CN113449624A - Method and device for determining vehicle behavior based on pedestrian re-recognition - Google Patents
Method and device for determining vehicle behavior based on pedestrian re-recognition Download PDFInfo
- Publication number
- CN113449624A CN113449624A CN202110689288.8A CN202110689288A CN113449624A CN 113449624 A CN113449624 A CN 113449624A CN 202110689288 A CN202110689288 A CN 202110689288A CN 113449624 A CN113449624 A CN 113449624A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- determining
- image
- driver
- distance
- 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 28
- 230000008859 change Effects 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 230000009471 action Effects 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 9
- 230000036544 posture Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 5
- 230000009191 jumping Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 26
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- 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
- G06T2207/30196—Human being; Person
-
- 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
- G06T2207/30241—Trajectory
Abstract
The embodiment of the invention provides a method and a device for determining vehicle behaviors based on pedestrian re-identification, wherein the method comprises the following steps: acquiring an image of a preset monitoring area, identifying the current image, and judging whether a vehicle exists in the current image; if the image information exists, acquiring a first image set containing the vehicle in a moving state in a preset time period, and determining the portrait information of a driver of the vehicle through a pedestrian re-identification algorithm; determining a first distance trend of change of the distance between the driver and the vehicle and a second distance trend of change of the distance between the vehicle and the berth; and determining the entrance and exit behavior of the vehicle according to the first distance variation trend and the second distance variation trend. The invention can accurately determine the entrance and exit behaviors of the vehicle without being limited by the number of the license plate, and avoids the condition that the behavior of the vehicle cannot be determined due to the fact that the image of the vehicle cannot be acquired because of the limitation of the shooting angle of the monitoring camera, the limitation of the environment and other factors.
Description
Technical Field
The invention relates to the technical field of intelligent parking management, in particular to a method and a device for determining vehicle behaviors based on pedestrian re-identification.
Background
Today of economic rapid development, people's standard of living and income constantly improve, and city motor vehicle reserves also increases rapidly, but follows thereupon, and city parking stall breach also constantly enlarges, can't satisfy huge parking demand far away, and the contradiction between parking stall and parking demand is sharp-pointed day by day. Especially, on two sides of an urban road, due to scarcity of roadside parking spaces and thin traffic safety awareness of motor vehicle drivers, urban roadside parking and roadside illegal parking become one of aeipathia of urban management, so that problems such as traffic jam and the like seriously restrict green and rapid development of a city, seriously affect city appearance and resident living environment, and the degree of irresistibility to treatment of urban roadside parking and roadside illegal parking is reached.
With the maturity of high-order video technology, real-time automatic supervision roadside parking lots become the main mode of roadside parking management, but because of being limited by factors such as site construction, environment and the like, the condition that roadside parking behaviors cannot be supervised by partial surveillance cameras can appear, and meanwhile, the condition that the target vehicle is shielded by other large-scale vehicles and cannot be supervised often appears. Therefore, how to accurately determine the vehicle behavior without being limited by the number of the license plate becomes a difficult problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining vehicle behaviors based on pedestrian re-recognition, which are not limited by license plate numbers and can accurately determine the vehicle behaviors.
In one aspect, an embodiment of the present invention provides a method for determining vehicle behavior based on pedestrian re-identification, including:
acquiring an image of a preset monitoring area, identifying the current image, and judging whether a vehicle exists in the current image;
if the image information exists, a first image set containing the vehicle in a moving state in a preset time period is obtained, the portrait information in the first image set is determined through a pedestrian re-identification algorithm, and the portrait information of a driver of the vehicle is determined according to the portrait information in the first image set;
determining the action track of the driver and the position of the vehicle at the berth in the first image set;
determining a first distance variation trend of the distance between the driver and the vehicle and a second distance variation trend of the distance between the vehicle and the berth according to the action track of the driver and the position of the berth where the vehicle is located;
and determining the entrance and exit behavior of the vehicle according to the first distance variation trend and the second distance variation trend.
Further, the acquiring a first set of images containing the vehicle in motion within a predetermined time period includes:
step A, continuously acquiring a second image set of a preset monitoring area in a preset time period, and judging whether the second image set contains images of a vehicle in a moving state;
if not, jumping to the step A until the second image set contains the images of the vehicle in the moving state;
and if so, determining the second image set as the first image set.
Further, the determining the portrait information in the first image set through a pedestrian re-identification algorithm includes:
extracting a network model according to a preset characteristic, and determining the characteristic of a portrait in each moving image of the vehicle in a moving state in the first image set;
calculating the feature distance in each moving image according to the features;
and sequencing the characteristic distances in the moving images, and determining portrait information in the vehicle from the moving images.
Further, the determining portrait information of a driver of the vehicle from the portrait information in the first image set includes:
determining the portrait information in a driving state at the driving position of the vehicle according to the portrait information;
detecting a position rectangular frame of a portrait at the driving position of the vehicle in each moving image through a predetermined feature extraction network model;
based on the position rectangular frame, segmenting each moving image aiming at the portrait of the vehicle driving position according to the pixel probability of the portrait in each moving image;
performing background replacement on each segmented moving image to obtain a segmented image of each moving image;
and detecting the skeleton key points and the postures of the portrait of the driving position of the vehicle in the segmentation image, and determining the portrait information of the driver of the vehicle in the first image set according to the detection result.
Further, the determining the action track of the driver and the position of the vehicle at the parking space in the first image set includes:
according to the determined portrait information of the driver of the vehicle, determining the characteristics of the driver in each moving image of the vehicle in a static state in the first image set;
and determining the action track of the driver according to the characteristics.
Further, the determining a first distance variation trend of the distance between the driver and the vehicle and a second distance variation trend of the distance between the vehicle and the parking space according to the action track of the driver and the position of the parking space where the vehicle is located includes:
determining a first change trend of the distance between the driver and the vehicle according to the action track of the driver;
and determining a second distance change trend of the distance between the vehicle and the berth in the first image set through a predetermined image recognition algorithm according to the determined position of the berth where the vehicle is located.
Further, the determining the access behavior of the vehicle according to the first distance variation trend and the second distance variation trend comprises:
if the first distance variation trend is gradually reduced and the second distance variation trend is gradually increased, determining that the vehicle is out of the field;
and if the first distance variation trend is gradually increased and the second distance variation trend is unchanged, determining that the vehicle enters the field.
In another aspect, an embodiment of the present invention provides an apparatus for determining vehicle behavior based on pedestrian re-recognition, including:
the acquisition and judgment module is used for acquiring the image of the preset monitoring area, identifying the current image and judging whether the vehicle exists in the current image or not;
the acquisition and determination module is used for acquiring a first image set containing the vehicle in a moving state in a preset time period if the first image set exists, determining portrait information in the first image set through a pedestrian re-identification algorithm, and determining the portrait information of a driver of the vehicle according to the portrait information in the first image set;
the first determining module is used for determining the action track of the driver and the position of the vehicle at the berth in the first image set;
the second determining module is used for determining a first distance change trend of the distance between the driver and the vehicle and a second distance change trend of the distance between the vehicle and the berth according to the action track of the driver and the position of the berth where the vehicle is located;
and the third determining module is used for determining the entrance and exit behavior of the vehicle according to the first distance variation trend and the second distance variation trend.
Further, the obtaining and determining module includes:
the device comprises a judging unit, a monitoring unit and a processing unit, wherein the judging unit is used for continuously acquiring a second image set of a preset monitoring area in a preset time period and judging whether the second image set contains images of a vehicle in a moving state;
the skipping unit is used for skipping to the judging unit if the images are not contained in the second image set until the images of the vehicle in the moving state are contained in the second image set;
and the first determining unit is used for determining the second image set as the first image set if the second image set contains the first image set.
Further, the obtaining and determining module includes:
a second determining unit configured to extract a network model based on a predetermined feature, and determine, in the first image set, a feature of a portrait in each moving image in which the vehicle is in a moving state;
a calculating unit configured to calculate a feature distance in each of the moving images according to the feature;
and the sequencing unit is used for sequencing the characteristic distances in the moving images and determining portrait information in the vehicle from the moving images.
Further, the obtaining and determining module includes:
a third determining unit, configured to determine portrait information in a driving state at the driving position of the vehicle according to the portrait information;
a detecting unit configured to detect a position rectangular frame of a portrait at the vehicle driving position in the moving images through a predetermined feature extraction network model;
a segmentation unit configured to segment each of the moving images for the portrait at the vehicle driving position according to a pixel probability of the portrait in each of the moving images based on the position rectangular frame;
the replacing unit is used for replacing the background of each segmented moving image to obtain the segmented image of each moving image;
and the detection and determination unit is used for detecting the skeleton key points and the postures of the portrait of the driving position of the vehicle in the segmentation image and determining the portrait information of the driver of the vehicle in the first image set according to the detection result.
Further, the first determining module is specifically configured to
According to the determined portrait information of the driver of the vehicle, determining the characteristics of the driver in each moving image of the vehicle in a static state in the first image set;
and determining the action track of the driver according to the characteristics.
Further, the second determination module is specifically configured to
Determining a first change trend of the distance between the driver and the vehicle according to the action track of the driver;
and determining a second distance change trend of the distance between the vehicle and the berth in the first image set through a predetermined image recognition algorithm according to the determined position of the berth where the vehicle is located.
Further, the third determining module is specifically configured to
If the first distance variation trend is gradually reduced and the second distance variation trend is gradually increased, determining that the vehicle is out of the field;
and if the first distance variation trend is gradually increased and the second distance variation trend is unchanged, determining that the vehicle enters the field.
The technical scheme has the following beneficial effects: according to the invention, the portrait information of the driver can be accurately determined based on a pedestrian re-recognition algorithm, and the entrance and exit behaviors of the vehicle can be accurately determined according to the position relationship between the driver and the driven vehicle without the limitation of the number of the license plate, so that the condition that the behavior of the vehicle cannot be determined due to the limitation of factors such as the shooting angle limitation of a monitoring camera, the environment and the like and the incapability of acquiring the vehicle image is avoided, further, an important precondition guarantee is provided for accurately and efficiently performing roadside parking management on the vehicle in the follow-up process, and the use experience of a user is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for determining vehicle behavior based on pedestrian re-identification in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an apparatus for determining vehicle behavior based on pedestrian re-identification according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical scheme of the embodiment of the invention has the following beneficial effects: according to the invention, the portrait information of the driver can be accurately determined based on a pedestrian re-recognition algorithm, and the entrance and exit behaviors of the vehicle can be accurately determined according to the position relationship between the driver and the driven vehicle without the limitation of the number of the license plate, so that the condition that the behavior of the vehicle cannot be determined due to the limitation of factors such as the shooting angle limitation of a monitoring camera, the environment and the like and the incapability of acquiring the vehicle image is avoided, further, an important precondition guarantee is provided for accurately and efficiently performing roadside parking management on the vehicle in the follow-up process, and the use experience of a user is greatly improved.
The above technical solutions of the embodiments of the present invention are described in detail below with reference to application examples:
the application example of the invention aims to accurately determine the vehicle behavior without being limited by the number of the license plate.
In a possible implementation manner, in a roadside parking management system, an image of a predetermined area is shot by a camera, the image of the predetermined monitoring area shot by the camera is obtained in real time, then, the obtained current image is identified, whether a vehicle exists in the current image is judged, if the vehicle exists in the current image, such as the vehicle C, a first image set containing the vehicle C in a moving state in a predetermined time period is obtained, portrait information in the first image set is determined through a pedestrian re-identification algorithm, and a driver of the vehicle C, such as the portrait information of the driver D, is determined according to the portrait information in the first image set; determining the action track of the driver D and the position of the vehicle C at the berth in the first image set; determining a first distance variation trend of the distance between the driver D and the vehicle C and a second distance variation trend of the distance between the vehicle C and the berth according to the action track of the driver D and the position of the berth where the vehicle C is located; and finally, determining the entrance and exit behavior of the vehicle C according to the first distance variation trend and the second distance variation trend.
It should be noted that, according to the embodiment, the behavior of the vehicle can be accurately determined without being limited by the number of the license plate, and after the number of the license plate is determined according to the clear image of any license plate of the vehicle in the image in the process of performing roadside parking management on the vehicle, such as vehicle parking charging, etc., can be accurately and efficiently performed without being limited by the factors of the camera shooting angle limitation, the environment, etc.
In one possible implementation, the step of obtaining a first image set containing a moving state of the vehicle within a predetermined time period in step 102 includes: step A, continuously acquiring a second image set of a preset monitoring area in a preset time period, and judging whether the second image set contains images of a vehicle in a moving state; if not, jumping to the step A until the second image set contains the images of the vehicle in the moving state; and if so, determining the second image set as the first image set.
For example, in a roadside parking management system, an image of a predetermined monitoring area captured by a camera is obtained in real time, the obtained current image is identified, whether a vehicle exists in the current image is judged, and if a vehicle, such as a vehicle C, exists in the current image, the step a is executed: continuously acquiring a second image set of a preset monitoring area within a preset time period, such as 5 minutes, if the acquisition time of the current image is 2021:08:00:10, and the preset time period is 2021:08:00:11 to 2021:08:05:10, and judging whether the second image set contains images of the vehicle C in a moving state or not; and if the judgment result is that the image is not contained, jumping to the step A until the second image set contains the images of the vehicle C in the moving state, and when the second image set contains the images of the vehicle C in the moving state, re-determining the second image set as the first image set.
In a possible implementation manner, the step of determining portrait information in the first image set through a pedestrian re-identification algorithm in step 102 includes: extracting a network model according to a preset characteristic, and determining the characteristic of a portrait in each moving image of the vehicle in a moving state in the first image set; calculating the feature distance in each moving image according to the features; and sequencing the characteristic distances in the moving images, and determining portrait information in the vehicle from the moving images.
For example, in the roadside parking management system, as described above, the network model is extracted according to the predetermined features, such as the pre-trained feature network model based on pedestrian re-recognition, and the features of the portrait in each moving image in which the vehicle C is in a moving state are determined in the first image set; calculating the characteristic distance in each moving image according to the extracted portrait characteristics; the feature distances in the moving images are sorted to obtain an average precision value, and then portrait information in the vehicle C is determined from the moving images according to the average precision value, wherein the portrait information includes frontal face information, hand postures, in-vehicle positions and the like of the portrait.
As will be appreciated by those skilled in the art, pedestrian re-identification (Person re-identification), also known as pedestrian re-identification, is a technique that uses computer vision techniques to determine whether a particular pedestrian is present in an image or video sequence. Is widely considered as a sub-problem for image retrieval. Given a monitored pedestrian image, the pedestrian image is retrieved across the device. The aim is to remedy the visual limitation of fixed cameras and to combine with pedestrian detection/pedestrian tracking technology. In the embodiments of the present invention, although a specific algorithm is taken as an example for explanation, the invention is not limited thereto.
In one possible implementation, the step of determining the portrait information of the driver of the vehicle from the portrait information in the first image set in step 102 includes: determining the portrait information in a driving state at the driving position of the vehicle according to the portrait information; detecting a position rectangular frame of a portrait at the driving position of the vehicle in each moving image through a predetermined feature extraction network model; based on the position rectangular frame, segmenting each moving image aiming at the portrait of the vehicle driving position according to the pixel probability of the portrait in each moving image; performing background replacement on each segmented moving image to obtain a segmented image of each moving image; and detecting the skeleton key points and the postures of the portrait of the driving position of the vehicle in the segmentation image, and determining the portrait information of the driver of the vehicle in the first image set according to the detection result.
For example, in the roadside parking management system, the portrait information in the driving state at the driving position of the vehicle C is determined according to the extracted portrait information, then, the position rectangular frame of the portrait at the driving position of the vehicle C in each moving image is detected through a predetermined feature extraction network model, based on each position rectangular frame, each moving image is segmented according to the pixel probability of the portrait in each moving image with respect to the portrait at the driving position of the vehicle C, and the segmented images of each moving image are obtained by performing background replacement on each segmented moving image; and detecting the skeleton key points and the postures of the human images of the driving positions of the vehicles C in the segmented images, determining the drivers D of the vehicles C in the first image set according to the detection results, and determining the human image information of the drivers D.
In a possible implementation manner, the step 103 of determining, in the first image set, the action trajectory of the driver and the position of the vehicle at the parking space includes: according to the determined portrait information of the driver of the vehicle, determining the characteristics of the driver in each moving image of the vehicle in a static state in the first image set; and determining the action track of the driver according to the characteristics.
For example, in the roadside parking management system, based on the determined portrait information of the driver D of the vehicle C, in the first image set, the features of the driver D such as the posture feature, the motion feature, and the like of the driver in each moving image in which the vehicle is in a stationary state are determined; and determining the action track of the driver D according to the posture characteristic and the action characteristic of the driver D.
In a possible implementation manner, the step 104 of determining, according to the action trajectory of the driver and the position of the vehicle at the parking space, a first distance variation trend of the distance between the driver and the vehicle and a second distance variation trend of the distance between the vehicle and the parking space includes: determining a first change trend of the distance between the driver and the vehicle according to the action track of the driver; and determining a second distance change trend of the distance between the vehicle and the berth in the first image set through a predetermined image recognition algorithm according to the determined position of the berth where the vehicle is located.
Wherein determining access behavior of the vehicle according to the first distance trend and the second distance trend comprises: if the first distance variation trend is gradually reduced and the second distance variation trend is gradually increased, determining that the vehicle is out of the field; and if the first distance variation trend is gradually increased and the second distance variation trend is unchanged, determining that the vehicle enters the field.
For example, in the roadside parking management system, the first trend of change in the distance between the driver D and the vehicle C is determined to be gradually decreasing according to the action trajectory of the driver D, and the second trend of change in the distance between the vehicle C and the parking space at which the vehicle C is located is determined to be gradually increasing in the first image set according to the determined position of the parking space at which the vehicle C is located by the predetermined image recognition algorithm, so that the vehicle C can be determined to be coming out of the field.
For another example, as described above, in the roadside parking management system, the first trend of change in the distance between the driver D and the vehicle C is determined to be gradually decreasing according to the action trajectory of the driver D, the second trend of change in the distance between the vehicle C and the parking space at which the vehicle C is located is determined to be gradually increasing according to the determined position of the parking space at which the vehicle C is located in the first image set by the predetermined image recognition algorithm, and the second trend of change in the distance between the vehicle C and the parking space at which the vehicle C is located is determined to be unchanged according to the determined position of the parking space at which the vehicle C is located in the first image set by the predetermined image recognition algorithm, so that the vehicle C can be determined to enter the field.
The embodiment of the invention provides a device for determining vehicle behavior based on pedestrian re-identification, which can implement the method embodiment provided above, and for specific function implementation, please refer to the description in the method embodiment, and details are not repeated herein.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. To those skilled in the art; various modifications to these embodiments will be readily apparent, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.
The various illustrative logical blocks, or elements, described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be located in a user terminal. In the alternative, the processor and the storage medium may reside in different components in a user terminal.
In one or more exemplary designs, the functions described above in connection with the embodiments of the invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store program code in the form of instructions or data structures and which can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Additionally, any connection is properly termed a computer-readable medium, and, thus, is included if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wirelessly, e.g., infrared, radio, and microwave. Such discs (disk) and disks (disc) include compact disks, laser disks, optical disks, DVDs, floppy disks and blu-ray disks where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included in the computer-readable medium.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (14)
1. A method of determining vehicle behavior based on pedestrian re-identification, comprising:
acquiring an image of a preset monitoring area, identifying the current image, and judging whether a vehicle exists in the current image;
if the image information exists, a first image set containing the vehicle in a moving state in a preset time period is obtained, the portrait information in the first image set is determined through a pedestrian re-identification algorithm, and the portrait information of a driver of the vehicle is determined according to the portrait information in the first image set;
determining the action track of the driver and the position of the vehicle at the berth in the first image set;
determining a first distance variation trend of the distance between the driver and the vehicle and a second distance variation trend of the distance between the vehicle and the berth according to the action track of the driver and the position of the berth where the vehicle is located;
and determining the entrance and exit behavior of the vehicle according to the first distance variation trend and the second distance variation trend.
2. The method of claim 1, wherein obtaining a first set of images containing the vehicle in motion for a predetermined period of time comprises:
step A, continuously acquiring a second image set of a preset monitoring area in a preset time period, and judging whether the second image set contains images of a vehicle in a moving state;
if not, jumping to the step A until the second image set contains the images of the vehicle in the moving state;
and if so, determining the second image set as the first image set.
3. The method of claim 2, wherein the determining the portrait information in the first image set by a pedestrian re-identification algorithm comprises:
extracting a network model according to a preset characteristic, and determining the characteristic of a portrait in each moving image of the vehicle in a moving state in the first image set;
calculating the feature distance in each moving image according to the features;
and sequencing the characteristic distances in the moving images, and determining portrait information in the vehicle from the moving images.
4. The method of claim 3, wherein determining the portrait information of the driver of the vehicle from the portrait information in the first set of images comprises:
determining the portrait information in a driving state at the driving position of the vehicle according to the portrait information;
detecting a position rectangular frame of a portrait at the driving position of the vehicle in each moving image through a predetermined feature extraction network model;
based on the position rectangular frame, segmenting each moving image aiming at the portrait of the vehicle driving position according to the pixel probability of the portrait in each moving image;
performing background replacement on each segmented moving image to obtain a segmented image of each moving image;
and detecting the skeleton key points and the postures of the portrait of the driving position of the vehicle in the segmentation image, and determining the portrait information of the driver of the vehicle in the first image set according to the detection result.
5. The method of claim 4, wherein determining the driver's trajectory and the location of the vehicle at the parking location in the first image set comprises:
according to the determined portrait information of the driver of the vehicle, determining the characteristics of the driver in each moving image of the vehicle in a static state in the first image set;
and determining the action track of the driver according to the characteristics.
6. The method according to claim 5, wherein the determining a first distance variation trend of the distance between the driver and the vehicle and a second distance variation trend of the distance between the vehicle and the parking space according to the action track of the driver and the position of the vehicle at the parking space comprises:
determining a first change trend of the distance between the driver and the vehicle according to the action track of the driver;
and determining a second distance change trend of the distance between the vehicle and the berth in the first image set through a predetermined image recognition algorithm according to the determined position of the berth where the vehicle is located.
7. The method of claim 6, wherein determining the access behavior of the vehicle based on the first and second distance trends comprises:
if the first distance variation trend is gradually reduced and the second distance variation trend is gradually increased, determining that the vehicle is out of the field;
and if the first distance variation trend is gradually increased and the second distance variation trend is unchanged, determining that the vehicle enters the field.
8. An apparatus for determining vehicle behavior based on pedestrian re-identification, comprising:
the acquisition and judgment module is used for acquiring the image of the preset monitoring area, identifying the current image and judging whether the vehicle exists in the current image or not;
the acquisition and determination module is used for acquiring a first image set containing the vehicle in a moving state in a preset time period if the first image set exists, determining portrait information in the first image set through a pedestrian re-identification algorithm, and determining the portrait information of a driver of the vehicle according to the portrait information in the first image set;
the first determining module is used for determining the action track of the driver and the position of the vehicle at the berth in the first image set;
the second determining module is used for determining a first distance change trend of the distance between the driver and the vehicle and a second distance change trend of the distance between the vehicle and the berth according to the action track of the driver and the position of the berth where the vehicle is located;
and the third determining module is used for determining the entrance and exit behavior of the vehicle according to the first distance variation trend and the second distance variation trend.
9. The apparatus of claim 8, wherein the obtaining and determining module comprises:
the device comprises a judging unit, a monitoring unit and a processing unit, wherein the judging unit is used for continuously acquiring a second image set of a preset monitoring area in a preset time period and judging whether the second image set contains images of a vehicle in a moving state;
the skipping unit is used for skipping to the judging unit if the images are not contained in the second image set until the images of the vehicle in the moving state are contained in the second image set;
and the first determining unit is used for determining the second image set as the first image set if the second image set contains the first image set.
10. The apparatus of claim 9, wherein the obtaining and determining module comprises:
a second determining unit configured to extract a network model based on a predetermined feature, and determine, in the first image set, a feature of a portrait in each moving image in which the vehicle is in a moving state;
a calculating unit configured to calculate a feature distance in each of the moving images according to the feature;
and the sequencing unit is used for sequencing the characteristic distances in the moving images and determining portrait information in the vehicle from the moving images.
11. The apparatus of claim 10, wherein the obtaining and determining module comprises:
a third determining unit, configured to determine portrait information in a driving state at the driving position of the vehicle according to the portrait information;
a detecting unit configured to detect a position rectangular frame of a portrait at the vehicle driving position in the moving images through a predetermined feature extraction network model;
a segmentation unit configured to segment each of the moving images for the portrait at the vehicle driving position according to a pixel probability of the portrait in each of the moving images based on the position rectangular frame;
the replacing unit is used for replacing the background of each segmented moving image to obtain the segmented image of each moving image;
and the detection and determination unit is used for detecting the skeleton key points and the postures of the portrait of the driving position of the vehicle in the segmentation image and determining the portrait information of the driver of the vehicle in the first image set according to the detection result.
12. The apparatus according to claim 11, wherein the first determining means is specifically configured to determine the first threshold value
According to the determined portrait information of the driver of the vehicle, determining the characteristics of the driver in each moving image of the vehicle in a static state in the first image set;
and determining the action track of the driver according to the characteristics.
13. The apparatus according to claim 12, wherein the second determination module is specifically configured to determine the second threshold value
Determining a first change trend of the distance between the driver and the vehicle according to the action track of the driver;
and determining a second distance change trend of the distance between the vehicle and the berth in the first image set through a predetermined image recognition algorithm according to the determined position of the berth where the vehicle is located.
14. The apparatus according to claim 13, wherein the third determination module is specifically configured to determine the second threshold value
If the first distance variation trend is gradually reduced and the second distance variation trend is gradually increased, determining that the vehicle is out of the field;
and if the first distance variation trend is gradually increased and the second distance variation trend is unchanged, determining that the vehicle enters the field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110689288.8A CN113449624A (en) | 2021-06-22 | 2021-06-22 | Method and device for determining vehicle behavior based on pedestrian re-recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110689288.8A CN113449624A (en) | 2021-06-22 | 2021-06-22 | Method and device for determining vehicle behavior based on pedestrian re-recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113449624A true CN113449624A (en) | 2021-09-28 |
Family
ID=77812125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110689288.8A Pending CN113449624A (en) | 2021-06-22 | 2021-06-22 | Method and device for determining vehicle behavior based on pedestrian re-recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449624A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060061680A (en) * | 2004-12-02 | 2006-06-08 | 주식회사 대우일렉트로닉스 | System and method for detecting location of car parking |
| CN106652052A (en) * | 2016-12-30 | 2017-05-10 | 苏州远扬智能科技有限公司 | Parking lot entrance and exit management system and parking lot entrance and exit management method |
| CN107680382A (en) * | 2017-02-24 | 2018-02-09 | 上海享泊信息科技有限公司 | Licence plate recognition method, module, cloud server and managing system of car parking |
| CN111353369A (en) * | 2019-10-16 | 2020-06-30 | 智慧互通科技有限公司 | Application method and system of high-order video of urban roadside parking in assisting criminal investigation |
| CN112820137A (en) * | 2020-12-31 | 2021-05-18 | 金茂智慧科技(广州)有限公司 | Parking lot management method and device |
| CN112836699A (en) * | 2020-11-30 | 2021-05-25 | 爱泊车美好科技有限公司 | Long-time multi-target tracking-based berth entrance and exit event analysis method |
-
2021
- 2021-06-22 CN CN202110689288.8A patent/CN113449624A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060061680A (en) * | 2004-12-02 | 2006-06-08 | 주식회사 대우일렉트로닉스 | System and method for detecting location of car parking |
| CN106652052A (en) * | 2016-12-30 | 2017-05-10 | 苏州远扬智能科技有限公司 | Parking lot entrance and exit management system and parking lot entrance and exit management method |
| CN107680382A (en) * | 2017-02-24 | 2018-02-09 | 上海享泊信息科技有限公司 | Licence plate recognition method, module, cloud server and managing system of car parking |
| CN111353369A (en) * | 2019-10-16 | 2020-06-30 | 智慧互通科技有限公司 | Application method and system of high-order video of urban roadside parking in assisting criminal investigation |
| CN112836699A (en) * | 2020-11-30 | 2021-05-25 | 爱泊车美好科技有限公司 | Long-time multi-target tracking-based berth entrance and exit event analysis method |
| CN112820137A (en) * | 2020-12-31 | 2021-05-18 | 金茂智慧科技(广州)有限公司 | Parking lot management method and device |
Non-Patent Citations (2)
| Title |
|---|
| 耿磊;梁晓昱;肖志涛;李月龙;: "基于多形态红外特征与深度学习的实时驾驶员疲劳检测", 红外与激光工程, no. 02 * |
| 邬敏杰;穆平安;张彩艳;: "基于眼睛和嘴巴状态的驾驶员疲劳检测算法", 计算机应用与软件, no. 03 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163107B (en) | Method and device for recognizing roadside parking behavior based on video frames | |
| CN111339994B (en) | Method and device for judging temporary illegal parking | |
| CN111739335B (en) | Parking detection method and device based on visual difference | |
| CN110909692A (en) | Abnormal license plate recognition method and device, computer storage medium and electronic equipment | |
| CN111582256A (en) | Parking management method and device based on radar and visual information | |
| CN113160575A (en) | Traffic violation detection method and system for non-motor vehicles and drivers | |
| CN113205689B (en) | Multi-dimension-based roadside parking admission event judgment method and system | |
| CN113055823B (en) | Method and device for managing shared bicycle based on road side parking | |
| CN111739338A (en) | Parking management method and system based on multiple types of sensors | |
| CN112487908A (en) | Front vehicle line pressing behavior detection and dynamic tracking method based on vehicle-mounted video | |
| CN113205691A (en) | Method and device for identifying vehicle position | |
| CN111611886B (en) | Parking information verification method and device based on vehicle behavior analysis | |
| CN112861773A (en) | Multi-level-based berthing state detection method and system | |
| CN112836699A (en) | Long-time multi-target tracking-based berth entrance and exit event analysis method | |
| CN113450575B (en) | Management method and device for roadside parking | |
| CN113205690B (en) | Roadside parking departure event judgment method and system based on multiple dimensions | |
| CN113869258A (en) | Traffic incident detection method and device, electronic equipment and readable storage medium | |
| CN112766222B (en) | Method and device for assisting in identifying vehicle behavior based on berth line | |
| CN113449605A (en) | Multi-dimension-based roadside vehicle illegal parking judgment method and system | |
| CN111951601B (en) | Method and device for identifying parking positions of distribution vehicles | |
| CN113449624A (en) | Method and device for determining vehicle behavior based on pedestrian re-recognition | |
| CN113570871A (en) | Multidimensional vehicle personnel getting-on and getting-off judgment method and system | |
| CN113473077A (en) | Multi-dimension-based roadside reverse parking judgment method and system | |
| CN114140762A (en) | Method for automatically identifying vehicle driving direction | |
| CN113283303A (en) | License plate recognition method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yan Jun Inventor after: Yang Xueming Inventor after: Wang Yiyao Inventor after: Liu Dong Inventor before: Yan Jun Inventor before: Yang Xueming |