CN115578698A - Vehicle axle type recognition method, device, electronic device and storage medium - Google Patents
Vehicle axle type recognition method, device, electronic device and storage medium Download PDFInfo
- Publication number
- CN115578698A CN115578698A CN202211119805.9A CN202211119805A CN115578698A CN 115578698 A CN115578698 A CN 115578698A CN 202211119805 A CN202211119805 A CN 202211119805A CN 115578698 A CN115578698 A CN 115578698A
- Authority
- CN
- China
- Prior art keywords
- image
- axle
- detected
- preset
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
-
- 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
- G06T2207/30242—Counting objects in image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a vehicle axle type identification method, a vehicle axle type identification device, an electronic device and a storage medium, wherein the vehicle axle type identification method comprises the following steps: updating the image to be detected into image cache information in response to the fact that a first position relation between an axle tracking result of a target vehicle in the image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset cache condition until the image to be detected accords with a preset cache termination condition based on the axle tracking result and the image cache information; and performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image processing result to obtain axle type information of the target vehicle. The vehicle axle type identification method based on the vehicle images realizes accurate identification of the vehicle axle type, does not need to rely on manual reading or laser radar scanning, and therefore can reduce labor cost and equipment cost for identifying the axle type of the vehicle.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a vehicle axle type identification method and apparatus, an electronic apparatus, and a storage medium.
Background
At present, depending on the technical development backgrounds of smart cities and safe cities, a close and inseparable relationship exists between the source control of the cargo vehicles and the realization of road safety management. The axle type identification of the cargo vehicle is used as a primary link of the 'source over-control' business, and the identification result is a key index for measuring the reliability of the 'source over-control' measure.
However, the axle type identification of the truck is still performed by manual reading or laser radar scanning, so the current axle type identification scheme needs high labor cost on one hand and high equipment cost on the other hand when a laser radar identification system is used.
Aiming at the problem that the cost for identifying the vehicle axle type is high in the related technology, no effective solution is provided at present.
Disclosure of Invention
The embodiment provides a vehicle axle type identification method, a vehicle axle type identification device, an electronic device and a storage medium, and aims to solve the problem that the cost for identifying the vehicle axle type is high in the related art.
In a first aspect, in the present embodiment, there is provided a vehicle axle type identification method, including:
responding to a first position relation between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is acquired in real time, and meeting a preset cache condition, updating the image to be detected into image cache information until the image to be detected meets the preset cache termination condition based on the axle tracking result and the image cache information; the image to be detected is a multi-frame image containing a wheel axle object of the target vehicle;
and according to the local characteristics of the wheel axle object in the image cache information, performing image processing on the image to be detected in the image cache information, and performing axle type identification based on the image processing result to obtain the axle type information of the target vehicle.
In some embodiments, the preset caching condition includes: the first wheel axle object tracked from the image to be detected touches the early warning identifier;
the preset cache termination condition comprises the following steps: and tracking a new wheel axle object from the image to be detected within a preset time period.
In some embodiments, the updating the to-be-detected map into image cache information includes:
and in the process of updating the image to be detected to the image cache information, counting the number of cache frames of the image in the image cache information until determining that a new wheel axle object touches the early warning identifier based on the wheel axle tracking result, and resetting and counting the number of cache frames.
In some of these embodiments, the method further comprises:
and responding to the wheel axle tracking result that a new wheel axle object is not updated in a preset time period, and confirming that the image to be detected meets the preset buffer termination condition when the buffer frame number of the image in the image buffer information reaches a preset frame number threshold value.
In some embodiments, the updating, in response to a first positional relationship between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, meeting a preset caching condition, the image to be detected into image caching information until it is determined that the image to be detected meets a preset caching termination condition based on the axle tracking result and the image caching information includes:
responding to the fact that a first position relation between a wheel axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset caching condition, and adjusting and updating inter-frame step distance of image caching information according to a displacement vector of the target vehicle;
and updating the image to be detected into the image cache information based on the adjusted interframe step pitch until the image to be detected meets the preset cache termination condition based on the wheel axle tracking result and the image cache information.
In some embodiments, the performing, according to the local feature of the axle object in the image cache information, image processing on an image to be detected in the image cache information, and performing axle type recognition based on a result of the image processing to obtain the axle type information of the target vehicle includes:
and performing image splicing on the images to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image splicing result to obtain the axle type information of the target vehicle.
In some embodiments, the performing axle type identification based on the result of the image processing to obtain the axle type information of the target vehicle includes:
carrying out wheel axle detection on the image processing result to obtain a first wheel axle detection result;
and coding and arranging the distance of each wheel axle object based on a preset distance coding rule and the distance proportion of each wheel axle object contained in the first wheel axle detection result, and determining the axle type information of the target vehicle based on the coding and arranging result.
In some embodiments, in response to a first positional relationship between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, meeting a preset caching condition, the image to be detected is updated into image caching information until the image to be detected meets the preset caching termination condition based on the axle tracking result and the image caching information, and the method further includes:
detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain a second axle detection result;
and associating the second wheel axle detection result with a preset wheel axle tracking linked list according to an angular point distance measurement method, updating the wheel axle tracking linked list based on the association result, and identifying the wheel axle tracking linked list as the wheel axle tracking result.
In some embodiments, the detecting, according to the trained detection model, the axle object of the target vehicle in the image to be detected to obtain a second axle detection result includes:
detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain an initial detection result of the axle object;
and screening the initial detection result based on the position information of the wheel axle object and the confidence coefficient of the initial detection result to obtain a second wheel axle detection result.
In some embodiments, in response to a first positional relationship between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, meeting a preset caching condition, the image to be detected is updated into image caching information until it is determined that the image to be detected meets a preset caching termination condition based on the axle tracking result and the image caching information, the method further includes:
determining a second position relation between a first tracked wheel axle object in the image to be detected and a plurality of preset identifiers according to the wheel axle tracking result;
determining the driving direction of the target vehicle based on the second position relation, and screening out an identifier corresponding to the driving direction from the plurality of preset identifiers to serve as an early warning identifier; wherein a pre-established correspondence exists between the plurality of preset identifiers and the entry direction.
In a second aspect, there is provided in the present embodiment a vehicle axle type identifying device comprising: the device comprises a cache module and an identification module; wherein:
the caching module is used for responding to the fact that a first position relation between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset caching condition, updating the image to be detected into image caching information until the image to be detected accords with the preset caching termination condition based on the axle tracking result and the image caching information; the image to be detected is a multi-frame image containing a wheel axle object of the target vehicle;
the identification module is used for carrying out image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and carrying out axle type identification based on the image processing result to obtain the axle type information of the target vehicle.
In a third aspect, in the present embodiment, there is provided an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the vehicle axle type identification method according to the first aspect.
In a fourth aspect, in the present embodiment, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the vehicle axle type identification method described in the first aspect above.
Compared with the related art, the vehicle axle type identification method, the vehicle axle type identification device, the electronic device and the storage medium provided in the embodiment update the image to be detected into the image cache information in response to the fact that the first position relation between the axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, meets the preset cache condition until the image to be detected meets the preset cache termination condition based on the axle tracking result and the image cache information; the image to be detected is a multi-frame image containing a wheel axle object of a target vehicle; and performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image processing result to obtain axle type information of the target vehicle. The vehicle axle type identification method based on the vehicle images realizes accurate identification of the vehicle axle type, does not need to rely on manual reading or laser radar scanning, and therefore can reduce labor cost and equipment cost for identifying the axle type of the vehicle.
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 an application scene diagram of the vehicle axle type identification method of the present embodiment;
fig. 2 is a block diagram of the hardware configuration of a terminal of the vehicle axle type identification method of the present embodiment;
fig. 3 is a flowchart of a vehicle axle type identifying method of the embodiment;
FIG. 4 is a schematic diagram illustrating the splicing result of the present embodiment;
fig. 5 is a schematic diagram illustrating a first axle detection result according to the embodiment;
FIG. 6 is a wheelset partitioning schematic of the present embodiment;
FIG. 7 is a flowchart of a vehicle axle type identification method of the present preferred embodiment;
fig. 8 is a block diagram of the structure of the vehicle axle type recognition device of the present embodiment.
Detailed Description
For a clearer understanding of the objects, technical solutions 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 in this application to "connected," "coupled," and the like is not intended to be 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". Reference in the present application to the terms "first," "second," "third," etc., merely distinguish between similar objects and do not denote a particular order or importance to the objects.
Fig. 1 is an application scenario diagram of the vehicle axle type identification method according to the embodiment. The method embodiment provided in the present embodiment may be applied to the application scenario as shown in fig. 1. The method comprises the following steps that an early warning line L and an early warning line R can be arranged in the visual field range of a camera, when a target vehicle enters from the left side of the visual field of the camera, the early warning line L is enabled, and the early warning line L is identified as an early warning identifier; when the target vehicle enters the right side of the camera view, the warning line R is enabled and recognized as a warning identifier. The target vehicle of the present embodiment may be any one of motor vehicles. Specifically, referring to fig. 1, a truck is taken as an example: and under the condition that the first axle object of the truck entering from the left side is detected to touch the early warning line L in the camera view field, starting to update the image to be detected into the image cache information until the cache of the image to be detected is finished under the condition that the camera view field is determined not to track the new axle object within the preset time period according to the axle tracking result of the truck and the image cache information. And then, according to the local characteristics of the wheel axle object in the image cache information, carrying out image processing on the image to be detected in the image cache information, and carrying out axle type identification on the image processing result to obtain the axle type information of the truck.
The method provided in this embodiment may be executed on a terminal, for example, on a computer or a smart camera, or may be executed on a server, for example, the server uploads an image after the camera captures the image, and the server may identify the image. In addition, the method can be executed at a cloud end or a distributed end. Fig. 2 is a hardware configuration block diagram of a terminal of the vehicle axle type recognition method of the present embodiment, taking an example of execution on the terminal. As shown in fig. 2, the terminal may include one or more processors 202 (only one shown in fig. 2) and a memory 204 for storing data, wherein the processor 202 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may also include a transmission device 206 for communication functions and an input-output device 208. It will be understood by those skilled in the art that the structure shown in fig. 2 is only an illustration and is not a limitation to the structure of the terminal. For example, the terminal may also include more or fewer components than shown in FIG. 2, or have a different configuration than shown in FIG. 2.
The memory 204 may be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the vehicle axle type identification method in the embodiment, and the processor 202 executes various functional applications and data processing by running the computer programs stored in the memory 204, so as to implement the method described above. Memory 204 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 204 may further include memory located remotely from the processor 202, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 206 is used to receive or transmit data via a network. The network described above includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 206 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 206 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
In the present embodiment, a vehicle axle type identification method is provided, and fig. 3 is a flowchart of the vehicle axle type identification method of the present embodiment, as shown in fig. 3, the flowchart includes the steps of:
step S310, in response to the fact that a first position relation between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, meets a preset caching condition, updating the image to be detected into image caching information until the image to be detected meets the preset caching termination condition based on the axle tracking result and the image caching information; the image to be detected is a multi-frame image containing a wheel axle object of the target vehicle.
The early warning identifier may be any one of the graphs that are set in the monitoring screen to determine whether to start the cache of the image to be detected based on the requirement of the actual application scene, for example, an early warning line, an early warning frame, or a plurality of early warning coordinate points that are set in the monitoring screen, or other graphs that are adapted to the monitoring scene, which is not specifically limited herein. Preferably, the warning identifier may be a warning line. Specifically, the wheel axle tracking result is a tracking result of a wheel axle object of the target vehicle detected in the image to be detected. The wheel axle tracking result contains the position information and the corresponding identification information of all the wheel axle objects tracked in the field of view of the camera in the image to be detected. It can be understood that, for the same axle object between different frames, the identification information thereof is unique, and the position information thereof in the axle tracking result is updated in real time as the position of the axle object in the image changes. In addition, the first position relationship can be determined based on the position information of each wheel axle object in the wheel axle tracking result and the position information of the early warning identifier. Preferably, the first tracked wheel axle object in the wheel axle tracking result in the current time period may be determined as the tracked first wheel axle object, and the current position information of the first wheel axle object may be compared with the position information where the warning identifier is located, so as to determine the first position relationship. The image caching information refers to relevant caching information obtained by caching the to-be-detected image meeting the caching condition, such as the cached image, the number of caching frames, and other information which needs to be recorded in the caching process according to the requirements of practical application. Specifically, the image cache information may be located in a cache pool.
The preset cache condition indicates that the wheel axle object touches the early warning identifier, and if the wheel axle object touches the early warning identifier can be determined according to the first position relationship, the first position relationship conforms to the preset cache condition. If the cache termination condition indicates that a new axle object is not tracked from the image to be detected within the preset time period, it indicates that all the axle objects of the target vehicle have appeared in the visual field of the camera, or the target vehicle has left the visual field range of the camera, the image to be detected does not need to be continuously updated into the image cache information, and image processing can be performed based on the current image cache information, for example, image stitching is performed based on the current image cache information. The image to be detected can be determined to meet the preset cache termination condition under the condition that the new axle object of the target vehicle is determined not to be tracked within the preset time period based on the axle tracking result and the cache frame number of the image cache information.
Preferably, when the detected axle object is tracked, the tracking information about the axle object may be updated to a preset tracking chain table, where the tracking chain table is composed of a plurality of nodes, and each node includes a coordinate, a category, and an Identity (id) of a tracked axle object. In addition, the tracking linked list is continuously updated based on the information of the wheel axle object detected in the current frame along with the change of the frame number of the image to be detected. The wheel axle object in each node comprises a tracking frame, and when the tracking frame of the first wheel axle object in the tracking chain table touches the identifier, for example, when a target vehicle drives into the field of view of the camera from the left side, the tracking frame of the first wheel axle object touches a preset left-side early warning line, the image to be detected is updated to the image cache information. During the caching process, the number of caching frames of the wheel axle object touching the early warning line at present can be counted through a preset caching frame number accumulation field, after the next wheel axle object touches the early warning line, the caching frame number accumulation field is cleared, and the counting of the caching frame number is restarted.
It can be understood that, if a new axle object of the target vehicle is not tracked within a preset time period, the buffer frame number accumulation field will not be cleared within the preset time period, and based on this, it may be determined whether a new axle object is not tracked within the preset time period by determining a value of the buffer frame number accumulation field, that is, the buffer frame number, and a preset frame number threshold. In addition, whether the tracking chain table is updated by a new node in a preset time period or not can be represented, and whether a new wheel axle object is tracked in the preset time period or not can be represented. Based on this, whether to terminate the buffering can be determined by combining the number of buffering frames in the image buffering information and the wheel axis tracking result.
And then, under the condition that the first position relation between the wheel axle tracking result and the preset early warning identifier accords with the preset caching condition, the image to be detected is updated to the image caching information. It is understood that the image to be detected is a plurality of frames of images collected by the camera in the field of view thereof, including the axle object of the target vehicle. Illustratively, the caching process may specifically include: enabling a preset image cache signal cache _ start _ flag, setting the state of the signal cache _ start _ flag to be 1, for example, starting caching from a current frame image in an image to be detected, storing the current frame image into a preset cache pool, continuously caching images of subsequent frames along with the change of the number of image frames acquired by a camera until the image to be detected accords with a preset cache termination condition based on a wheel axle tracking result and image cache information, setting the state of the image cache signal cache _ start _ flag to be 0, and ending the caching operation of the image to be detected.
And step S320, performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image processing result to obtain axle type information of the target vehicle.
After the cache is finished, the splicing cache finishing flag bit cache _ stop _ flag may be set to 1, and the image processing on the image to be detected of the image cache information in the cache pool is started. In particular, the image processing may be image stitching. And sequentially inputting an image set to be spliced consisting of the images to be detected in the cache pool into a preset image splicing algorithm according to the sequence of entering the cache pool to complete matching and splicing of local features, so that a complete spliced image is output, and an image splicing result is obtained. Fig. 4 is a schematic diagram of the splicing result of this embodiment. As can be seen from fig. 4, in the monitoring scene, the camera may be mounted at a height corresponding to the axle of the target vehicle, so that the axle object of the target vehicle can be completely detected in the camera view. Due to the limitation of the field of view of the camera and the structure of the target vehicle, the frame of image to be detected acquired by the camera may only contain a part of wheel axle objects of the target vehicle, for example, only one wheel axle object of the target vehicle. Therefore, it is necessary to obtain an image containing all the wheel axle objects of the target vehicle as shown in fig. 4 by image stitching the images to be detected in the image buffer information in step S310.
After the result of the image processing is obtained, the result of the image processing may be input into a preset axle detection algorithm, all the axle objects therein are detected, and the axle type information of the target vehicle is determined based on the positional relationship between all the axle objects in the result of the image processing. Preferably, the axle type of the target vehicle may be determined based on the distance ratio between all detected axle objects.
In the above steps S310 to S320, in response to that the first positional relationship between the wheel axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, conforms to the preset caching condition, the image to be detected is updated to the image caching information until it is determined that the image to be detected conforms to the preset caching termination condition based on the wheel axle tracking result and the image caching information; the method comprises the steps that an image to be detected is a multi-frame image containing a wheel axle object of a target vehicle; and performing image processing on the image to be detected in the image cache information according to the local characteristics of the axle object in the image cache information, and performing axle type identification based on the result of the image processing to obtain axle type information of the target vehicle. The vehicle axle type identification method based on the vehicle images realizes accurate identification of the vehicle axle type, does not need to rely on manual reading or laser radar scanning, and therefore can reduce labor cost and equipment cost for identifying the axle type of the vehicle.
Further, in one embodiment, the preset caching condition includes: the first wheel axle object tracked from the image to be detected touches the early warning identifier; the preset cache termination condition comprises the following steps: and tracking a new wheel axle object from the image to be detected within a preset time period.
It will be appreciated that the detection of the first wheel axle object touching the early warning identifier in the field of view of the camera indicates that there is a target vehicle entering the detection area of the axle type identification, and therefore it is necessary to initiate axle type identification for the target vehicle. Accordingly, if no new axle object is tracked from the image to be detected within the predetermined time period, this indicates that the target vehicle has left the field of view of the camera or that all wheels of the target vehicle have moved away from the field of view of the camera, so that the buffering of the image to be detected can be terminated. Based on this, in this embodiment, the tracked first axle object touching the early warning identifier is determined as a mark for starting the caching of the image to be detected, so that the time point for caching the image to be detected can be accurately started, a new axle object that is not tracked from the image to be detected within a preset time period is used as a mark for terminating the caching, and therefore the integrity of the axle position image of the target vehicle obtained by splicing subsequent images can be improved.
In an embodiment, based on the step S310, the step of updating the image to be detected into the image cache information may further include the following steps:
step S311, in the process of updating the image to be detected to the image cache information, counting the number of cache frames of the image in the image cache information until determining that a new wheel axle object touches the early warning identifier based on the wheel axle tracking result, and resetting and counting the number of cache frames.
Specifically, based on the above analysis, it is known that a new axle object may not be tracked within a preset time period, and the buffering of the image to be detected may be terminated. In the caching process, by setting a count field of the caching frame number, when a new wheel axle object touches the early warning identifier, the caching frame number is cleared and counted again, and if the new wheel axle object does not touch the early warning identifier within a period of time, the caching frame number is continuously accumulated within the period of time. Therefore, if the buffer frame number exceeds the preset frame number threshold, it indicates that no new axle object touches the warning identifier within the preset time period. According to the embodiment, the counting of the number of the caching frames is set in the image caching process, and the driving-in and driving-out conditions of the axle object of the target vehicle in the field of view of the camera can be accurately judged, so that the time for terminating caching can be more accurately determined, excessive useless information is avoided being cached, and the efficiency of subsequent image processing and identification is improved.
Further, in one embodiment, the vehicle axle type identification method may further include:
step S312, in response to the wheel axle tracking result not updating the new wheel axle object within the preset time period and the number of the cache frames of the images in the image cache information reaching the preset frame number threshold, confirming that the images to be detected meet the preset cache termination condition.
As in step S311, on the one hand, the on-coming and off-going situation of the axle object in the field of view of the camera can be determined based on the number of the buffer frames in the image buffer information. On the other hand, if no new axle object is added in the axle tracking result obtained in real time within the preset time period, all the axle objects of the target vehicle can be indicated to leave the visual field of the camera. Therefore, the wheel axle tracking result and the image cache information can be integrated, and the image to be detected is stopped being updated to the image cache information when the wheel axle tracking result does not update the new wheel axle object within the preset time period and the cache frame number of the image in the image cache information reaches the preset frame number threshold. The embodiment determines the cache termination condition based on the updating condition of the axle object and the number of the cache frames in the axle tracking result, can more accurately determine the time for ending the cache, and reduces the cache of the invalid image.
Additionally, in an embodiment, based on the step S310, in response to that the first position relationship between the axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, meets the preset caching condition, the image to be detected is updated into the image caching information until it is determined that the image to be detected meets the preset caching termination condition based on the axle tracking result and the image caching information, which may specifically include the following steps:
step 313, responding to that a first position relation between a wheel axle tracking result of the target vehicle in the image to be detected and a preset early warning identifier, which is acquired in real time, meets a preset caching condition, and adjusting and updating the inter-frame step distance of the image caching information according to the displacement vector of the target vehicle.
The inter-frame step represents the number of image frames spaced apart when the image to be detected is buffered. For example, if the inter-frame step size is 5 frames, when the to-be-detected image is updated to the image buffer information, one frame of to-be-detected image is buffered every 5 frames. The displacement vector of the target vehicle includes a vehicle speed and a vehicle entrance direction of the target vehicle. Wherein the vehicle speed of the target vehicle may be an average displacement speed of the N images of the first axle object of the target vehicle before touching the early warning identifier. The driving-in direction of the target vehicle can be determined based on the position relationship between the first axle object and a plurality of preset identifiers, for example, if the abscissa of the central point of the first axle object is smaller than the abscissa of the left warning line, the target vehicle is driven into the field of view of the camera from left to right; similarly, if the abscissa of the center point of the first axle object is greater than the abscissa of the right precaution line, the target vehicle is driven from right to left into the camera view. The center of the axle object may be a center point of the detection frame of the axle object.
In order to adapt the number of buffered images to the displacement vector of the target vehicle, the images in the image buffer information can contain all wheel axle objects of the target vehicle. The faster the vehicle speed of the target vehicle, the smaller the number of frames of the buffer interval. Preferably, the inter-frame step distance for buffering the image to be detected can be adaptively adjusted according to the proportional relation between the vehicle speed and the set speed threshold. For example, the vehicle speed of the target vehicle is V _ vehicle, the preset speed threshold is V _ set, and the proportional relationship therebetween is α. The inter-frame step Δ step may be 1/α. When alpha is 1, the buffer is buffered for the full frame rate.
And step S314, updating the image to be detected into image cache information based on the adjusted interframe step distance until the image to be detected meets the preset cache termination condition based on the wheel axle tracking result and the image cache information.
In the steps S313 to S314, the inter-frame step distance is adaptively adjusted based on the displacement vector of the target vehicle, so that occurrence of redundant images can be effectively avoided, and the efficiency of subsequent processing of image cache information is improved.
Additionally, in an embodiment, based on the step S320, the image processing is performed on the image to be detected in the image cache information according to the local feature of the axle object in the image cache information, and the axle type recognition is performed based on the result of the image processing to obtain the axle type information of the target vehicle, which may specifically include:
s321, performing image splicing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image splicing result to obtain axle type information of the target vehicle.
In the embodiment, the images to be detected of different frames are spliced based on the local features of the axle objects, so that the distribution arrangement condition of the complete axle objects of the target vehicle can be determined, the axle type information of the target vehicle can be determined based on the splicing result, and the accuracy of axle type identification is improved.
Additionally, in an embodiment, based on the step S320, performing axle type identification based on the result of the image processing to obtain the axle type information of the target vehicle, specifically, the method may include the following steps:
step S322, performing wheel axle detection on the image processing result to obtain a first wheel axle detection result.
Specifically, the spliced image may be subjected to axle detection based on a preset axle detection algorithm, so as to obtain all axle objects of the target vehicle contained therein. It should be noted that, before the images to be detected are spliced, the axle object included in each frame of the image to be detected is only a part of the axle object of the target vehicle, for example, an axle object. And after the image splicing, all wheel axle objects of the target vehicle are obtained through detection. Fig. 5 is a schematic diagram illustrating a first axle detection result according to the embodiment. As shown in fig. 5, each of the boxes is a detection box of the wheel axle object, and the object in the detection box is the wheel axle object.
Step S323, based on a preset distance coding rule and a distance ratio of each axle object included in the first axle detection result, code-arranging the distances of each axle object, and determining the axle type information of the target vehicle based on the result of the code-arrangement.
Also illustrated by way of example in fig. 5, the target vehicle may have different wheel axles with different spacing. Therefore, the distance proportion of each wheel axle object can be coded and arranged based on the preset distance coding rule. Illustratively, when the ratio of the center point distance between two adjacent axle objects to the preset minimum reference distance is smaller than the preset ratio, the two adjacent axle objects are confirmed to be in the close proximity state, and the distance between the two adjacent axle objects is coded to be 0, otherwise, the two adjacent axle objects are confirmed to be in the spaced state, and the distance between the two adjacent axle objects is coded to be 1. Based on this, FIG. 6 is a schematic diagram of wheelset partitioning. After the distances between the axle objects in fig. 5 are encoded according to the distance encoding rule, the axle group division as shown in fig. 6 can be obtained. Wherein, different numeral numbers 1 to 6 in fig. 6 represent different wheel axle objects, the wheel axle distance coded value of 10100 of the target vehicle can be obtained. And mapping corresponding axle type information of the target vehicle based on the wheel axle distance code value, namely the code arrangement result.
Additionally, in an embodiment, before determining that the image to be detected meets the preset cache termination condition based on the wheel axle tracking result and the image cache information, the vehicle axle type identification method may further include, in response to that the first positional relationship between the wheel axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier obtained in real time meets the preset cache condition, updating the image to be detected into the image cache information:
step S331, detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain a second axle detection result;
and S332, associating the second wheel axle detection result with a preset wheel axle tracking linked list according to an angular point distance measurement method, updating the wheel axle tracking linked list based on the association result, and identifying the wheel axle tracking linked list as a wheel axle tracking result.
For example, updating the axle tracking chain table based on the second axle detection result may be performed according to the following procedure: after an axle object is detected in an object to be detected, initializing node information node _ info and chain table length L in an axle tracking chain track _ list, wherein the node information node _ info comprises a tracking target coordinate rect, a class and id information. The second axle detection result is an axle detection target set axis _ od _ set. And performing association matching on the axle detection target set and the tracking nodes of the axle tracking linked list in a corner distance measurement mode. And if the association is successful, updating the information of the corresponding tracking node in the wheel axle tracking chain table by using the attribute information, such as coordinates and categories, of the wheel axle detection target centralized detection frame. And regarding the wheel axle detection frame which is not matched with the tracking node in the wheel axle detection target set as a new wheel axle object, initializing the attribute information of the new wheel axle object into a new tracking node, updating the new tracking node into a wheel axle tracking chain table, and distributing a tracking id.
Wherein, the association process may be: assuming that the coordinates of the upper left corner of the detection frame BBox of each axle object in the axle detection target set are (x 1, y 1), the coordinates of the lower right corner are (x 2, y 2), the coordinates of the upper left corner of the tracking frame BBox _ track corresponding to the nodes in the axle tracking linked list are (x 3, y 3), the coordinates of the lower right corner are (x 4, y 4), and the calculation method of the angular point distance measurement method is as follows:
firstly, whether an intersection exists between the current detection frame BBox and the tracking frame BBox _ track is judged, and the judgment mode is as follows:
where max () denotes taking the maximum value and min () denotes taking the minimum value. If x is satisfied i ≤x j And y is i ≤y j If the detection frame BBox and the tracking frame BBox _ track are in an intersection state, the corner distance measurement calculation formula is as follows:
wherein, Δ d 1 Is the distance, Δ d, between the coordinates of the upper left corners of the two boxes 2 And delta d is the distance between the coordinates of the upper left corner of the detection frame and the coordinates of the lower right corner of the tracking frame. Association degree associate between two frames score The calculation formula is as follows:
associate score ＝1-(Δd 1 +Δd 2 )/Δd (3)
if associate score If the value of (A) is greater than the set threshold value, the association of the two is considered to be successful, otherwise, the association of the two is failed.
Further, in an embodiment, based on the step S332, detecting the axle object of the target vehicle in the image to be detected according to the trained detection model, to obtain a second axle detection result, specifically including: detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain an initial detection result of the axle object; and screening the initial detection result based on the position information of the axle object and the confidence coefficient of the initial detection result to obtain a second axle detection result.
For example, for a near-field scene target vehicle, the central point of the detection frame of the axle object is often located in the lower half of the image to be detected, and therefore, the axle object can be screened by judging whether the position information of the axle object belongs to a preset region. And if the wheel axle object is located in the preset area, setting the valid state bit of the detection frame corresponding to the wheel axle object to be 1, and identifying the wheel axle object as a valid object, otherwise, setting the valid state bit to be 0, and identifying the wheel axle object as an invalid object. Invalid axle objects are not updated into the axle tracking results. In addition, the detected axle objects can be screened based on the confidence of the detection frame, so as to improve the reliability of the second axle detection result.
In addition, if no valid axle object exists in the valid area in the field of view of the camera, the axle type identification function of the target vehicle is in an Idle state, the state value of the corresponding Idle state bit Idle _ flag is 0, the buffer cumulative frame number frame _ cnt is set to 0, and the detection of the axle object is continuously performed until the valid axle object is detected.
Additionally, in an embodiment, before the image to be detected is updated to the image cache information in response to the first position relationship between the wheel axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, meeting the preset cache condition until the image to be detected is determined to meet the preset cache termination condition based on the wheel axle tracking result and the image cache information, the vehicle axle type identification method may further include the following steps:
step S341, determining a second position relationship between the first tracked wheel axle object in the image to be detected and the plurality of preset identifiers according to the wheel axle tracking result. The second positional relationship may include distances between the center point of the axle object and a plurality of preset identifiers, or a coordinate size. For example, the second positional relationship may be a magnitude relationship between an abscissa of a center point of a tracking frame of the first tracked wheel axle object and an abscissa of the left warning line and an abscissa of the right warning line, respectively.
Step S342, determining the entrance direction of the target vehicle based on the second positional relationship, and screening out an identifier corresponding to the entrance direction among a plurality of preset identifiers as an early warning identifier; the preset identifiers and the driving direction have a pre-established corresponding relation.
Continue to take the left and right early warning lines as an example. If the abscissa of the central point of the tracking frame of the first axle object is smaller than the abscissa corresponding to the left early warning line, the driving-in direction of the target vehicle is from left to right to drive into the field of view of the camera. If the abscissa of the central point of the tracking frame of the first wheel axle object is larger than the abscissa corresponding to the right early warning line, the driving-in direction of the target vehicle is from right to left to drive into the field of view of the camera. It is understood that the present embodiment may also determine the driving-in direction based on other position relationships between the axle object and the identifier, such as a distance, a relative angle, and the like, which is not described herein again.
The present embodiment is described and illustrated below by means of preferred embodiments.
Fig. 7 is a flowchart of the vehicle axle type identification method of the present preferred embodiment. As shown in fig. 7, the vehicle axle type identification method includes the steps of:
s701, reading an image to be detected in a visual field acquired by a camera;
step S702, performing wheel axle detection and effective target judgment on an image to be detected to obtain a first wheel axle detection result;
step S703, associating the first axle detection result with a preset axle tracking linked list based on an angular point distance measurement method, and updating the axle tracking linked list based on the association result to obtain an axle tracking result;
step S704, if no effective wheel axle object exists in the effective area in the camera visual field, setting a bit 0 of a status bit for executing the vehicle axle type identification method, and clearing the accumulated frame number of the wheel axle object until the effective wheel axle object is detected in the camera visual field;
step S705, enabling the early warning line under the condition that the first tracked wheel axle object touches the early warning line;
step S706, determining the entering direction of the target vehicle based on the position relation between the first tracked wheel axle object and the left and right early warning lines, determining the vehicle speed of the target vehicle based on the image information before the first tracked wheel axle object touches the early warning lines, and obtaining a displacement vector based on the vehicle speed and the entering direction;
step S707, enabling the buffer signal, starting to update the image to be detected into the image buffer information, counting the buffer frame number of the image in the image buffer information until a new wheel axle object touches the early warning line, resetting the count and counting again;
step S708, judging whether the number of the buffer frames reaches a preset frame number threshold value and whether a new wheel axle object is not added in the wheel axle tracking chain table within a preset time period; if yes, executing step S709, otherwise, continuing to execute step S707;
step S709, terminating the caching of the image to be detected, and performing image splicing on the image to be detected in the image caching information to obtain a target splicing result;
step S710, performing axle type recognition on the target splicing result to obtain axle type information of the target vehicle;
and step S711, reporting the axle type, the axle number, the target splicing result and the load information of the corresponding wagon balance of the target vehicle.
In this embodiment, a vehicle axle type identification apparatus is further provided, which is used to implement the above embodiments and preferred embodiments, and the description of which is already given is omitted. The terms "module," "unit," "subunit," and the like as used below may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Fig. 8 is a block diagram showing the structure of the vehicle axle type recognition device 80 of the present embodiment, and as shown in fig. 8, the vehicle axle type recognition device 80 includes: a caching module 82 and an identification module 84; wherein:
the cache module 82 is configured to update the image to be detected into image cache information in response to that a first positional relationship between an axle tracking result of the target vehicle in the image to be detected and a preset early warning identifier, which is obtained in real time, meets a preset cache condition, until it is determined that the image to be detected meets a preset cache termination condition based on the axle tracking result and the image cache information; the method comprises the steps that an image to be detected is a multi-frame image containing a wheel axle object of a target vehicle;
and the identification module 84 is configured to perform image processing on the image to be detected in the image cache information according to the local features of the axle object in the image cache information, and perform axle type identification based on the result of the image processing to obtain axle type information of the target vehicle.
The vehicle axle type recognition device 80 updates the image to be detected into the image cache information in response to the fact that the first positional relationship between the axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, meets the preset cache condition, until the image to be detected meets the preset cache termination condition based on the axle tracking result and the image cache information; the image to be detected is a multi-frame image containing a wheel axle object of a target vehicle; and performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image processing result to obtain axle type information of the target vehicle. The vehicle axle type identification method based on the vehicle images realizes accurate identification of the vehicle axle type, does not need to rely on manual reading or laser radar scanning, and therefore can reduce labor cost and equipment cost for identifying the axle type of the vehicle.
It should be noted that 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 may be located in different processors in any combination.
There is also provided in this embodiment an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
updating the image to be detected into image cache information in response to the fact that a first position relation between an axle tracking result of a target vehicle in the image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset cache condition until the image to be detected accords with a preset cache termination condition based on the axle tracking result and the image cache information, and finishing caching the image to be detected; the method comprises the steps that an image to be detected is a multi-frame image containing a wheel axle object of a target vehicle;
and performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image processing result to obtain axle type information of the target vehicle.
It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementations, and details are not described again in this embodiment.
In addition, in combination with the vehicle axle type identification method provided in the above embodiment, a storage medium may also be provided to implement in this embodiment. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the vehicle axle type identification methods in the above embodiments.
It is noted that the information and data referred to in this application (including but not limited to data for analysis, stored data, displayed data, etc.) are subject to relevant legal regulations.
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 such a development effort might be complex and lengthy, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, and is not intended to limit the present disclosure to the particular forms disclosed herein.
Reference throughout this application to "an embodiment" means 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 the phrase 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-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the 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, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (13)
1. A vehicle axle type identification method, characterized by comprising:
responding to a first position relation between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is acquired in real time, and meeting a preset cache condition, updating the image to be detected into image cache information until the image to be detected meets the preset cache termination condition based on the axle tracking result and the image cache information; the image to be detected is a multi-frame image containing a wheel axle object of the target vehicle;
and performing image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification on the basis of the image processing result to obtain the axle type information of the target vehicle.
2. The vehicle axle type identification method according to claim 1, characterized in that:
the preset caching condition comprises the following steps: the first axle object tracked from the image to be detected touches the early warning identifier;
the preset cache termination condition comprises the following steps: and tracking a new wheel axle object from the image to be detected within a preset time period.
3. The vehicle axle type identification method according to claim 2, wherein said updating said image to be detected into image buffer information comprises:
and in the process of updating the image to be detected to the image cache information, counting the number of cache frames of the image in the image cache information until determining that a new wheel axle object touches the early warning identifier based on the wheel axle tracking result, and resetting and counting the number of cache frames.
4. The vehicle axle type identification method according to claim 3, characterized in that the method further comprises:
and responding to the wheel axle tracking result that a new wheel axle object is not updated in a preset time period, and confirming that the image to be detected meets the preset buffer termination condition when the buffer frame number of the image in the image buffer information reaches a preset frame number threshold value.
5. The vehicle axle type identification method according to claim 1, wherein the updating the image to be detected into image cache information in response to the first positional relationship between the axle tracking result of the target vehicle in the image to be detected and the preset early warning identifier, which is obtained in real time, meeting a preset cache condition until the image to be detected is determined to meet a preset cache termination condition based on the axle tracking result and the image cache information comprises:
responding to the fact that a first position relation between a wheel axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset caching condition, and adjusting and updating inter-frame step distance of image caching information according to a displacement vector of the target vehicle;
and updating the image to be detected into the image cache information based on the adjusted interframe step distance until the image to be detected meets a preset cache termination condition based on the wheel axle tracking result and the image cache information.
6. The vehicle axle type identification method according to claim 1, wherein the image processing is performed on the image to be detected in the image cache information according to the local features of the axle object in the image cache information, and the axle type identification is performed based on the result of the image processing to obtain the axle type information of the target vehicle, and the method comprises the following steps:
and performing image splicing on the images to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and performing axle type identification based on the image splicing result to obtain the axle type information of the target vehicle.
7. The vehicle axle type recognition method according to claim 1, wherein the performing axle type recognition based on the result of the image processing to obtain the axle type information of the target vehicle includes:
carrying out wheel axle detection on the image processing result to obtain a first wheel axle detection result;
and coding and arranging the distance of each wheel axle object based on a preset distance coding rule and the distance proportion of each wheel axle object contained in the first wheel axle detection result, and determining the axle type information of the target vehicle based on the result of coding and arranging.
8. The vehicle axle type identification method according to claim 1, wherein in response to a first positional relationship between an axle tracking result of a target vehicle in an image to be detected acquired in real time and a preset early warning identifier meeting a preset cache condition, the image to be detected is updated into image cache information until it is determined that the image to be detected meets a preset cache termination condition based on the axle tracking result and the image cache information, the method further comprises:
detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain a second axle detection result;
and associating the second wheel axle detection result with a preset wheel axle tracking linked list according to an angular point distance measurement method, updating the wheel axle tracking linked list based on the association result, and identifying the wheel axle tracking linked list as the wheel axle tracking result.
9. The vehicle axle type identification method according to claim 8, wherein the detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain a second axle detection result comprises:
detecting the axle object of the target vehicle in the image to be detected according to the trained detection model to obtain an initial detection result of the axle object;
and screening the initial detection result based on the position information of the wheel axle object and the confidence coefficient of the initial detection result to obtain a second wheel axle detection result.
10. The vehicle axle type identification method according to any one of claims 1 to 9, wherein in response to a first positional relationship between an axle tracking result of a target vehicle in an image to be detected acquired in real time and a preset warning identifier meeting a preset cache condition, the image to be detected is updated into image cache information until it is determined that the image to be detected meets a preset cache termination condition based on the axle tracking result and the image cache information, the method further comprises:
determining a second position relation between a first tracked wheel axle object in the image to be detected and a plurality of preset identifiers according to the wheel axle tracking result;
determining the driving direction of the target vehicle based on the second position relation, and screening an identifier corresponding to the driving direction from the plurality of preset identifiers to serve as an early warning identifier; wherein a pre-established correspondence exists between the plurality of preset identifiers and the entry direction.
11. A vehicle axle type identifying device, characterized by comprising: the device comprises a cache module and an identification module; wherein:
the caching module is used for responding to the fact that a first position relation between an axle tracking result of a target vehicle in an image to be detected and a preset early warning identifier, which is obtained in real time, accords with a preset caching condition, updating the image to be detected into image caching information until the image to be detected accords with the preset caching termination condition based on the axle tracking result and the image caching information; the image to be detected is a multi-frame image containing a wheel axle object of the target vehicle;
the identification module is used for carrying out image processing on the image to be detected in the image cache information according to the local characteristics of the wheel axle object in the image cache information, and carrying out axle type identification based on the image processing result to obtain the axle type information of the target vehicle.
12. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the vehicle axle type identification method according to any one of claims 1 to 10.
13. 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 vehicle axle type identification method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211119805.9A CN115578698A (en) | 2022-09-15 | 2022-09-15 | Vehicle axle type recognition method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211119805.9A CN115578698A (en) | 2022-09-15 | 2022-09-15 | Vehicle axle type recognition method, device, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115578698A true CN115578698A (en) | 2023-01-06 |
Family
ID=84582043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211119805.9A Pending CN115578698A (en) | 2022-09-15 | 2022-09-15 | Vehicle axle type recognition method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115578698A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116358679A (en) * | 2023-05-16 | 2023-06-30 | 中铁大桥局集团有限公司 | Dynamic weighing method for urban rail transit train bridge |
-
2022
- 2022-09-15 CN CN202211119805.9A patent/CN115578698A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116358679A (en) * | 2023-05-16 | 2023-06-30 | 中铁大桥局集团有限公司 | Dynamic weighing method for urban rail transit train bridge |
| CN116358679B (en) * | 2023-05-16 | 2024-04-23 | 中铁大桥局集团有限公司 | Dynamic weighing method for urban rail transit train bridge |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109828564B (en) | Optimization method and device for unmanned vehicle path planning and terminal equipment | |
| CN109484435B (en) | Train positioning method and device suitable for intelligent rail transit detection system | |
| EP4152204A1 (en) | Lane line detection method, and related apparatus | |
| WO2019205020A1 (en) | Road condition recognition method, apparatus and device | |
| WO2021056341A1 (en) | Lane line fusion method, lane line fusion apparatus, vehicle, and storage medium | |
| CN112747755B (en) | Method and device for determining road route, readable storage medium and map updating system | |
| CN115578698A (en) | Vehicle axle type recognition method, device, electronic device and storage medium | |
| CN114332707A (en) | Method and device for determining equipment effectiveness, storage medium and electronic device | |
| CN114926809A (en) | Passable area detection method and device, moving tool and storage medium | |
| CN110991215A (en) | Lane line detection method, lane line detection device, storage medium, and electronic apparatus | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN114092909A (en) | Lane line extraction method and device, vehicle and storage medium | |
| CN113052141A (en) | Method and device for detecting parking position of vehicle | |
| US20220219699A1 (en) | On-board apparatus, driving assistance method, and driving assistance system | |
| CN112598668A (en) | Defect identification method and device based on three-dimensional image and electronic equipment | |
| CN116086429A (en) | Map updating method, device, equipment and computer readable storage medium | |
| CN116358528A (en) | Map updating method, map updating device, self-mobile device and storage medium | |
| CN112859109B (en) | Unmanned aerial vehicle panoramic image processing method and device and electronic equipment | |
| CN111986347B (en) | Device management method, device, electronic device and storage medium | |
| CN115062240A (en) | Parking lot sorting method and device, electronic equipment and storage medium | |
| CN114202272A (en) | Vehicle and goods matching method and device based on electronic fence, storage medium and terminal | |
| CN115905247A (en) | High-precision map updating method, system, medium, terminal and server | |
| JP7232727B2 (en) | Map data management device and map data management method | |
| CN112685517B (en) | Method and apparatus for identifying diverging/converging regions | |
| CN111709354A (en) | Method and device for identifying target area, electronic equipment and road side equipment |
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 |