state or not, and the identified state is fed back to the video monitoring equipment, so that the computational power consumption of the video monitoring equipment can be reduced.
In some embodiments, determining that the target vehicle is in a braking state in the acquisition period of the surveillance video based on the position information of the target vehicle in each video frame of the surveillance video includes: the method comprises the steps of acquiring position information of a target vehicle in each video frame of a surveillance video respectively due to the fact that the time intervals of the video frames of the surveillance video are consistent, determining displacement difference values of the video frames of the surveillance video, acquiring deceleration amplitude of the target vehicle in unit time according to the displacement difference values and the time intervals, judging whether the deceleration amplitude in unit time is larger than a speed threshold value or not, and if the deceleration amplitude in unit time is larger than the speed threshold value, determining that the target vehicle is in a braking state in the acquisition time period of the surveillance video.
In this embodiment, the position information of the target vehicle in each video frame of the surveillance video is identified, the position of the target vehicle in each video frame is identified, the time interval of each video frame of the surveillance video is consistent, the displacement difference value of the adjacent video frame of the surveillance video can be determined according to the position information of the target vehicle in each video frame of the surveillance video, the deceleration amplitude of the target vehicle in unit time can be calculated according to the displacement difference value of the adjacent video frame and the known time interval of the adjacent video frame, and if the deceleration amplitude of the target vehicle in unit time is greater than the speed threshold, the target vehicle can be determined to be in a braking state in the surveillance video acquisition time period.
In some embodiments, after capturing the target vehicle, the method for determining abnormality of brake lights of the vehicle further includes: and marking abnormal brake lamps on the captured vehicle image.
After the video monitoring equipment captures the vehicle with the abnormal brake lamp, the abnormal brake lamp is marked on the captured image of the vehicle, so that the screening personnel can rapidly screen the vehicle conveniently.
Fig. 2 is a flowchart of a vehicle capturing method of the present preferred embodiment. As shown in fig. 2, the process includes the following steps:
s300: and acquiring a monitoring image in real time.
The information of the target vehicle is acquired in real time through the image acquisition equipment, and because the brake is in a continuous state, the information in a certain duration of the target vehicle needs to be collected for comprehensive judgment.
S301: and detecting the vehicles in the monitored images, allocating IDs (identification) and further tracking.
In the range of videos or pictures collected by the monitoring equipment, the target vehicle is detected, the license plate of the target vehicle is identified, the ID is distributed to the target vehicle, and meanwhile the target vehicle and the license plate are subjected to associated tracking. In this embodiment, the video or picture range refers to all regions included in the monitoring device or a region that needs to be focused on in all regions, such as a straight lane region, a left-turn lane region, or a right-turn lane region. In the embodiment, the target vehicle is detected, and the target vehicle and the license plate are associated and tracked, mainly for associating different time dimensions of the same target vehicle.
For example, all the sets of vehicles to be detected having tracking IDs acquired in the present embodiment may be represented as Cars ═ { C0,C1,…,CN-1Where the total target amount is expressed by N, and the vehicle information C with ID i is trackediContains coordinate information in all historical frames and license plate identification information, wherein the coordinate position of the jth frame is (x)j,yj,wj,hj) To express.
S302: and sequentially judging whether the target vehicle is in a braking state or not.
And sequentially judging whether the target is in a braking state, if so, entering step S303, and if not, returning to step S300.
Judging whether the target vehicle is in a braking state, taking a vehicle with a tracking ID of i as an example:
all video frame sequences are extracted. Extracting coordinate information C of all objects with ID i in image sequencei。
The speed of the target vehicle is determined. Transforming the collected image to the overlooking visual angle according to the camera parameters, and firstly determining the central point of the target on the transformed overlooking image
And judging whether the deceleration operation exists according to the displacement speeds of the central points of the jth frame and the previous and next frames, and performing primary filtering on the vehicle in the deceleration operation.
Since the time intervals between adjacent images of the image sequence are consistent, the velocity is equalized by calculating the displacement distance. For example, the speed of the jth frame may be expressed as
The velocity after the jth frame can be expressed as
By comparing the speed difference delta-vj-vj+1Whether the current target vehicle is in a braking state or not can be obtained when delta is>d1When it is determined that the current target vehicle is in a braking state, wherein d1Is a second threshold value, d1Is a threshold range taken empirically. Of course, the method for determining the vehicle speed is not limited to the prediction by using only the video information collected by the current device, and the determination can be performed by using the vehicle speed data transmitted back by a speed measuring instrument, for example. And will not be described in detail herein.
S303: and detecting a brake lamp area.
And detecting the brake lamp of the target vehicle in the braking state in the image before the visual angle is changed, and constructing a sequence to be identified. The method mainly comprises the following steps:
s303-1: and judging whether the brake lamp is shielded or not. Due to the installation angle problem of the image information acquisition equipment, when a target vehicle is jammed in the driving process and other special conditions, the image information of the brake lamp area is easy to lose, so that the position of the brake lamp included in the acquired vehicle tail needs to be identified, and whether the brake lamp of the target vehicle is blocked or not is judged.
The occlusion judgment can directly adopt a light-weight deep learning classification model to classify the tail region of the target vehicle. When the brake lamp of the target vehicle is shielded, the vehicle lamp cannot be effectively identified, and the current image cannot be used for constructing a sequence to be identified. When the brake lights of the target vehicle are not shielded, the operation of step S303-2 is performed.
S303-2: and carrying out brake lamp area detection on the tail area of the vehicle. The detection method can adopt a traditional detection method or a detection method based on deep learning. The position of the brake light is first located for subsequent identification.
The brake lamps comprise a left brake lamp and a right brake lamp which are positioned at two ends of the tail of the vehicle, and a high-level brake lamp which is positioned at the upper part of the tail of the vehicle. All detect the brake lamp of three position in this embodiment, can effectively promote the relevance ratio of brake lamp. And constructing a sequence to be identified of the brake lamp according to whether the brake lamp in the step S303-1 has the shielded information, for example, the length of the sequence to be identified of the brake lamp is M, and M can be adjusted according to the identification scene and the requirement. And if the current image has shielding, emptying the current sequence to be identified, and reconstructing a new sequence to be identified for the brake lamp from the subsequent images of which the brake lamp does not have shielding phenomenon.
For example, a left brake lamp to-be-identified sequence TL, a right brake lamp to-be-identified sequence TR and a high brake lamp to-be-identified sequence TH are sequentially constructed according to the positions of tail lights.
S304: and judging the state of the brake lamp. Includes the step S304-1: judging the on state or off state of the brake lamp and step S304-2: and judging whether the brake lamp is abnormal or not.
S304-1: judging the on state or off state of the brake lamp,specifically, the state of a single brake lamp is judged according to the detected brake lamp sequence. In this embodiment, basic characteristic information such as color can be combined, and a timing network such as LSTM, GRU, or a video detection method is used for determining to obtain the on/off states S of the left brake light, the right brake light, and the high-mount brake light respectivelyTL,STRAnd STH. And each brake lamp state corresponds to three values, the brake lamp is on, the brake lamp is off, and the brake lamp state is unknown.
S304-2: the judgment of whether the brake lamp is abnormal is mainly based on the brake lamp status S obtained in step S304-1 in this embodimentTL,STRAnd STHAnd then judging whether the current target vehicle is in a braking state or not, wherein the judgment can be carried out by judging whether the deceleration amplitude of the target vehicle is larger than a second preset threshold value d or not2To judge whether the target vehicle is in a braking state when the speed difference delta>d2When the target vehicle is in the braking state, the current target vehicle can be judged to be in the braking state, wherein the second preset threshold value d2Is a threshold value taken empirically, and d2>d1。
After the target vehicle is confirmed to be in the brake state, the high-mount stop lamp state S is judgedTHWhether the brake lamp is lighted or not is relatively easy to judge because no other light interference exists around the high-position brake lamp. When the high-order brake lamp is on and the left brake lamp or the right brake lamp of the target vehicle is not on, marking the target position as the abnormal target of the brake lamp and marking the corresponding position according to the unlighted brake lamp.
S305: and outputting the state of the brake lamp.
The current state of the target vehicle is captured and evidence is obtained, the driver can be associated according to the license plate information associated with the target, and the information is integrated and then fed back to law enforcement personnel in time.
In some embodiments, the brake lamp is determined to be abnormal, and when the three brake lamp to-be-identified sequences exist and the high-order brake lamp is not turned on, the states of all the brake lamps are checked to be consistent. If the brake lights are not consistent with the preset brake light, the target is judged to be the abnormal target of the brake lights, and meanwhile, the unlighted brake light position is marked.
In some embodiments, whether the brake lamp is abnormal or not can be determined by checking whether the states of the left brake lamp and the right brake lamp are consistent or not when the high-order brake lamp sequence does not exist, and if the states of the left brake lamp and the right brake lamp are not consistent, determining that the target is the target of the brake lamp abnormality and marking the position of the brake lamp which is not lighted.
Through the steps, the embodiment can effectively judge whether the brake lamp of the vehicle running on the road is abnormal or not, and take a snapshot to obtain evidence, and can judge the brake lamp state of the target vehicle in the braking state only by prejudging whether the target vehicle is in the braking state or not, and does not judge the vehicle in the non-braking state, namely, preliminarily filters the speed of the target vehicle, so that the calculated amount can be greatly reduced.
In the process of processing the brake lamp, the state of the target vehicle is selectively judged, a large amount of computing resources are saved, the detection speed is increased, and special conditions such as large flow, congestion and the like can be met.
And the judgment of the state of the brake lamp adopts a time sequence method, and an effective continuous time interval is selected for detection. Compared with an identification method based on pictures, the method can effectively avoid the problems of illumination, shielding and the like in the detection process, improve the detection robustness and reduce false alarm and missing report.
In the present embodiment, there is also provided a brake lamp abnormality determination apparatus for a vehicle, and fig. 5 is a block diagram of a structure of a vehicle capture apparatus of the present embodiment, as shown in fig. 5, the apparatus includes:
the first acquisition module 10 is used for acquiring a monitoring video of a vehicle to be processed;
a second obtaining module 20, based on the first obtaining module, for obtaining a video frame sequence to be processed of the target vehicle;
the first judgment module 30 is used for judging whether the target vehicle is in a braking state within the acquisition time period of the monitoring video;
the detection module 40 is used for detecting the vehicle lamp states of at least two brake lamps according to the video frame sequence to be processed;
and the second judging module 50 is used for judging whether at least one of the at least two brake lamps of the target vehicle is abnormal.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
Fig. 6 is a structural view of the vehicle capturing apparatus of the present preferred embodiment, and as shown in fig. 6, the apparatus includes: the system comprises a processing terminal, an image acquisition module, a target detection tracking module, a vehicle speed filtering module, a brake lamp detection module and a brake lamp state judgment module, wherein a computer program is stored in the processing terminal, and the processing terminal is set to run the computer program to execute the steps in any method embodiment.
The processing terminal 100 is configured to send a command for starting to detect whether the brake lamp is abnormal, receive information collected by the image acquisition module, and perform a series of analysis on the received information, where the hardware platform may be a camera with good computational performance, or a hardware platform with computing capability, such as a server deployed at a back end.
The image acquisition module 200 is mainly used for continuously acquiring information of an area to be detected after receiving the detection command, and sending the information back to the processing terminal for subsequent processing. The image acquisition module needs to be able to fully acquire information of the tail of the vehicle (including the position of the brake light). Corresponding to the first acquisition module 10 in the above-described embodiment.
And the target detection and tracking module 300 is configured to perform preliminary analysis on the information acquired by the image acquisition module, assign an independent ID to the detected target, and perform tracking so as to facilitate subsequent processing. This module corresponds to the second acquiring module 20 in the above-described embodiment.
The vehicle speed filtering module 400 performs subsequent brake light abnormality determination only on the target vehicle in the deceleration stage in order to reduce the amount of calculation. This block corresponds to the determination block 30 in the above embodiment.
The brake light detection module 500 judges whether the brake light is shielded or not, detects the position of the brake light meeting the conditions, obtains the area of the brake light, and performs subsequent judgment. This module corresponds to the detection module 40 in the above-described embodiment.
The brake lamp state judging module 600 judges the state of the brake lamp according to the position of the brake lamp obtained by the brake lamp detecting module, and transmits the obtained state of the brake lamp back to the processing terminal. And if the abnormal condition exists, storing the corresponding image video evidence in time and uploading the evidence to related law enforcement personnel. This module corresponds to the snapshot module 50 in the above-described embodiment.
There is also provided in this embodiment an electronic device comprising a processing terminal having a computer program stored therein, the processing terminal being configured to run the computer program to perform the steps of any of the above method embodiments.
There is also provided in this embodiment a computer readable storage medium having stored thereon a computer program for execution by a processor of the steps in any of the method embodiments described above.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly or implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above examples 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 patent protection. 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 application shall be subject to the appended claims.
Claims (12)
1. A brake lamp abnormality determination method for a vehicle, characterized by comprising:
acquiring a monitoring video containing at least one vehicle to be processed;
determining a sequence of video frames to be processed of a target vehicle based on the monitoring video; the video frame sequence to be processed comprises at least two brake lamps of the target vehicle, and the target vehicle comprises at least one vehicle in the vehicle to be processed;
determining that the target vehicle is in a braking state within a collection time period of the surveillance video; and
and determining the vehicle lamp states of at least two brake lamps based on the video frame sequence to be processed, and determining whether at least two brake lamps are abnormal or not based on the vehicle lamp states of at least two brake lamps.
2. The method of claim 1, wherein determining whether at least two of the brake lights are abnormal based on a lamp status of the at least two brake lights comprises:
and if the states of the vehicle lamps of the at least two brake lamps are not consistent, determining that at least one brake lamp in the at least two brake lamps is abnormal.
3. The method of claim 2, wherein determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent comprises:
the vehicle lamp states at least comprise a bright state and a dead state, and if it is determined that a high-order brake lamp exists in at least two brake lamps, the state of the high-order brake lamp is determined to be the bright state, and the state of at least one brake lamp in the rest brake lamps is determined to be the dead state, at least one brake lamp in the at least two brake lamps is determined to be abnormal; the rest brake lamps comprise at least two brake lamps except the high-position brake lamp; or
And if it is determined that the high-order brake lamp does not exist in the at least two brake lamps, and it is determined that the on state and the off state exist in the vehicle lamp states of the at least two brake lamps, it is determined that at least one brake lamp in the at least two brake lamps is abnormal.
4. The method of claim 2, wherein determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent comprises:
the vehicle lamp state comprises a bright state and a non-bright state; if it is determined that a high-order brake lamp exists in at least two brake lamps, the state of the high-order brake lamp is determined to be the bright state, and the state of at least one brake lamp in the rest brake lamps is determined to be the non-bright state, determining that at least one brake lamp in the at least two brake lamps is abnormal; and the rest of the brake lights comprise at least two brake lights except the high-position brake light.
5. The method of claim 2, wherein determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent comprises:
and if the fact that the deceleration amplitude of the target vehicle in the unit time in the acquisition time period is larger than the speed threshold value is determined, and the fact that the brake lamp with the lamp state being in the off state exists in the at least two brake lamps is determined, it is determined that at least one of the at least two brake lamps is abnormal.
6. The method according to any one of claims 2 to 5, wherein after determining that at least one of the at least two brake lights is abnormal if it is determined that the lamp states of the at least two brake lights are not consistent, the method further comprises: and capturing the target vehicle.
7. The method of claim 1, wherein determining that the target vehicle is in a braking state for the acquisition period of the surveillance video comprises:
determining that the target vehicle is in a braking state within the acquisition time period of the monitoring video based on the speed information of the target vehicle measured by a speed measuring instrument within the acquisition time period; or
And determining that the target vehicle is in a braking state in the acquisition time period of the monitoring video based on the position information of the target vehicle in each video frame of the monitoring video.
8. The method of claim 7, wherein determining that the target vehicle is in a braking state during the acquisition period of the surveillance video based on the position information of the target vehicle in each video frame of the surveillance video comprises:
the method comprises the steps of acquiring position information of a target vehicle in each video frame of a surveillance video respectively due to the fact that the time intervals of the video frames of the surveillance video are consistent, determining a displacement difference value of each video frame of the surveillance video, acquiring a deceleration amplitude of the target vehicle in unit time according to the displacement difference value and the time intervals, judging whether the deceleration amplitude in unit time is larger than a speed threshold value or not, and if the deceleration amplitude in unit time is larger than the speed threshold value, determining that the target vehicle is in a braking state in a collection time period of the surveillance video.
9. The method of claim 6, wherein after snapping the target vehicle, the method further comprises:
and marking abnormal brake lamps on the captured vehicle image.
10. A brake lamp abnormality determination device for a vehicle, characterized by comprising:
the first acquisition module is used for acquiring a monitoring video of a vehicle to be processed;
the second acquisition module is used for acquiring the video frame sequence to be processed of the target vehicle based on the first acquisition module;
the first judgment module is used for judging whether the target vehicle is in a braking state within the acquisition time period of the monitoring video;
the detection module is used for detecting the vehicle lamp states of at least two brake lamps according to the video frame sequence to be processed;
and the second judgment module is used for judging whether at least two brake lamps of the target vehicle are abnormal or not.
11. An electronic device comprising a processing terminal, characterized in that the processing terminal has a computer program stored therein, and the processing terminal is configured to run the computer program to execute the brake lamp abnormality determination method of the vehicle according to any one of claims 1 to 9.
12. 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 brake lamp abnormality determination method for a vehicle of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110806639.9A CN113561896A (en) | 2021-07-16 | 2021-07-16 | Method and device for determining abnormality of brake lamp of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110806639.9A CN113561896A (en) | 2021-07-16 | 2021-07-16 | Method and device for determining abnormality of brake lamp of vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113561896A true CN113561896A (en) | 2021-10-29 |
Family
ID=78165323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110806639.9A Pending CN113561896A (en) | 2021-07-16 | 2021-07-16 | Method and device for determining abnormality of brake lamp of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113561896A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210312198A1 (en) * | 2020-04-03 | 2021-10-07 | Toyota Jidosha Kabushiki Kaisha | Apparatus, method, and computer program for identifying state of signal light, and controller |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030167123A1 (en) * | 2002-03-01 | 2003-09-04 | Hitachi, Ltd | Vehicle control apparatus |
| KR20130055836A (en) * | 2011-11-21 | 2013-05-29 | 현대자동차주식회사 | Alarm system for lamp error in vehicle and method thereof |
| KR20150050645A (en) * | 2013-10-29 | 2015-05-11 | 한국도로공사 | System and method for sensing condition of brake tail lamp |
| JP2017102585A (en) * | 2015-11-30 | 2017-06-08 | 日本電気株式会社 | Abnormality determination system, object device, abnormality determination device, determination method, and program |
| CN107303847A (en) * | 2016-04-19 | 2017-10-31 | 株式会社万都 | Car light confirming operation system and method |
| US20190061620A1 (en) * | 2017-08-31 | 2019-02-28 | Toyota Jidosha Kabushiki Kaisha | Abnormality detection apparatus, abnormality detection method, and abnormality detection system |
| CN110246337A (en) * | 2018-08-10 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method, apparatus and computer storage medium detecting Misuse car light |
| KR20200071405A (en) * | 2018-12-11 | 2020-06-19 | 한국교통대학교산학협력단 | Brake light inoperative detection system |
| CN112785850A (en) * | 2020-12-29 | 2021-05-11 | 上海眼控科技股份有限公司 | Method and device for identifying vehicle lane change without lighting |
-
2021
- 2021-07-16 CN CN202110806639.9A patent/CN113561896A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030167123A1 (en) * | 2002-03-01 | 2003-09-04 | Hitachi, Ltd | Vehicle control apparatus |
| KR20130055836A (en) * | 2011-11-21 | 2013-05-29 | 현대자동차주식회사 | Alarm system for lamp error in vehicle and method thereof |
| KR20150050645A (en) * | 2013-10-29 | 2015-05-11 | 한국도로공사 | System and method for sensing condition of brake tail lamp |
| JP2017102585A (en) * | 2015-11-30 | 2017-06-08 | 日本電気株式会社 | Abnormality determination system, object device, abnormality determination device, determination method, and program |
| CN107303847A (en) * | 2016-04-19 | 2017-10-31 | 株式会社万都 | Car light confirming operation system and method |
| US20190061620A1 (en) * | 2017-08-31 | 2019-02-28 | Toyota Jidosha Kabushiki Kaisha | Abnormality detection apparatus, abnormality detection method, and abnormality detection system |
| CN110246337A (en) * | 2018-08-10 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method, apparatus and computer storage medium detecting Misuse car light |
| KR20200071405A (en) * | 2018-12-11 | 2020-06-19 | 한국교통대학교산학협력단 | Brake light inoperative detection system |
| CN112785850A (en) * | 2020-12-29 | 2021-05-11 | 上海眼控科技股份有限公司 | Method and device for identifying vehicle lane change without lighting |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210312198A1 (en) * | 2020-04-03 | 2021-10-07 | Toyota Jidosha Kabushiki Kaisha | Apparatus, method, and computer program for identifying state of signal light, and controller |
| US11900690B2 (en) * | 2020-04-03 | 2024-02-13 | Toyota Jidosha Kabushiki Kaisha | Apparatus, method, and computer program for identifying state of signal light, and controller |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6442474B1 (en) | Vision-based method and apparatus for monitoring vehicular traffic events | |
| CN109326124A (en) | A kind of urban environment based on machine vision parks cars Activity recognition system | |
| CN202077142U (en) | Vehicle-mounted intelligent video detecting and analyzing system | |
| CN102129779B (en) | Monitoring system of safety and efficiency of traffic signal of intersection | |
| CN108154686A (en) | A kind of vehicle-mounted act of violating regulations capturing system | |
| US20150332097A1 (en) | Short-time stopping detection from red light camera videos | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| CN101739809A (en) | Automatic alarm and monitoring system for pedestrian running red light | |
| CN201307337Y (en) | Automatic alarming and monitoring device for traffic-lights nonobservance of pedestrian | |
| CA2925843C (en) | System for traffic behaviour surveillance | |
| CN110895884A (en) | Control method and device of traffic signal lamp | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN103021175A (en) | Pedestrian red light running video detection method and device based on Davinci architecture | |
| CN105608906A (en) | System for monitoring illegal emergency lane occupancy of expressway motor vehicles and implementation method | |
| CN112349087B (en) | Visual data input method based on holographic perception of intersection information | |
| CN103236181A (en) | Traffic signal lamp state monitoring system and method based on machine vision | |
| CN109544936A (en) | Motor vehicle zebra stripes based on radar video camera do not give precedence to pedestrian's early warning capturing system | |
| CN111292530A (en) | Method, device, server and storage medium for processing violation pictures | |
| CN112489383A (en) | Early warning system and method for preventing red light running accident based on machine vision | |
| CN108986476A (en) | Motor vehicle does not use according to regulations high beam recognition methods, system and storage medium | |
| CN112560546B (en) | Method and device for detecting throwing behavior and storage medium | |
| CN112395976A (en) | Motorcycle manned identification method, device, equipment and storage medium | |
| CN113561896A (en) | Method and device for determining abnormality of brake lamp of vehicle | |
| CN109887303B (en) | Lane-changing behavior early warning system and method | |
| CN111341114A (en) | Vehicle-mounted video traffic violation detection method, device and system based on Internet of things |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211029 |