WO2020133488A1 - 车辆检测方法和设备 - Google Patents
车辆检测方法和设备 Download PDFInfo
- Publication number
- WO2020133488A1 WO2020133488A1 PCT/CN2018/125800 CN2018125800W WO2020133488A1 WO 2020133488 A1 WO2020133488 A1 WO 2020133488A1 CN 2018125800 W CN2018125800 W CN 2018125800W WO 2020133488 A1 WO2020133488 A1 WO 2020133488A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- area
- vehicle
- vehicle candidate
- image
- processed
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/571—Depth or shape recovery from multiple images from focus
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V10/87—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using selection of the recognition techniques, e.g. of a classifier in a multiple classifier system
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- Embodiments of the present invention relate to the field of image processing technology, and in particular, to a vehicle detection method and device.
- Automatic detection of vehicles is an indispensable content in automatic driving and assisted driving technologies.
- camera equipment is provided on the vehicle.
- the camera equipment captures images of the vehicles on the road.
- the vehicle detection model through deep learning or machine learning on the image, the vehicle in front can be automatically detected.
- the invention provides a vehicle detection method and equipment, which improves the accuracy and reliability of vehicle detection and reduces the probability of false detection and missed detection.
- the present invention provides a vehicle detection method, including:
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the present invention provides a vehicle detection method, including:
- the distance value of the vehicle candidate area is obtained according to the distance between the two tail lights and the focal length of the shooting device;
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the present invention provides a vehicle detection device, including: a memory, a processor, and a camera device;
- the shooting device is used to obtain an image to be processed
- the memory is used to store program codes
- the processor calls the program code, and when the program code is executed, it is used to perform the following operations:
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the present invention provides a vehicle detection device, including: a memory, a processor, and a shooting device;
- the shooting device is used to obtain an image to be processed
- the memory is used to store program codes
- the processor calls the program code, and when the program code is executed, it is used to perform the following operations:
- the distance value of the vehicle candidate area is obtained according to the distance between the two tail lights and the focal length of the shooting device;
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the present invention provides a storage medium, including: a readable storage medium and a computer program, where the computer program is used to implement the vehicle detection method provided in any one embodiment of the first aspect or the second aspect.
- the present invention provides a program product including a computer program (ie, executing instructions), the computer program being stored in a readable storage medium.
- the processor may read the computer program from a readable storage medium, and the processor executes the computer program for implementing the vehicle detection method provided in any one embodiment of the first aspect or the second aspect.
- the present invention provides a vehicle detection method and device, which can obtain the distance value of the vehicle candidate area in the image to be processed through the image to be processed and the depth information of each pixel in the image to be processed, which can be determined according to the distance value of the vehicle candidate area
- the detection model corresponding to the vehicle candidate area. Since different detection models are used to detect vehicles according to different distances, the accuracy and reliability of vehicle detection are improved, and the probability of false detection and missed detection is reduced.
- FIG. 1 is a flowchart of a vehicle detection method according to Embodiment 1 of the present invention.
- FIG. 2 is a schematic diagram of a correspondence between a preset detection model and a preset distance value range provided by Embodiment 1 of the present invention
- Embodiment 3 is a schematic diagram of a vehicle candidate area provided by Embodiment 1 of the present invention.
- FIG. 4 is a flowchart of a vehicle detection method according to Embodiment 2 of the present invention.
- FIG. 5 is a schematic diagram of the principle of tail lamp area matching in Embodiment 2 of the present invention.
- FIG. 6 is a flowchart of a vehicle detection method according to Embodiment 3 of the present invention.
- FIG. 7 is a schematic structural diagram of a vehicle detection device according to an embodiment of the present invention.
- FIG. 1 is a flowchart of a vehicle detection method according to Embodiment 1 of the present invention.
- the execution subject may be a vehicle detection device, which is applied to a scene where vehicle detection is performed on an image captured by a shooting device.
- the shooting equipment is set on a device that can be used on the road, for example: a vehicle, an auxiliary driving device on the vehicle, a driving recorder installed on the vehicle, an intelligent electric vehicle, a scooter, a balance car, and so on.
- the vehicle detection device may be provided on the above-mentioned device that can be used on the road.
- the vehicle detection device may include the shooting device.
- the vehicle detection method provided in this embodiment may include:
- the image to be processed is a two-dimensional image.
- the depth information of each pixel in the image to be processed is a kind of three-dimensional information, which is used to indicate the distance of the pixel from the shooting device.
- this embodiment does not limit the implementation manner of acquiring the depth information of the image.
- Lidar ranging technology can obtain the three-dimensional information of the scene through laser scanning.
- the basic principle is: emit laser light into space, and record the time between the signal of each scanning point from the lidar to the object in the measured scene, and then reflect back to the lidar through the object, and then calculate the surface of the object and the lidar the distance between.
- a device operating on the road may be provided with a binocular vision system or a monocular vision system.
- the imaging device is used to obtain two images of the measured object from different positions, and the distance of the object is obtained by calculating the position deviation between corresponding points in the two images.
- a binocular vision system two images can be acquired through two imaging devices.
- a monocular vision system two images can be acquired at two different locations through an imaging device.
- acquiring the depth information of each pixel in the image to be processed may include:
- the vehicle candidate area is first obtained.
- the vehicle candidate area may or may not include vehicles, and needs to be further determined through the detection model.
- the detection model may be a model commonly used in deep learning or machine learning.
- the detection model may be a neural network model. For example, Convolutional Neural Networks (CNN) model.
- the size, location and characteristics of the objects occupied by objects with different distances are different. For example, if the vehicle is closer to the shooting device, the vehicle occupies a larger area in the image, usually located in the lower left corner or lower right corner of the image, and can display the vehicle door, side area, etc.
- the area occupied by the vehicle in the image is relatively small, usually located in the middle of the image, and can display the tail and side of the vehicle.
- the occupied area of the vehicle in the image is smaller, usually located in the upper middle of the image, and only a small tail can be exposed.
- the distance value of the vehicle candidate area can be obtained.
- the distance value may indicate the distance between the vehicle and the shooting device in the physical space. According to the distance value, a detection model matching the distance value is obtained. Subsequently, it will be more accurate to use the detection model to determine whether the vehicle candidate area includes vehicles.
- the distance value of the vehicle candidate region is not limited.
- the distance value may be the depth value of any pixel in the vehicle candidate area.
- the distance value may be an average value or a weighted average value determined according to the depth value of pixels in the vehicle candidate area.
- multiple preset detection models are preset.
- the preset detection model corresponds to a certain preset distance value range.
- the range of the preset distance corresponding to each preset detection model is not limited.
- the vehicle detection method provided in this embodiment can obtain the distance value of the vehicle candidate area through the to-be-processed image and the depth information of each pixel in the image, and the matching detection model can be determined according to the distance value, which improves the detection model Accuracy.
- the vehicle detection method provided in this embodiment uses different detection models to detect vehicles according to different distances, which improves the accuracy and reliability of vehicle detection and reduces the probability of false detections and missed detections.
- the vehicle detection method provided in this embodiment may further include:
- the detection model corresponding to the vehicle candidate area is used to determine whether the vehicle candidate area is a vehicle area.
- determining the detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area may include:
- the preset detection model corresponding to the preset distance value range where the distance value of the vehicle candidate area is located is determined as the detection corresponding to the vehicle candidate area model.
- the preset detection models corresponding to each preset distance value range where the distance value of the vehicle candidate area is located are determined as The detection model corresponding to the vehicle candidate area.
- FIG. 2 is a schematic diagram of a correspondence between a preset detection model and a preset distance value range according to Embodiment 1 of the present invention.
- the preset distance value range of 0-90 meters corresponds to the detection model 1
- the preset distance value range of 75-165 meters corresponds to the detection model 2
- the preset distance value range of 150-200 meters corresponds to the detection model 3.
- the distance ranges corresponding to the detection model 1 and the detection model 2 have overlapping areas, which are specifically 75 to 90 meters.
- the distance ranges corresponding to the detection model 2 and the detection model 3 have overlapping regions, specifically 150 to 165 meters.
- the detection model corresponding to the vehicle candidate area is detection model 1.
- the detection models corresponding to the vehicle candidate area are detection model 1 and detection model 2.
- the detection model 1 and the detection model 2 can be adopted respectively to determine whether the vehicle candidate area is a vehicle area.
- the detection results of the detection model 1 and the detection model 2 are integrated to determine whether the vehicle candidate area is a vehicle area. For example, when both the detection model 1 and the detection model 2 are used to determine the vehicle candidate area as the vehicle area, the vehicle candidate area is finally determined as the vehicle area. For another example, when the detection model 1 or the detection model 2 can be used to determine the vehicle candidate area as the vehicle area, the vehicle candidate area is finally determined as the vehicle area.
- obtaining the distance value of the vehicle candidate area in the image to be processed according to the image to be processed and the depth information may include:
- the first neural network model is used to obtain the road area in the image.
- This embodiment does not limit the way of expressing the road area.
- the road area may be represented by the boundary line of the road.
- the boundary line of the road can be determined by multiple edge points of the road.
- the road area may include a plane area determined by the boundary line of the road.
- the pixels in the image to be processed can be clustered.
- the so-called cluster analysis refers to the analysis method of grouping a collection of physical or abstract objects into multiple classes composed of similar objects.
- cluster analysis is performed according to the depth information of the pixels, and pixels at different positions in the image to be processed can be clustered to form multiple clusters. Then, the vehicle candidate area adjacent to the road area is determined among the plurality of clusters, and the distance value of the vehicle candidate area is acquired.
- this embodiment does not limit the implementation manner of the first neural network model.
- the candidate vehicle area adjacent to the road area includes: a candidate vehicle area whose minimum distance from pixels in the road area is less than or equal to a preset distance.
- This embodiment does not limit the specific value of the preset distance.
- the distance value of the vehicle candidate area is the depth value of the cluster center point of the vehicle candidate area.
- FIG. 3 is a schematic diagram of a vehicle candidate area provided in Embodiment 1 of the present invention. As shown in Fig. 3, traverse the pixels in the image to be processed, and perform k-means clustering on each pixel according to the depth. There are two points a and b, and the corresponding depth values are Da and Db. In the x, y coordinate value is Xa, Ya, Xb, Yb, then the distance function is:
- k is a positive number.
- Vehicle candidate areas adjacent to the road area are obtained as areas 100 to 104 in FIG. 3.
- Vehicle candidate areas may include vehicles, street signs, street lights, and even grass, walls, etc., all of which are bordered by roads and meet the results of cluster analysis.
- the detection model will be used to further determine whether the vehicle candidate area is a vehicle area.
- This embodiment provides a vehicle detection method, including: acquiring depth information of a pixel to be processed and each pixel in the image to be processed, and acquiring distance values of vehicle candidate regions in the image to be processed according to the image to be processed and the depth information, according to The distance value of the vehicle candidate area determines the detection model corresponding to the vehicle candidate area.
- the vehicle detection method provided in this embodiment can use different detection models to detect vehicles according to different distances by acquiring the distance value of the vehicle candidate area, which improves the accuracy and reliability of vehicle detection and reduces the probability of false detection and missed detection .
- the vehicle detection method provided in this embodiment before determining the detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area in S103, may further include:
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the distance value of the vehicle candidate area needs to be checked. S103 is executed only after the verification is passed. By verifying the distance value, the accuracy of the distance value can be further determined. Therefore, the detection model corresponding to the vehicle candidate area is determined according to the distance value, which further improves the accuracy of the detection model.
- verifying the distance value of the vehicle candidate area may include:
- the verification distance value of the vehicle candidate area is obtained according to the distance between the two tail lights and the focal length of the shooting device.
- the vehicle candidate area is a vehicle area.
- Another calculation method can be used to obtain the distance value of a vehicle candidate area through the distance between the two tail lights on the vehicle, which is called the check distance value.
- the check distance value By comparing the distance value of the vehicle candidate area previously obtained from the depth information of the pixels in the image to be processed with the check distance value obtained from the distance between the tail lights, it can be determined whether the distance value of the vehicle candidate area is accurate. If the difference between the distance value of the vehicle candidate area and the check distance value is within the preset difference value range, the check passes. If the difference between the distance value of the vehicle candidate area and the check distance value is within the preset difference value range, the check fails.
- the specific value of the preset difference range is not limited.
- the verification distance value is determined according to the focal length of the shooting device, the preset vehicle width, and the distance between the outer edges of the two tail lights.
- the check distance value can be determined by the following formula:
- Distance indicates that focus_length indicates the focal length of the shooting device
- W indicates the preset vehicle width
- d indicates the distance between the outer edges of the two tail lights.
- This embodiment does not limit the specific value of the preset vehicle width.
- the value of W can range from 2.8 to 3m.
- existing image processing methods such as image recognition and image detection may be used to determine whether the vehicle candidate area includes a pair of tail lights of the vehicle.
- the image processing method is used to determine whether the vehicle candidate area includes a pair of vehicle tail lights, which improves the accuracy of the judgment.
- a deep learning algorithm to determine whether the vehicle candidate area includes a pair of tail lights of the vehicle, a deep learning algorithm, a machine learning algorithm, or a neural network algorithm may be used.
- determining whether the vehicle candidate area includes a pair of tail lights of the vehicle may include:
- the image to be processed is horizontally corrected to obtain a horizontally corrected image.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the image may be horizontally corrected according to the horizontal line of the shooting device, so that the x-axis direction of the image is parallel to the horizontal line.
- the horizontal line of the photographing equipment is obtained by an inertial measurement unit (IMU) in the photographing equipment.
- IMU inertial measurement unit
- focus_length represents the focal length
- pitch_angle represents the pitch axis rotation angle
- roll_angle represents the roll axis rotation angle
- Image_width represents the image width
- Image_height represents the image height.
- determining whether the vehicle candidate area includes a pair of tail lights of the vehicle may include:
- the region corresponding to the vehicle candidate region in the horizontally corrected image is input to the second neural network model, and it is determined whether the vehicle candidate region includes a pair of tail lights of the vehicle.
- the second neural network model is used to determine whether the image includes a pair of tail lights of the vehicle.
- this embodiment does not limit the implementation manner of the second neural network model.
- the method may further include:
- the first to-be-processed area and the second to-be-processed area are acquired in the horizontally corrected image.
- the first area to be processed includes a left tail light area
- the second area to be processed includes a right tail light area.
- Mirror the left taillight area to obtain the first target area and perform image matching in the second area to be processed according to the first target area, or mirror the right taillight area to obtain the second target area, according to the second target area. Perform image matching in the first area to be processed to obtain a matching result.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- FIG. 5 is a schematic diagram of the principle of tail lamp area matching in Embodiment 2 of the present invention.
- the first to-be-processed area 203 is obtained based on the left tail light area (not shown).
- the second to-be-processed area 202 is obtained according to the right tail light area 201.
- the right tail light area 201 performs mirror image inversion to obtain the second target area 204.
- Image matching may be performed in the first to-be-processed area 203 along the horizontal direction according to the second target area 204.
- the distance between the second target area 204 and the left tail light area may be calculated. If the distance is less than the first preset threshold, it is determined that the image matching is successful.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- a matching area closest to the second target area 204 is determined in the first to-be-processed area 203 along the horizontal direction. If the distance between the matching area and the second target area 204 is less than the second preset threshold, it is determined that the image matching is successful.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the specific values of the first preset threshold and the second preset threshold are not limited.
- the second neural network model is used to determine that the vehicle candidate area includes a pair of tail lights of the vehicle, and after obtaining the tail light areas, the accuracy of determining whether the vehicle candidate area includes the pair of tail lights of the vehicle is further improved by determining whether the tail light areas match.
- the method may further include:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- performing image matching in the horizontally corrected image according to the third target area to obtain a matching result may include:
- image matching is performed on both sides in the horizontal direction with the third target area as the center, and the matching area closest to the third target area is obtained.
- the tail lights on the vehicle are arranged symmetrically and located on the same horizontal line. Since the horizontally corrected image has been horizontally corrected, centering the third target area as the center and performing image matching to both ends in the horizontal direction can quickly find the closest matching area that matches the third target area, which improves Processing speed.
- determining whether the vehicle candidate area includes a pair of tail lights of the vehicle according to the matching result may include:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the vehicle candidate area does not include a pair of tail lights of the vehicle.
- the matching area is an area symmetrical to the tail light area determined by image matching.
- the distance between the matching area and the tail light area should be approximately equal to the distance between the two tail lights on the vehicle. Therefore, by matching the distance between the area and the tail light area, it can be determined whether the vehicle candidate area includes a pair of tail lights of the vehicle.
- This embodiment provides a vehicle detection method. By checking the distance value of the vehicle candidate region obtained from the depth information of the pixels in the image to be processed, the accuracy of the distance value can be further determined. Therefore, the detection model corresponding to the vehicle candidate area is determined according to the distance value, and the accuracy of vehicle detection is further improved.
- the execution subject may be a vehicle detection device, which is applied to a scene where vehicle detection is performed on an image captured by a shooting device.
- the shooting equipment is set on a device that can be used on the road, for example: a vehicle, an auxiliary driving device on the vehicle, a driving recorder installed on the vehicle, an intelligent electric vehicle, a scooter, a balance car, and so on.
- the vehicle detection device may be provided on the above-mentioned device that can be used on the road.
- the vehicle detection device may include the shooting device.
- the vehicle detection method provided by this embodiment may include:
- S601 Acquire an image to be processed.
- S602 Obtain a vehicle candidate area in the image to be processed.
- the distance value of the candidate vehicle area is obtained according to the distance between the two tail lights and the focal length of the photographing device.
- S604 Determine a detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area.
- the vehicle detection method provided in this embodiment for the vehicle candidate area in the image to be processed, if the vehicle candidate area includes a pair of tail lights of the vehicle, it means that the vehicle candidate area is a vehicle area.
- the distance value of the vehicle candidate area is obtained through the distance between the two tail lights on the vehicle.
- the matching detection model can be determined according to the distance value, which improves the accuracy of the detection model.
- the vehicle detection method provided in this embodiment uses different detection models to detect vehicles according to different distances, which improves the accuracy and reliability of vehicle detection and reduces the probability of false detections and missed detections.
- this embodiment does not limit how to obtain the vehicle candidate region in the image to be processed.
- image processing methods may be used, or deep learning, machine learning, or neural network algorithms may be used.
- the vehicle detection method provided in this embodiment may further include:
- the detection model corresponding to the vehicle candidate area is used to determine whether the vehicle candidate area is a vehicle area.
- the distance value is determined according to the focal length of the shooting device, the preset vehicle width, and the distance between the outer edges of the two tail lights.
- the method before determining that the candidate vehicle area includes a pair of tail lights of the vehicle, the method further includes:
- the image to be processed is horizontally corrected to obtain a horizontally corrected image.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the vehicle candidate area includes a pair of tail lights of the vehicle, including:
- the region corresponding to the vehicle candidate region in the horizontally corrected image is input to the neural network model to determine whether the vehicle candidate region includes a pair of vehicle tail lights.
- the method further includes:
- the first to-be-processed area and the second to-be-processed area are acquired in the horizontally corrected image.
- the first area to be processed includes a left tail light area
- the second area to be processed includes a right tail light area.
- Mirror the left taillight area to obtain the first target area and perform image matching in the second area to be processed according to the first target area, or mirror the right taillight area to obtain the second target area, according to the second target area. Perform image matching in the first area to be processed to obtain a matching result.
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the method further includes:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- performing image matching in the horizontally corrected image according to the third target area to obtain a matching result includes:
- image matching is performed on both sides in the horizontal direction with the third target area as the center, and the matching area closest to the third target area is obtained.
- the candidate vehicle area includes a pair of tail lights of the vehicle, including:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the vehicle candidate area does not include a pair of tail lights of the vehicle.
- determining the detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area includes:
- the preset detection model corresponding to the preset distance value range where the distance value of the vehicle candidate area is located is determined as the detection corresponding to the vehicle candidate area model.
- the distance value of the vehicle candidate region in this embodiment is similar to the "check distance value of the vehicle candidate region” in the second embodiment shown in FIGS. 4 to 5, and the “neural network model” in this embodiment It is similar to the “checking distance value of the second vehicle candidate area” in the second embodiment shown in FIGS. 4 to 5.
- the technical principles and technical effects are similar and will not be repeated here.
- Embodiment 1 of the present invention provides a vehicle detection device, as shown in FIG. 7.
- 7 is a schematic structural diagram of a vehicle detection device according to an embodiment of the present invention.
- the vehicle detection device provided in this embodiment is used to execute the vehicle detection method provided in the embodiments shown in FIGS. 1 to 5.
- the vehicle detection device provided in this embodiment may include: a memory 12, a processor 11, and a shooting device 13;
- the shooting device 13 is used to obtain an image to be processed
- Memory 12 used to store program code
- the processor 11, calling the program code, is used to perform the following operations when the program code is executed:
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- processor 11 is specifically used for:
- the candidate vehicle area adjacent to the road area includes: a candidate vehicle area whose minimum distance from pixels in the road area is less than or equal to a preset distance.
- processor 11 is specifically used for:
- K-means algorithm is used for cluster analysis.
- the distance value of the vehicle candidate area is the depth value of the cluster center point of the vehicle candidate area.
- processor 11 is specifically used for:
- the preset detection model corresponding to the preset distance value range where the distance value of the vehicle candidate area is located is determined as the detection corresponding to the vehicle candidate area model.
- processor 11 is also used for:
- the step of determining the detection model corresponding to the vehicle candidate area according to the distance value of the vehicle candidate area is performed.
- processor 11 is specifically used for:
- the verification distance value of the vehicle candidate area is obtained according to the distance between the two tail lights and the focal length of the shooting device;
- the verification distance value is determined according to the focal length of the shooting device, the preset vehicle width, and the distance between the outer edges of the two tail lights.
- processor 11 is specifically used for:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- the region corresponding to the vehicle candidate region in the horizontally corrected image is input to the second neural network model, and it is determined whether the vehicle candidate region includes a pair of tail lights of the vehicle.
- the processor 11 is further used to:
- the first to-be-processed area includes a left tail light area
- the second to-be-processed area includes a right tail light area
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the processor 11 is further used to:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- image matching is performed on both sides in the horizontal direction with the third target area as the center, and the matching area closest to the third target area is obtained.
- processor 11 is specifically used for:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the vehicle candidate area does not include a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- the vehicle detection device provided in this embodiment is used to execute the vehicle detection method provided in the embodiments shown in FIGS. 1 to 5.
- the technical principles and technical effects are similar and will not be repeated here.
- Embodiment 2 of the present invention provides a vehicle detection device, as shown in FIG. 7.
- 7 is a schematic structural diagram of a vehicle detection device according to an embodiment of the present invention.
- the vehicle detection device provided in this embodiment is used to execute the vehicle detection method provided in the embodiment shown in FIG. 6.
- the vehicle detection device provided in this embodiment may include: a memory 12, a processor 11, and a shooting device 13;
- the shooting device 13 is used to obtain an image to be processed
- Memory 12 used to store program code
- the processor 11, calling the program code, is used to perform the following operations when the program code is executed:
- the distance value of the vehicle candidate area is obtained according to the distance between the two tail lights and the focal length of the shooting device;
- the detection model corresponding to the vehicle candidate area is determined according to the distance value of the vehicle candidate area.
- the distance value is determined according to the focal length of the shooting device, the preset vehicle width, and the distance between the outer edges of the two tail lights.
- processor 11 is specifically used for:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- the region corresponding to the vehicle candidate region in the horizontally corrected image is input to the neural network model to determine whether the vehicle candidate region includes a pair of vehicle tail lights.
- the processor 11 is further used to:
- the first to-be-processed area includes a left tail light area
- the second to-be-processed area includes a right tail light area
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the processor 11 is specifically used to:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- image matching is performed on both sides in the horizontal direction with the third target area as the center, and the matching area closest to the third target area is obtained.
- processor 11 is specifically used for:
- the vehicle candidate area includes a pair of tail lights of the vehicle.
- the vehicle candidate area does not include a pair of tail lights of the vehicle.
- processor 11 is specifically used for:
- the preset detection model corresponding to the preset distance value range where the distance value of the vehicle candidate area is located is determined as the detection corresponding to the vehicle candidate area model.
- the vehicle detection device provided in this embodiment is used to execute the vehicle detection method provided in the embodiment shown in FIG. 6.
- the technical principles and technical effects are similar and will not be repeated here.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明实施例提供一种车辆检测方法和设备。其中,车辆检测方法包括:获取待处理图像和待处理图像中每个像素点的深度信息;根据待处理图像和深度信息,获取待处理图像中车辆候选区域的距离值;根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。可以根据不同的距离采用不同的检测模型检测车辆,提升了车辆检测的准确性和可靠性,降低了误检测和漏检测概率。
Description
本发明实施例涉及图像处理技术领域,尤其涉及一种车辆检测方法和设备。
自动检测车辆,在自动驾驶、辅助驾驶技术中是不可缺少的内容。通常,车辆上设置有摄像设备。车辆在行使过程中,摄像设备对道路上的车辆进行拍摄获得图像。利用车辆检测模型,通过对图像进行深度学习或者机器学习,可以自动检测出前方的车辆。
但是,采用同一种车辆检测模型对车辆进行检测,误检测/漏检测的概率很大,导致车辆检测的准确率较低。
发明内容
本发明提供一种车辆检测方法和设备,提升了车辆检测的准确性和可靠性,降低了误检测和漏检测概率。
第一方面,本发明提供一种车辆检测方法,包括:
获取待处理图像和所述待处理图像中每个像素点的深度信息;
根据所述待处理图像和所述深度信息,获取所述待处理图像中车辆候选区域的距离值;
根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
第二方面,本发明提供一种车辆检测方法,包括:
获取待处理图像;
获取所述待处理图像中的车辆候选区域;
若判断所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取所述车辆候选区域的距离值;
根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
第三方面,本发明提供一种车辆检测设备,包括:存储器、处理器和拍 摄设备;
所述拍摄设备,用于获取待处理图像;
所述存储器,用于存储程序代码;
所述处理器,调用所述程序代码,当所述程序代码被执行时,用于执行以下操作:
获取所述待处理图像中每个像素点的深度信息;
根据所述待处理图像和所述深度信息,获取所述待处理图像中车辆候选区域的距离值;
根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
第四方面,本发明提供一种车辆检测设备,包括:存储器、处理器和拍摄设备;
所述拍摄设备,用于获取待处理图像;
所述存储器,用于存储程序代码;
所述处理器,调用所述程序代码,当所述程序代码被执行时,用于执行以下操作:
获取所述待处理图像中的车辆候选区域;
若判断所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取所述车辆候选区域的距离值;
根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
第五方面,本发明提供一种存储介质,包括:可读存储介质和计算机程序,所述计算机程序用于实现第一方面或第二方面任一实施方式提供的车辆检测方法。
第六方面,本发明提供一种程序产品,该程序产品包括计算机程序(即执行指令),该计算机程序存储在可读存储介质中。处理器可以从可读存储介质读取该计算机程序,处理器执行该计算机程序用于实现第一方面或第二方面任一实施方式提供的车辆检测方法。
本发明提供一种车辆检测方法和设备,通过待处理图像和待处理图像中每个像素点的深度信息,可以获取待处理图像中车辆候选区域的距离值,根据车辆候选区域的距离值可以确定车辆候选区域对应的检测模型。由于根据不同的距离采用不同的检测模型检测车辆,提升了车辆检测的准确性和可靠 性,降低了误检测和漏检测概率。
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明实施例一提供的车辆检测方法的流程图;
图2为本发明实施例一提供的预设检测模型与预设距离值范围之间对应关系的示意图;
图3为本发明实施例一提供的车辆候选区域的示意图;
图4为本发明实施例二提供的车辆检测方法的流程图;
图5为本发明实施例二中尾灯区域匹配的原理示意图;
图6为本发明实施例三提供的车辆检测方法的流程图;
图7为本发明实施例提供的车辆检测设备的结构示意图。
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
图1为本发明实施例一提供的车辆检测方法的流程图。本实施例提供的车辆检测方法,执行主体可以为车辆检测设备,应用于对拍摄设备拍摄的图像进行车辆检测的场景。其中,拍摄设备设置在可以行使在道路上的装置,例如:车辆、车辆上的辅助驾驶设备、安装在车辆上的行车记录仪、智能电动车、滑板车、平衡车,等等。可选的,车辆检测设备可以设置在上述可以行使在道路上的装置。可选的,车辆检测设备可以包括所述拍摄设备。
如图1所示,本实施例提供的车辆检测方法,可以包括:
S101、获取待处理图像和待处理图像中每个像素点的深度信息。
其中,待处理图像为二维图像。待处理图像中每个像素点的深度信息是一种三维信息,用于指示像素点距离拍摄设备的远近。
需要说明的是,本实施例对于获取图像的深度信息的实现方式不做限定。
例如,行使在道路上的装置可以安装激光雷达。激光雷达测距技术通过激光扫描的方式可以得到场景的三维信息。其基本原理是:向空间发射激光,并记录各个扫描点的信号从激光雷达到达被测场景中的物体,随后又经过物体反射回到激光雷达的相隔时间,据此计算出物体表面与激光雷达之间的距离。
又例如,行使在道路上的装置可以设置双目视觉系统或者单目视觉系统。基于视差原理,利用成像设备从不同的位置获取被测物体的两幅图像,通过计算两幅图像中对应点间的位置偏差来获取物体的距离。在双目视觉系统中,可以通过两个成像设备获取两幅图像。在单目视觉系统中,可以通过成像设备在两个不同的位置获取两幅图像。
可选的,S101中,获取待处理图像中每个像素点的深度信息,可以包括:
获取待处理图像对应的雷达图或者深度图。
将雷达图或者深度图与待处理图像匹配,获取待处理图像中每个像素点的深度信息。
S102、根据待处理图像和深度信息,获取待处理图像中车辆候选区域的距离值。
S103、根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。
具体的,根据待处理图像和图像中每个像素点的深度信息,首先获得车辆候选区域。车辆候选区域中可能包括车辆,也可能不包括车辆,需要通过检测模型进一步确定。需要说明的是,本实施例对于检测模型的实现方式不做限定。可选的,检测模型可以为深度学习或者机器学习中常用的模型。可选的,检测模型可以为神经网络模型。例如,卷积神经网络(Convolutional Neural Networks,CNN)模型。
在图像中,远近不同的物体占用的区域大小、位置和物体显示出来的特征均不相同。例如,如果车辆距离拍摄设备较近,车辆在图像中占用的区域较大,通常位于图像的左下角或者右下角,能够显示车辆的车门、侧面区域 等。对于中距离的车辆,车辆在图像中占用的区域相对较小,通常位于图像的中部,能够显示车辆的尾部和侧面。而对于远距离的车辆,车辆在图像中的占用区域更小,通常位于图像的中上部,只有很小的尾部可以露出。
因此,根据待处理图像和图像中每个像素点的深度信息,可以获得车辆候选区域的距离值。该距离值可以指示物理空间中车辆与拍摄设备之间的远近程度。根据该距离值,获取与该距离值匹配的检测模型。后续,采用该检测模型确定车辆候选区域是否包括车辆,将更加准确。
需要说明的是,本实施例对于车辆候选区域的距离值不做限定。比如,该距离值可以为车辆候选区域中任一个像素点的深度值。又比如,该距离值可以为根据车辆候选区域内像素点的深度值确定的平均值或者加权平均值。
需要说明的是,在本实施例中,会预先设置多个预设检测模型。预设检测模型对应有一定的预设距离值范围。本实施例对于每个预设检测模型分别对应的预设距离值范围不做限定。可选的,相邻的预设检测模型对应的预设距离值范围可以存在重叠区域。
可见,本实施例提供的车辆检测方法,通过待处理图像和图像中每个像素点的深度信息,可以获得车辆候选区域的距离值,根据距离值可以确定匹配的检测模型,提升了检测模型的精确度。相比于采用单一模型检测车辆,本实施例提供的车辆检测方法,根据不同的距离采用不同的检测模型检测车辆,提升了车辆检测的准确性和可靠性,降低了误检测和漏检测概率。
可选的,本实施例提供的车辆检测方法,还可以包括:
采用车辆候选区域对应的检测模型,确定车辆候选区域是否为车辆区域。
可选的,S103中,根据车辆候选区域的距离值确定车辆候选区域对应的检测模型,可以包括:
根据多个预设距离值范围与多个预设检测模型之间的对应关系,将车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为车辆候选区域对应的检测模型。
可选的,如果车辆候选区域的距离值所在的预设距离值范围的数量大于1,则将车辆候选区域的距离值所在的每个预设距离值范围对应的预设检测模型,均确定为车辆候选区域对应的检测模型。
下面通过示例对预设检测模型与预设距离值范围之间的对应关系进行说 明。
图2为本发明实施例一提供的预设检测模型与预设距离值范围之间对应关系的示意图。如图2所示,在200米内,预先设置3个预设距离值范围。其中,预设距离值范围0~90米对应检测模型1,预设距离值范围75~165米对应检测模型2,预设距离值范围150~200米对应检测模型3。检测模型1和检测模型2对应的距离值范围存在重叠区域,具体为75~90米。检测模型2和检测模型3对应的距离值范围存在重叠区域,具体为150~165米。
假设,车辆候选区域的距离值为50米,则车辆候选区域对应的检测模型为检测模型1。假设,车辆候选区域的距离值为80米,则车辆候选区域对应的检测模型为检测模型1和检测模型2。可以分别采用检测模型1和检测模型2,确定车辆候选区域是否为车辆区域。最后综合检测模型1和检测模型2的检测结果,确定车辆候选区域是否为车辆区域。例如,当采用检测模型1和检测模型2均确定车辆候选区域为车辆区域时,才最终确定车辆候选区域为车辆区域。又例如,当采用检测模型1或者检测模型2可以确定车辆候选区域为车辆区域时,就最终确定车辆候选区域为车辆区域。
可以理解,预设距离值范围的数量越多,每个预设距离值范围的区间越小,对于车辆检测的精细度更高。
可选的,S102中,根据待处理图像和深度信息,获取待处理图像中车辆候选区域的距离值,可以包括:
将待处理图像输入第一神经网络模型,获取待处理图像中的道路区域。
根据深度信息对待处理图像中的像素点进行聚类分析,确定待处理图像中与道路区域邻接的车辆候选区域,并获取车辆候选区域的距离值。
其中,第一神经网络模型用于获取图像中的道路区域。本实施例对于道路区域的表示方式不做限定。例如,道路区域可以通过道路的边界线表示。道路的边界线可以通过道路的多个边缘点确定。又例如,道路区域可以包括道路的边界线确定的平面区域。
根据待处理图像中每个像素点的深度信息可以对待处理图像中的像素点进行聚类分析。所谓聚类分析,是指将物理或者抽象对象的集合分组为类似的对象组成的多个类的分析方法。在本实施例中,根据像素点的深度信息进行聚类分析,可以将待处理图像中不同位置处的像素点聚类,形成多个簇。 然后,在多个簇中确定与道路区域邻接的车辆候选区域,并获取车辆候选区域的距离值。
需要说明的是,本实施例对于第一神经网络模型的实现方式不做限定。
可选的,与道路区域邻接的车辆候选区域,包括:与道路区域中像素点之间的最小距离小于或者等于预设距离的车辆候选区域。
本实施例对于预设距离的具体取值不做限定。
可选的,车辆候选区域的距离值为车辆候选区域的簇中心点的深度值。
需要说明的是,本实施例对于聚类分析算法不做限定。
下面通过示例,以聚类分析算法为K均值(k-means)算法为例进行说明。
图3为本发明实施例一提供的车辆候选区域的示意图。如图3所示,遍历待处理图像中的像素点,对每个像素点按深度进行k-means聚类。设有a,b两点,对应深度值为Da,Db。在x,y坐标的值为Xa,Ya,Xb,Yb,则距离函数为:
Loss=(Da-Db)
2+k((Xa-Xb)
2+(Ya-Yb)
2)
其中,k为正数。
通过k-means算法,得到的与道路区域邻接的车辆候选区域如图3中的区域100~104。车辆候选区域可能包括车辆、路牌、路灯,甚至是草地、墙面等,都是与道路接壤并符合聚类分析结果的。后续,会采用检测模型进一步确定车辆候选区域是否为车辆区域。
本实施例提供一种车辆检测方法,包括:获取待处理图像和待处理图像中每个像素点的深度信息,根据待处理图像和深度信息,获取待处理图像中车辆候选区域的距离值,根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。本实施例提供的车辆检测方法,通过获取车辆候选区域的距离值,可以根据不同的距离采用不同的检测模型检测车辆,提升了车辆检测的准确性和可靠性,降低了误检测和漏检测概率。
图4为本发明实施例二提供的车辆检测方法的流程图。本实施例在上述实施例一的基础上,提供了车辆检测方法的另一种实现方式。如图4所示,本实施例提供的车辆检测方法,在S103,根据车辆候选区域的距离值确定车辆候选区域对应的检测模型之前,还可以包括:
S401、对车辆候选区域的距离值进行校验。
S402、若校验通过,则根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。
具体的,在执行S103之前,需要对车辆候选区域的距离值进行校验。校验通过才执行S103。通过对距离值进行校验,可以进一步确定该距离值的准确性。从而,根据该距离值确定车辆候选区域对应的检测模型,进一步提升了检测模型的准确性。
可选的,S401中,对车辆候选区域的距离值进行校验,可以包括:
判断车辆候选区域是否包括车辆的一对尾灯。
若车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取车辆候选区域的校验距离值。
判断车辆候选区域的距离值与校验距离值之间的差值是否在预设差值范围内。
具体的,如果车辆候选区域包括车辆的尾灯,说明车辆候选区域为车辆区域。通过车辆上两个尾灯之间的距离采用另一种计算方法可以再获得一个车辆候选区域的距离值,称为校验距离值。将之前根据待处理图像中像素点的深度信息获得的车辆候选区域的距离值与根据尾灯间距离获得的校验距离值进行比对,可以确定车辆候选区域的距离值是否准确。如果车辆候选区域的距离值与校验距离值之间的差值在预设差值范围内,校验通过。如果车辆候选区域的距离值与校验距离值之间的差值在预设差值范围内,校验没有通过。
需要说明的是,本实施例对于预设差值范围的具体取值不做限定。
可选的,校验距离值为根据拍摄设备的焦距、预设的车辆宽度和两个尾灯的外边沿之间的距离确定的。
可选的,校验距离值可以通过下面的公式确定:
Distance=focus_length*W/d
其中,Distance表示,focus_length表示拍摄设备的焦距,W表示预设的车辆宽度,d表示两个尾灯的外边沿之间的距离。
本实施例对于预设的车辆宽度的具体取值不做限定。例如,W的取值范围可以为2.8~3m。
可选的,判断车辆候选区域是否包括车辆的一对尾灯,可以采用现有的 图像识别、图像检测等图像处理方法,判断车辆候选区域是否包括车辆的一对尾灯。
由于图像处理方法较为成熟,通过图像处理方法判断车辆候选区域是否包括车辆的一对尾灯,提升了判断的准确性。
可选的,判断车辆候选区域是否包括车辆的一对尾灯,可以采用深度学习算法、机器学习算法或者神经网络算法。
由于深度学习算法、机器学习算法或者神经网络算法基于大量的样本数据训练模型,应用场景更加广泛和全面,因此提升了判断的准确性。
可选的,判断车辆候选区域是否包括车辆的一对尾灯,可以包括:
对待处理图像进行水平校正,获得水平校正图像。
根据水平校正图像中与车辆候选区域对应的区域,判断车辆候选区域是否包括车辆的一对尾灯。
通过对待处理图像先进行水平校正,再判断车辆候选区域是否包括车辆的一对尾灯,消除了图像误差,提升了判断的准确性。
需要说明的是,对图像进行水平校正的方法有很多,本实施例对此不做限定。
示例性的,在一种实现方式中,可以根据拍摄设备的水平线对图像进行水平校正,使得图像的x轴方向与水平线平行。
其中,拍摄设备的水平线通过拍摄设备中的惯性测量单元(Inertial measurement unit,IMU)获得。
假设图像的左上角为原点,地平线直线方程为:ax+by+c=0。其中,
r=tan(pitch_angle)*focus_length
a=tan(roll_angle)
b=1
c=-tan(roll_angle)*Image_width/2+r*sin(roll_angle)*tan(roll_angle)-
Image_height/2+r*cos(roll_angle)
其中,focus_length表示焦距,pitch_angle表示pitch轴旋转角度,roll_angle表示roll轴旋转角度,Image_width表示图像宽度,Image_height表示图像高度。
可选的,根据水平校正图像中与车辆候选区域对应的区域,判断车辆候 选区域是否包括车辆的一对尾灯,可以包括:
将水平校正图像中与车辆候选区域对应的区域输入第二神经网络模型,判断车辆候选区域是否包括车辆的一对尾灯。
其中,第二神经网络模型用于判断图像中是否包括车辆的一对尾灯。
需要说明的是,本实施例对于第二神经网络模型的实现方式不做限定。
可选的,若采用第二神经网络模型判断车辆候选区域包括车辆的一对尾灯,判断车辆候选区域是否包括车辆的一对尾灯,还可以包括:
获取左尾灯区域和右尾灯区域。
在水平校正图像中获取第一待处理区域和第二待处理区域。第一待处理区域包括左尾灯区域,第二待处理区域包括右尾灯区域。
对左尾灯区域进行镜像翻转获得第一目标区域,根据第一目标区域在第二待处理区域中进行图像匹配,或者,对右尾灯区域进行镜像翻转获得第二目标区域,根据第二目标区域在第一待处理区域中进行图像匹配,获得匹配结果。
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
下面结合示例进行说明。
图5为本发明实施例二中尾灯区域匹配的原理示意图。如图5所示,第一待处理区域203为根据左尾灯区域(未示出)获得的。第二待处理区域202为根据右尾灯区域201获得的。右尾灯区域201进行镜像翻转,获得第二目标区域204。可以根据第二目标区域204,沿着水平方向,在第一待处理区域203中进行图像匹配。可选的,在一种实现方式中,可以计算第二目标区域204与左尾灯区域之间的距离。若该距离小于第一预设阈值,则确定图像匹配成功。车辆候选区域包括车辆的一对尾灯。可选的,在另一种实现方式中,根据第二目标区域204,沿着水平方向,在第一待处理区域203中确定最靠近第二目标区域204的匹配区域。如果匹配区域与第二目标区域204之间的距离小于第二预设阈值,则确定图像匹配成功。车辆候选区域包括车辆的一对尾灯。
其中,本实施例对于第一预设阈值和第二预设阈值的具体取值不做限定。
可见,当采用第二神经网络模型判断车辆候选区域包括车辆的一对尾灯,获得尾灯区域之后,通过确定尾灯区域是否匹配,进一步提升了判断车辆候 选区域是否包括车辆的一对尾灯的准确性。
可选的,若采用第二神经网络模型判断车辆候选区域包括车辆的一对尾灯,判断车辆候选区域是否包括车辆的一对尾灯,还可以包括:
获取任一个尾灯的尾灯区域。
对尾灯区域进行镜像翻转获得第三目标区域,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果。
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
该种实现方式与上面实现方式的区别在于,在尾灯区域翻转后,直接以翻转获得的区域为模板进行图像匹配。简化了计算复杂度,提升了计算效率。
可选的,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果,可以包括:
在水平校正图像中以第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与第三目标区域距离最近的匹配区域。
具体的,车辆上的尾灯是对称设置的,位于同一水平线上。由于水平校正图像已经进行了水平校正,因此,以第三目标区域为中心,沿水平方向向两端进行图像匹配,可以更快的找到与第三目标区域匹配且距离最近的匹配区域,提升了处理速度。
可选的,根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯,可以包括:
若匹配区域与尾灯区域之间的距离小于或者等于预设阈值,则判断车辆候选区域包括车辆的一对尾灯。
若匹配区域与尾灯区域之间的距离大于预设阈值,则判断车辆候选区域不包括车辆的一对尾灯。
具体的,匹配区域是通过图像匹配的方式确定的与尾灯区域对称的区域。匹配区域与尾灯区域之间的距离,与车辆上两个尾灯之间的距离应该近似相等。因此,通过匹配区域与尾灯区域之间的距离,可以判断车辆候选区域是否包括车辆的一对尾灯。
本实施例提供了一种车辆检测方法,通过对根据待处理图像中像素点的深度信息获得的车辆候选区域的距离值进行校验,可以进一步确定该距离值的准确性。从而,根据该距离值确定车辆候选区域对应的检测模型,进一步 提升了车辆检测的准确性。
图6为本发明实施例三提供的车辆检测方法的流程图。本实施例提供的车辆检测方法,执行主体可以为车辆检测设备,应用于对拍摄设备拍摄的图像进行车辆检测的场景。其中,拍摄设备设置在可以行使在道路上的装置,例如:车辆、车辆上的辅助驾驶设备、安装在车辆上的行车记录仪、智能电动车、滑板车、平衡车,等等。可选的,车辆检测设备可以设置在上述可以行使在道路上的装置。可选的,车辆检测设备可以包括所述拍摄设备。
如图6所示,本实施例提供的车辆检测方法,可以包括:
S601、获取待处理图像。
S602、获取待处理图像中的车辆候选区域。
S603若判断车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取车辆候选区域的距离值。
S604、根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。
本实施例提供的车辆检测方法,对于待处理图像中的车辆候选区域,如果车辆候选区域包括车辆的一对尾灯,说明车辆候选区域为车辆区域。通过车辆上两个尾灯之间的距离获得车辆候选区域的距离值。根据距离值可以确定匹配的检测模型,提升了检测模型的精确度。相比于采用单一模型检测车辆,本实施例提供的车辆检测方法,根据不同的距离采用不同的检测模型检测车辆,提升了车辆检测的准确性和可靠性,降低了误检测和漏检测概率。
需要说明的是,本实施例对于如何获取待处理图像中车辆候选区域的实现方式不做限定。例如,可以采用图像处理的方法,也可以采用深度学习、机器学习或者神经网络算法。
可选的,本实施例提供的车辆检测方法,还可以包括:
采用车辆候选区域对应的检测模型,确定车辆候选区域是否为车辆区域。
可选的,距离值为根据拍摄设备的焦距、预设的车辆宽度和两个尾灯的外边沿之间的距离确定的。
可选的,在S603,判断车辆候选区域包括车辆的一对尾灯之前,还包括:
对待处理图像进行水平校正,获得水平校正图像。
根据水平校正图像中与车辆候选区域对应的区域,判断车辆候选区域是 否包括车辆的一对尾灯。
可选的,根据水平校正图像中与车辆候选区域对应的区域,判断车辆候选区域是否包括车辆的一对尾灯,包括:
将水平校正图像中与车辆候选区域对应的区域输入神经网络模型,判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,判断车辆候选区域是否包括车辆的一对尾灯,还包括:
获取左尾灯区域和右尾灯区域。
在水平校正图像中获取第一待处理区域和第二待处理区域。第一待处理区域包括左尾灯区域,第二待处理区域包括右尾灯区域。
对左尾灯区域进行镜像翻转获得第一目标区域,根据第一目标区域在第二待处理区域中进行图像匹配,或者,对右尾灯区域进行镜像翻转获得第二目标区域,根据第二目标区域在第一待处理区域中进行图像匹配,获得匹配结果。
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,判断车辆候选区域是否包括车辆的一对尾灯,还包括:
获取任一个尾灯的尾灯区域。
对尾灯区域进行镜像翻转获得第三目标区域,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果。
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果,包括:
在水平校正图像中以第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与第三目标区域距离最近的匹配区域。
可选的,根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯,包括:
若匹配区域与尾灯区域之间的距离小于或者等于预设阈值,则判断车辆候选区域包括车辆的一对尾灯。
若匹配区域与尾灯区域之间的距离大于预设阈值,则判断车辆候选区域 不包括车辆的一对尾灯。
可选的,S604中,根据车辆候选区域的距离值确定车辆候选区域对应的检测模型,包括:
根据多个预设距离值范围与多个预设检测模型之间的对应关系,将车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为车辆候选区域对应的检测模型。
可选的,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
需要说明的是,对于本实施例中技术方案的详细描述,可以参见图1~图5所示实施例中的相关描述。其中,本实施例中的“车辆候选区域的距离值”与图4~图5所示实施例二中的“车辆候选区域的校验距离值”相似,本实施例中的“神经网络模型”与图4~图5所示实施例二中的“第二车辆候选区域的校验距离值”相似。技术原理和技术效果相似,此处不再赘述。
本发明实施例一提供一种车辆检测设备,可以参见图7。图7为本发明实施例提供的车辆检测设备的结构示意图。本实施例提供的车辆检测设备,用于执行图1~图5所示实施例提供的车辆检测方法。如图7所示,本实施例提供的车辆检测设备,可以包括:存储器12、处理器11和拍摄设备13;
拍摄设备13,用于获取待处理图像;
存储器12,用于存储程序代码;
处理器11,调用程序代码,当程序代码被执行时,用于执行以下操作:
获取待处理图像中每个像素点的深度信息;
根据待处理图像和深度信息,获取待处理图像中车辆候选区域的距离值;
根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。
可选的,处理器11具体用于:
将待处理图像输入第一神经网络模型,获取待处理图像中的道路区域;
根据深度信息对待处理图像中的像素点进行聚类分析,确定待处理图像中与道路区域邻接的车辆候选区域,并获取车辆候选区域的距离值。
可选的,与道路区域邻接的车辆候选区域,包括:与道路区域中像素点之间的最小距离小于或者等于预设距离的车辆候选区域。
可选的,处理器11具体用于:
采用K均值算法进行聚类分析。
可选的,车辆候选区域的距离值为车辆候选区域的簇中心点的深度值。
可选的,处理器11具体用于:
根据多个预设距离值范围与多个预设检测模型之间的对应关系,将车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为车辆候选区域对应的检测模型。
可选的,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
可选的,处理器11还用于:
对车辆候选区域的距离值进行校验;
若校验通过,则执行根据车辆候选区域的距离值确定车辆候选区域对应的检测模型的步骤。
可选的,处理器11具体用于:
判断车辆候选区域是否包括车辆的一对尾灯;
若车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取车辆候选区域的校验距离值;
判断车辆候选区域的距离值与校验距离值之间的差值是否在预设差值范围内。
可选的,校验距离值为根据拍摄设备的焦距、预设的车辆宽度和两个尾灯的外边沿之间的距离确定的。
可选的,处理器11具体用于:
对待处理图像进行水平校正,获得水平校正图像;
根据水平校正图像中与车辆候选区域对应的区域,判断车辆候选区域是否包括车辆的一对尾灯。
可选的,处理器11具体用于:
将水平校正图像中与车辆候选区域对应的区域输入第二神经网络模型,判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,处理器11还用于:
获取左尾灯区域和右尾灯区域;
在水平校正图像中获取第一待处理区域和第二待处理区域;第一待处理 区域包括左尾灯区域,第二待处理区域包括右尾灯区域;
对左尾灯区域进行镜像翻转获得第一目标区域,根据第一目标区域在第二待处理区域中进行图像匹配,或者,对右尾灯区域进行镜像翻转获得第二目标区域,根据第二目标区域在第一待处理区域中进行图像匹配,获得匹配结果;
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,处理器11还用于:
获取任一个尾灯的尾灯区域;
对尾灯区域进行镜像翻转获得第三目标区域,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果;
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,处理器11具体用于:
在水平校正图像中以第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与第三目标区域距离最近的匹配区域。
可选的,处理器11具体用于:
若匹配区域与尾灯区域之间的距离小于或者等于预设阈值,则判断车辆候选区域包括车辆的一对尾灯。
若匹配区域与尾灯区域之间的距离大于预设阈值,则判断车辆候选区域不包括车辆的一对尾灯。
可选的,处理器11具体用于:
获取待处理图像对应的雷达图或者深度图;
将雷达图或者深度图与待处理图像匹配,获取待处理图像中每个像素点的深度信息。
本实施例提供的车辆检测设备,用于执行图1~图5所示实施例提供的车辆检测方法。技术原理和技术效果相似,此处不再赘述。
本发明实施例二提供一种车辆检测设备,可以参见图7。图7为本发明实施例提供的车辆检测设备的结构示意图。本实施例提供的车辆检测设备,用于执行图6所示实施例提供的车辆检测方法。如图7所示,本实施例提供 的车辆检测设备,可以包括:存储器12、处理器11和拍摄设备13;
拍摄设备13,用于获取待处理图像;
存储器12,用于存储程序代码;
处理器11,调用程序代码,当程序代码被执行时,用于执行以下操作:
获取待处理图像中的车辆候选区域;
若判断车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取车辆候选区域的距离值;
根据车辆候选区域的距离值确定车辆候选区域对应的检测模型。
可选的,距离值为根据拍摄设备的焦距、预设的车辆宽度和两个尾灯的外边沿之间的距离确定的。
可选的,处理器11具体用于:
对待处理图像进行水平校正,获得水平校正图像;
根据水平校正图像中与车辆候选区域对应的区域,判断车辆候选区域是否包括车辆的一对尾灯。
可选的,处理器11具体用于:
将水平校正图像中与车辆候选区域对应的区域输入神经网络模型,判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,处理器11还用于:
获取左尾灯区域和右尾灯区域;
在水平校正图像中获取第一待处理区域和第二待处理区域;第一待处理区域包括左尾灯区域,第二待处理区域包括右尾灯区域;
对左尾灯区域进行镜像翻转获得第一目标区域,根据第一目标区域在第二待处理区域中进行图像匹配,或者,对右尾灯区域进行镜像翻转获得第二目标区域,根据第二目标区域在第一待处理区域中进行图像匹配,获得匹配结果;
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,若采用神经网络模型判断车辆候选区域包括车辆的一对尾灯,处理器11具体用于:
获取任一个尾灯的尾灯区域;
对尾灯区域进行镜像翻转获得第三目标区域,根据第三目标区域在水平校正图像中进行图像匹配,获得匹配结果;
根据匹配结果判断车辆候选区域是否包括车辆的一对尾灯。
可选的,处理器11具体用于:
在水平校正图像中以第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与第三目标区域距离最近的匹配区域。
可选的,处理器11具体用于:
若匹配区域与尾灯区域之间的距离小于或者等于预设阈值,则判断车辆候选区域包括车辆的一对尾灯。
若匹配区域与尾灯区域之间的距离大于预设阈值,则判断车辆候选区域不包括车辆的一对尾灯。
可选的,处理器11具体用于:
根据多个预设距离值范围与多个预设检测模型之间的对应关系,将车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为车辆候选区域对应的检测模型。
可选的,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
本实施例提供的车辆检测设备,用于执行图6所示实施例提供的车辆检测方法。技术原理和技术效果相似,此处不再赘述。
本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上各实施例仅用以说明本发明实施例的技术方案,而非对其限制;尽管参照前述各实施例对本发明实施例进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明实施例技术方案的范围。
Claims (55)
- 一种车辆检测方法,其特征在于,包括:获取待处理图像和所述待处理图像中每个像素点的深度信息;根据所述待处理图像和所述深度信息,获取所述待处理图像中车辆候选区域的距离值;根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
- 根据权利要求1所述的方法,其特征在于,所述根据所述待处理图像和所述深度信息,获取所述待处理图像中车辆候选区域的距离值,包括:将所述待处理图像输入第一神经网络模型,获取所述待处理图像中的道路区域;根据所述深度信息对所述待处理图像中的像素点进行聚类分析,确定所述待处理图像中与所述道路区域邻接的车辆候选区域,并获取所述车辆候选区域的距离值。
- 根据权利要求2所述的方法,其特征在于,所述与所述道路区域邻接的车辆候选区域,包括:与所述道路区域中像素点之间的最小距离小于或者等于预设距离的车辆候选区域。
- 根据权利要求2所述的方法,其特征在于,所述进行聚类分析,包括:采用K均值算法进行聚类分析。
- 根据权利要求2所述的方法,其特征在于,所述车辆候选区域的距离值为所述车辆候选区域的簇中心点的深度值。
- 根据权利要求1所述的方法,其特征在于,所述根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型,包括:根据多个预设距离值范围与多个预设检测模型之间的对应关系,将所述车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为所述车辆候选区域对应的检测模型。
- 根据权利要求6所述的方法,其特征在于,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
- 根据权利要求1-7任一项所述的方法,其特征在于,所述根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型之前,还包括:对所述车辆候选区域的距离值进行校验;若校验通过,则执行根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型的步骤。
- 根据权利要求8所述的方法,其特征在于,所述对所述车辆候选区域的距离值进行校验,包括:判断所述车辆候选区域是否包括车辆的一对尾灯;若所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取所述车辆候选区域的校验距离值;判断所述车辆候选区域的距离值与所述校验距离值之间的差值是否在预设差值范围内。
- 根据权利要求9所述的方法,其特征在于,所述校验距离值为根据所述拍摄设备的焦距、预设的车辆宽度和所述两个尾灯的外边沿之间的距离确定的。
- 根据权利要求9所述的方法,其特征在于,所述判断所述车辆候选区域是否包括车辆的一对尾灯,包括:对所述待处理图像进行水平校正,获得水平校正图像;根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求11所述的方法,其特征在于,所述根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯,包括:将所述水平校正图像中与所述车辆候选区域对应的区域输入第二神经网络模型,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求12所述的方法,其特征在于,若采用所述第二神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述判断所述车辆候选区域是否包括车辆的一对尾灯,还包括:获取左尾灯区域和右尾灯区域;在所述水平校正图像中获取第一待处理区域和第二待处理区域;所述第一待处理区域包括所述左尾灯区域,所述第二待处理区域包括所述右尾灯区域;对所述左尾灯区域进行镜像翻转获得第一目标区域,根据所述第一目标 区域在所述第二待处理区域中进行图像匹配,或者,对所述右尾灯区域进行镜像翻转获得第二目标区域,根据所述第二目标区域在所述第一待处理区域中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求12所述的方法,其特征在于,若采用所述第二神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述判断所述车辆候选区域是否包括车辆的一对尾灯,还包括:获取任一个尾灯的尾灯区域;对所述尾灯区域进行镜像翻转获得第三目标区域,根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求14所述的方法,其特征在于,所述根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果,包括:在所述水平校正图像中以所述第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与所述第三目标区域距离最近的匹配区域。
- 根据权利要求15所述的方法,其特征在于,所述根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯,包括:若所述匹配区域与所述尾灯区域之间的距离小于或者等于预设阈值,则判断所述车辆候选区域包括车辆的一对尾灯;若所述匹配区域与所述尾灯区域之间的距离大于所述预设阈值,则判断所述车辆候选区域不包括车辆的一对尾灯。
- 根据权利要求1-16任一项所述的方法,其特征在于,获取所述待处理图像中每个像素点的深度信息,包括:获取所述待处理图像对应的雷达图或者深度图;将所述雷达图或者所述深度图与所述待处理图像匹配,获取所述待处理图像中每个像素点的深度信息。
- 一种车辆检测方法,其特征在于,包括:获取待处理图像;获取所述待处理图像中的车辆候选区域;若判断所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的 距离和拍摄设备的焦距,获取所述车辆候选区域的距离值;根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
- 根据权利要求18所述的方法,其特征在于,所述距离值为根据所述拍摄设备的焦距、预设的车辆宽度和所述两个尾灯的外边沿之间的距离确定的。
- 根据权利要求18所述的方法,其特征在于,所述判断所述车辆候选区域包括车辆的一对尾灯之前,还包括:对所述待处理图像进行水平校正,获得水平校正图像;根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求20所述的方法,其特征在于,所述根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯,包括:将所述水平校正图像中与所述车辆候选区域对应的区域输入神经网络模型,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求21所述的方法,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述判断所述车辆候选区域是否包括车辆的一对尾灯,还包括:获取左尾灯区域和右尾灯区域;在所述水平校正图像中获取第一待处理区域和第二待处理区域;所述第一待处理区域包括所述左尾灯区域,所述第二待处理区域包括所述右尾灯区域;对所述左尾灯区域进行镜像翻转获得第一目标区域,根据所述第一目标区域在所述第二待处理区域中进行图像匹配,或者,对所述右尾灯区域进行镜像翻转获得第二目标区域,根据所述第二目标区域在所述第一待处理区域中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求21所述的方法,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述判断所述车辆候选区域是否包括车辆的一对尾灯,还包括:获取任一个尾灯的尾灯区域;对所述尾灯区域进行镜像翻转获得第三目标区域,根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求23所述的方法,其特征在于,所述根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果,包括:在所述水平校正图像中以所述第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与所述第三目标区域距离最近的匹配区域。
- 根据权利要求24所述的方法,其特征在于,所述根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯,包括:若所述匹配区域与所述尾灯区域之间的距离小于或者等于预设阈值,则判断所述车辆候选区域包括车辆的一对尾灯;若所述匹配区域与所述尾灯区域之间的距离大于所述预设阈值,则判断所述车辆候选区域不包括车辆的一对尾灯。
- 根据权利要求18-25任一项所述的方法,其特征在于,所述根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型,包括:根据多个预设距离值范围与多个预设检测模型之间的对应关系,将所述车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为所述车辆候选区域对应的检测模型。
- 根据权利要求26所述的方法,其特征在于,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
- 一种车辆检测设备,其特征在于,包括:存储器、处理器和拍摄设备;所述拍摄设备,用于获取待处理图像;所述存储器,用于存储程序代码;所述处理器,调用所述程序代码,当所述程序代码被执行时,用于执行以下操作:获取所述待处理图像中每个像素点的深度信息;根据所述待处理图像和所述深度信息,获取所述待处理图像中车辆候选区域的距离值;根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
- 根据权利要求28所述的设备,其特征在于,所述处理器具体用于:将所述待处理图像输入第一神经网络模型,获取所述待处理图像中的道路区域;根据所述深度信息对所述待处理图像中的像素点进行聚类分析,确定所述待处理图像中与所述道路区域邻接的车辆候选区域,并获取所述车辆候选区域的距离值。
- 根据权利要求29所述的设备,其特征在于,所述与所述道路区域邻接的车辆候选区域,包括:与所述道路区域中像素点之间的最小距离小于或者等于预设距离的车辆候选区域。
- 根据权利要求29所述的设备,其特征在于,所述处理器具体用于:采用K均值算法进行聚类分析。
- 根据权利要求29所述的设备,其特征在于,所述车辆候选区域的距离值为所述车辆候选区域的簇中心点的深度值。
- 根据权利要求28所述的设备,其特征在于,所述处理器具体用于:根据多个预设距离值范围与多个预设检测模型之间的对应关系,将所述车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为所述车辆候选区域对应的检测模型。
- 根据权利要求33所述的设备,其特征在于,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
- 根据权利要求28-34任一项所述的设备,其特征在于,所述处理器还用于:对所述车辆候选区域的距离值进行校验;若校验通过,则执行根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型的步骤。
- 根据权利要求35所述的设备,其特征在于,所述处理器具体用于:判断所述车辆候选区域是否包括车辆的一对尾灯;若所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取所述车辆候选区域的校验距离值;判断所述车辆候选区域的距离值与所述校验距离值之间的差值是否在预 设差值范围内。
- 根据权利要求36所述的设备,其特征在于,所述校验距离值为根据所述拍摄设备的焦距、预设的车辆宽度和所述两个尾灯的外边沿之间的距离确定的。
- 根据权利要求36所述的设备,其特征在于,所述处理器具体用于:对所述待处理图像进行水平校正,获得水平校正图像;根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求38所述的设备,其特征在于,所述处理器具体用于:将所述水平校正图像中与所述车辆候选区域对应的区域输入第二神经网络模型,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求39所述的设备,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述处理器还用于:获取左尾灯区域和右尾灯区域;在所述水平校正图像中获取第一待处理区域和第二待处理区域;所述第一待处理区域包括所述左尾灯区域,所述第二待处理区域包括所述右尾灯区域;对所述左尾灯区域进行镜像翻转获得第一目标区域,根据所述第一目标区域在所述第二待处理区域中进行图像匹配,或者,对所述右尾灯区域进行镜像翻转获得第二目标区域,根据所述第二目标区域在所述第一待处理区域中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求39所述的设备,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述处理器还用于:获取任一个尾灯的尾灯区域;对所述尾灯区域进行镜像翻转获得第三目标区域,根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求41所述的设备,其特征在于,所述处理器具体用于:在所述水平校正图像中以所述第三目标区域为中心向水平方向的两侧分 别进行图像匹配,获得与所述第三目标区域距离最近的匹配区域。
- 根据权利要求42所述的设备,其特征在于,所述处理器具体用于:若所述匹配区域与所述尾灯区域之间的距离小于或者等于预设阈值,则判断所述车辆候选区域包括车辆的一对尾灯;若所述匹配区域与所述尾灯区域之间的距离大于所述预设阈值,则判断所述车辆候选区域不包括车辆的一对尾灯。
- 根据权利要求28-43任一项所述的设备,其特征在于,所述处理器具体用于:获取所述待处理图像对应的雷达图或者深度图;将所述雷达图或者所述深度图与所述待处理图像匹配,获取所述待处理图像中每个像素点的深度信息。
- 一种车辆检测设备,其特征在于,包括:存储器、处理器和拍摄设备;所述拍摄设备,用于获取待处理图像;所述存储器,用于存储程序代码;所述处理器,调用所述程序代码,当所述程序代码被执行时,用于执行以下操作:获取所述待处理图像中的车辆候选区域;若判断所述车辆候选区域包括车辆的一对尾灯,则根据两个尾灯之间的距离和拍摄设备的焦距,获取所述车辆候选区域的距离值;根据所述车辆候选区域的距离值确定所述车辆候选区域对应的检测模型。
- 根据权利要求45所述的设备,其特征在于,所述距离值为根据所述拍摄设备的焦距、预设的车辆宽度和所述两个尾灯的外边沿之间的距离确定的。
- 根据权利要求45所述的设备,其特征在于,所述处理器还用于:对所述待处理图像进行水平校正,获得水平校正图像;根据所述水平校正图像中与所述车辆候选区域对应的区域,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求47所述的设备,其特征在于,所述处理器具体用于:将所述水平校正图像中与所述车辆候选区域对应的区域输入神经网络模 型,判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求48所述的设备,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述处理器还用于:获取左尾灯区域和右尾灯区域;在所述水平校正图像中获取第一待处理区域和第二待处理区域;所述第一待处理区域包括所述左尾灯区域,所述第二待处理区域包括所述右尾灯区域;对所述左尾灯区域进行镜像翻转获得第一目标区域,根据所述第一目标区域在所述第二待处理区域中进行图像匹配,或者,对所述右尾灯区域进行镜像翻转获得第二目标区域,根据所述第二目标区域在所述第一待处理区域中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求48所述的设备,其特征在于,若采用所述神经网络模型判断所述车辆候选区域包括车辆的一对尾灯,所述处理器还用于:获取任一个尾灯的尾灯区域;对所述尾灯区域进行镜像翻转获得第三目标区域,根据所述第三目标区域在所述水平校正图像中进行图像匹配,获得匹配结果;根据所述匹配结果判断所述车辆候选区域是否包括车辆的一对尾灯。
- 根据权利要求50所述的设备,其特征在于,所述处理器具体用于:在所述水平校正图像中以所述第三目标区域为中心向水平方向的两侧分别进行图像匹配,获得与所述第三目标区域距离最近的匹配区域。
- 根据权利要求51所述的设备,其特征在于,所述处理器具体用于:若所述匹配区域与所述尾灯区域之间的距离小于或者等于预设阈值,则判断所述车辆候选区域包括车辆的一对尾灯;若所述匹配区域与所述尾灯区域之间的距离大于所述预设阈值,则判断所述车辆候选区域不包括车辆的一对尾灯。
- 根据权利要求45-52任一项所述的设备,其特征在于,所述处理器具体用于:根据多个预设距离值范围与多个预设检测模型之间的对应关系,将所述车辆候选区域的距离值所在的预设距离值范围对应的预设检测模型,确定为 所述车辆候选区域对应的检测模型。
- 根据权利要求53所述的设备,其特征在于,相邻的两个预设检测模型对应的预设距离值范围存在重叠区域。
- 一种存储介质,其特征在于,包括:可读存储介质和计算机程序,所述计算机程序用于实现如权利要求1-27中任一项所述的车辆检测方法。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201880069541.6A CN111386530B (zh) | 2018-12-29 | 2018-12-29 | 车辆检测方法和设备 |
| PCT/CN2018/125800 WO2020133488A1 (zh) | 2018-12-29 | 2018-12-29 | 车辆检测方法和设备 |
| US17/358,999 US20210326612A1 (en) | 2018-12-29 | 2021-06-25 | Vehicle detection method and device |
| US17/360,985 US20210326613A1 (en) | 2018-12-29 | 2021-06-28 | Vehicle detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/125800 WO2020133488A1 (zh) | 2018-12-29 | 2018-12-29 | 车辆检测方法和设备 |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US17/358,999 Continuation US20210326612A1 (en) | 2018-12-29 | 2021-06-25 | Vehicle detection method and device |
| US17/360,985 Continuation US20210326613A1 (en) | 2018-12-29 | 2021-06-28 | Vehicle detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020133488A1 true WO2020133488A1 (zh) | 2020-07-02 |
Family
ID=71127452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/125800 Ceased WO2020133488A1 (zh) | 2018-12-29 | 2018-12-29 | 车辆检测方法和设备 |
Country Status (3)
| Country | Link |
|---|---|
| US (2) | US20210326612A1 (zh) |
| CN (1) | CN111386530B (zh) |
| WO (1) | WO2020133488A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3937066A1 (en) * | 2020-07-07 | 2022-01-12 | KNORR-BREMSE Systeme für Nutzfahrzeuge GmbH | Peer vehicle center line determination system and method |
| CN114056428A (zh) * | 2021-10-13 | 2022-02-18 | 中科云谷科技有限公司 | 用于工程车辆的倒车引导方法、装置、处理器及系统 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11620522B2 (en) * | 2019-12-31 | 2023-04-04 | Magna Electronics Inc. | Vehicular system for testing performance of headlamp detection systems |
| CN114386721B (zh) * | 2022-03-23 | 2023-06-20 | 蔚来汽车科技(安徽)有限公司 | 用于换电站的路径规划方法、系统、介质和换电站 |
| JP7607610B2 (ja) | 2022-03-31 | 2024-12-27 | 三菱重工業株式会社 | 対象物検知装置、対象物検知方法及び対象物検知プログラム |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470806A (zh) * | 2007-12-27 | 2009-07-01 | 东软集团股份有限公司 | 车灯检测方法和装置、感兴趣区域分割方法和装置 |
| EP2192564A1 (en) * | 2008-11-28 | 2010-06-02 | Isbak Istanbul Ulasim Haberlesme ve Guvenlik Teknolojileri San . ve TIC . A . S . | Mobile electronic control system |
| CN102509098A (zh) * | 2011-10-08 | 2012-06-20 | 天津大学 | 一种鱼眼图像车辆识别方法 |
| CN106710240A (zh) * | 2017-03-02 | 2017-05-24 | 公安部交通管理科学研究所 | 融合多目标雷达与视频信息的通行车辆跟踪测速方法 |
| CN108759667A (zh) * | 2018-05-29 | 2018-11-06 | 福州大学 | 车载摄像头下基于单目视觉与图像分割的前车测距方法 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3115933B1 (en) * | 2015-07-07 | 2021-03-17 | Ricoh Company, Ltd. | Image processing device, image capturing device, mobile body control system, image processing method, and computer-readable recording medium |
| CN107609483B (zh) * | 2017-08-15 | 2020-06-16 | 中国科学院自动化研究所 | 面向驾驶辅助系统的危险目标检测方法、装置 |
| CN108875519B (zh) * | 2017-12-19 | 2023-05-26 | 北京旷视科技有限公司 | 对象检测方法、装置和系统及存储介质 |
-
2018
- 2018-12-29 WO PCT/CN2018/125800 patent/WO2020133488A1/zh not_active Ceased
- 2018-12-29 CN CN201880069541.6A patent/CN111386530B/zh active Active
-
2021
- 2021-06-25 US US17/358,999 patent/US20210326612A1/en not_active Abandoned
- 2021-06-28 US US17/360,985 patent/US20210326613A1/en not_active Abandoned
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470806A (zh) * | 2007-12-27 | 2009-07-01 | 东软集团股份有限公司 | 车灯检测方法和装置、感兴趣区域分割方法和装置 |
| EP2192564A1 (en) * | 2008-11-28 | 2010-06-02 | Isbak Istanbul Ulasim Haberlesme ve Guvenlik Teknolojileri San . ve TIC . A . S . | Mobile electronic control system |
| CN102509098A (zh) * | 2011-10-08 | 2012-06-20 | 天津大学 | 一种鱼眼图像车辆识别方法 |
| CN106710240A (zh) * | 2017-03-02 | 2017-05-24 | 公安部交通管理科学研究所 | 融合多目标雷达与视频信息的通行车辆跟踪测速方法 |
| CN108759667A (zh) * | 2018-05-29 | 2018-11-06 | 福州大学 | 车载摄像头下基于单目视觉与图像分割的前车测距方法 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3937066A1 (en) * | 2020-07-07 | 2022-01-12 | KNORR-BREMSE Systeme für Nutzfahrzeuge GmbH | Peer vehicle center line determination system and method |
| WO2022008267A1 (en) * | 2020-07-07 | 2022-01-13 | Knorr-Bremse Systeme für Nutzfahrzeuge GmbH | Peer vehicle center line determination system and method |
| CN114056428A (zh) * | 2021-10-13 | 2022-02-18 | 中科云谷科技有限公司 | 用于工程车辆的倒车引导方法、装置、处理器及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20210326612A1 (en) | 2021-10-21 |
| US20210326613A1 (en) | 2021-10-21 |
| CN111386530A (zh) | 2020-07-07 |
| CN111386530B (zh) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210326612A1 (en) | Vehicle detection method and device | |
| WO2021004312A1 (zh) | 一种基于双目立体视觉系统的车辆智能测轨迹方法 | |
| CN104700414A (zh) | 一种基于车载双目相机的前方道路行人快速测距方法 | |
| JP2020035447A (ja) | 物体識別方法、装置、機器、車両及び媒体 | |
| CN110334678A (zh) | 一种基于视觉融合的行人检测方法 | |
| US11126875B2 (en) | Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium | |
| CN105608417A (zh) | 交通信号灯检测方法及装置 | |
| KR102565603B1 (ko) | 긴급 제동 시스템의 성능평가 장치 및 방법 | |
| CN108573215B (zh) | 道路反光区域检测方法、装置和终端 | |
| CN111160233A (zh) | 基于三维成像辅助的人脸活体检测方法、介质及系统 | |
| CN113092079A (zh) | 清晰度检测标板和方法及其系统、电子设备以及检测平台 | |
| WO2020087322A1 (zh) | 车道线识别方法和装置、车辆 | |
| CN111192329A (zh) | 传感器标定结果的验证方法、装置及存储介质 | |
| CN114898321A (zh) | 道路可行驶区域检测方法、装置、设备、介质及系统 | |
| CN106650732B (zh) | 一种车牌识别方法及装置 | |
| WO2020187311A1 (zh) | 一种图像识别方法及装置 | |
| CN111376904A (zh) | 一种自动跟车方法及装置 | |
| CN109829401A (zh) | 基于双拍摄设备的交通标志识别方法及装置 | |
| WO2014054124A1 (ja) | 路面標示検出装置及び路面標示検出方法 | |
| CN108399357A (zh) | 一种人脸定位方法及装置 | |
| CN115082894B (zh) | 距离检测方法、车辆远光灯控制方法、设备、介质及车辆 | |
| CN111462244A (zh) | 车载环视系统在线标定方法、系统及装置 | |
| CN116485842A (zh) | 自动目标识别的方法、装置及存储介质 | |
| US11010625B2 (en) | Vehicle exterior environment recognition apparatus and method of recognizing exterior environment outside vehicle | |
| CN115018991B (zh) | 一种基于三维成像的自动报靶方法及系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18944257 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18944257 Country of ref document: EP Kind code of ref document: A1 |