Shared vehicle parking camera anomaly detection method, device, equipment and medium

Abstract

The present invention relates to the field of vehicle-mounted camera technology, and provides a method, device, equipment and medium for detecting abnormalities in parking cameras of shared vehicles, the method comprising: obtaining multiple groups of images to be detected collected by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition; identifying inherent features in the images to be detected; the inherent features are used to characterize the target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle; and detecting whether the camera has abnormalities according to the inherent features. By using the inherent features as a criterion for determining whether the camera has abnormalities, abnormality detection of the camera is achieved, and abnormalities in the camera can be discovered in time, reducing the impact on the user's return of the vehicle, and avoiding the impact of the camera abnormality on the user's normal return of the vehicle.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-mounted camera technology, and in particular to a method, device, equipment and medium for detecting anomalies of a parking camera of a shared vehicle. Background Art

[0002] With the development and popularization of shared vehicles, more and more shared vehicles need to be managed in a standardized manner, and the parking of shared vehicles is a key link in standardized management. Most of the existing standardized management methods for shared vehicles use various methods to regulate users' vehicle returns, such as the common electronic fence method. However, due to the limited positioning accuracy of shared vehicles, the electronic fence method can usually only restrict users to park their vehicles in designated areas, and cannot require users to park in a specific manner. Therefore, it is usually necessary to combine the electronic fence with the road stud parking or image recognition method to regulate users' parking of shared vehicles.

[0003] The image recognition of shared vehicles is realized through the on-board camera. Its principle is to identify the ground parking signs in the parking area, and judge the relative position relationship between the parking signs and the shared vehicles according to the posture of the parking signs, so as to determine whether the user has parked in accordance with the requirements. Since shared vehicles are in public areas, the on-board cameras are prone to stains and looseness, and since the cameras are generally set in hidden locations such as under the basket that are difficult for users to observe, users usually cannot detect abnormalities in the cameras in time, which can easily affect the normal return of the users. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for detecting anomalies of parking cameras of shared vehicles, so as to solve the defect in the prior art that users cannot timely discover anomalies of cameras, which easily affects the normal return of users.

[0005] The present invention provides a method for detecting anomalies of a parking camera of a shared vehicle, comprising:

[0006] Acquire multiple groups of images to be detected captured by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0007] Identifying inherent features in the image to be detected; the inherent features are used to characterize a target portion of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0008] Whether the camera is abnormal is detected according to the inherent characteristics.

[0009] According to the shared vehicle parking camera abnormality detection method provided by the present invention, the fault type when the camera is abnormal includes position offset; the detecting whether the camera is abnormal according to the inherent characteristics includes:

[0010] Acquire a first position of the inherent feature in the image to be detected, and acquire a second position of the inherent feature in a reference image; the reference image is acquired by the camera when there is no abnormality;

[0011] Comparing the first position with the second position to determine the displacement of the inherent feature in the image to be detected;

[0012] Determine whether the camera has a positional deviation abnormality according to the displacement.

[0013] According to the shared vehicle parking camera abnormality detection method provided by the present invention, the fault type when the camera is abnormal includes equipment contamination; the detecting whether the camera is abnormal according to the inherent characteristics includes:

[0014] Based on any group of the images to be detected, calculating the difference between any two adjacent frames of images to obtain a plurality of difference images;

[0015] Performing binarization processing on each of the difference images to obtain a binarized image corresponding to each of the difference images;

[0016] According to the position of the inherent feature in the binary image, it is detected whether the camera has an abnormality of device contamination.

[0017] According to the shared vehicle parking camera anomaly detection method provided by the present invention, detecting whether the camera has an abnormality of device contamination according to the position of the inherent feature in the binary image includes:

[0018] Performing bitwise OR operation on each of the binary images pixel by pixel to obtain connected areas in the binary images;

[0019] Obtaining a third position of the connected region in the binary image, and obtaining a fourth position of the inherent feature in the binary image;

[0020] Comparing the fourth position with the third position to determine the relative position relationship between the connected region and the inherent feature in the binary image;

[0021] Determine whether the camera has an abnormality of equipment contamination based on the relative position relationship.

[0022] According to the shared vehicle parking camera anomaly detection method provided by the present invention, the binarization processing is performed on each of the difference images to obtain a binarized image corresponding to each of the difference images, including:

[0023] Obtaining an initial pixel value of each pixel point in a target difference image; the target difference image is any one of the difference images;

[0024] Setting the pixel value of the first pixel point as the first eigenvalue and the pixel value of the second pixel point as the second eigenvalue to perform binarization processing on the target difference image to obtain a binarized image of the target difference image;

[0025] The first pixel point is a pixel point in the target difference image whose initial pixel value is greater than a preset threshold, and the second pixel point is a pixel point in the target difference image whose initial pixel value is less than or equal to the preset threshold.

[0026] According to the shared vehicle parking camera anomaly detection method provided by the present invention, after detecting whether the camera has an abnormality according to the inherent characteristics, the method further includes:

[0027] If the camera is abnormal, generate fault information of the camera; the fault information includes fault type and fault level;

[0028] Report the fault information to the server; the server generates an operation and maintenance work order according to the fault information, and configures the return strategy of the shared vehicle to the backup return strategy corresponding to the fault information; wherein the operation and maintenance urgency of the operation and maintenance work order is determined according to the fault information.

[0029] According to the shared vehicle parking camera anomaly detection method provided by the present invention, after reporting the fault information to the server, the method further includes:

[0030] receiving a vehicle locking instruction from the server; the vehicle locking instruction is generated by the server according to a received vehicle return request of the shared vehicle when it is determined that the shared vehicle satisfies the backup vehicle return strategy;

[0031] When the server detects that the shared vehicle has been returned, if it is determined according to the fault information that the shared vehicle needs to be deactivated, the server sets the vehicle state of the shared vehicle to a disabled state.

[0032] The present invention also provides a shared vehicle parking camera abnormality detection device, comprising the following modules:

[0033] An image acquisition module, used to obtain a plurality of groups of images to be detected acquired by the camera to be detected; the images to be detected are acquired by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0034] A feature recognition module, used for recognizing inherent features in the image to be detected; the inherent features are used for characterizing a target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0035] An abnormality detection module is used to detect whether there is an abnormality in the camera according to the inherent characteristics.

[0036] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the shared vehicle parking camera anomaly detection method as described in any one of the above are implemented.

[0037] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described methods for detecting anomalies in a shared vehicle parking camera.

[0038] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for detecting anomalies in a shared vehicle parking camera.

[0039] The shared vehicle parking camera abnormality detection method, device, equipment and medium provided by the present invention obtain multiple groups of images to be detected collected by the camera to be detected when the vehicle state of the shared vehicle meets the preset self-test conditions, and identify the inherent features in the images to be detected, and detect whether the camera is abnormal according to the identified inherent features. By using the inherent features as a criterion for determining whether the camera is abnormal, the abnormality detection of the camera is realized, and the abnormality of the camera can be discovered in time, reducing the impact on the user's return of the vehicle, and avoiding the impact of the camera abnormality on the user's normal return of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of a shared vehicle parking camera anomaly detection method provided by an embodiment of the present invention.

[0042] Figure 2 It is a schematic diagram of a difference image provided by an embodiment of the present invention.

[0043] Figure 3 It is a schematic diagram of the calculation process of the contaminated area provided by an embodiment of the present invention.

[0044] Figure 4 It is a structural schematic diagram of a shared vehicle parking camera anomaly detection device provided in an embodiment of the present invention.

[0045] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In order to solve the problem that it is difficult for users to detect camera abnormalities in time, which affects the normal return of the vehicle, an embodiment of the present invention provides a shared vehicle parking camera abnormality detection method, which can realize fault detection of the shared vehicle's on-board camera, and promptly detect abnormalities in the camera, so as to avoid affecting the normal return of the user due to camera abnormalities.

[0048] Specifically, the shared vehicle parking camera anomaly detection method provided by the embodiment of the present invention is applied to a shared vehicle, which can be a shared bicycle or a shared electric vehicle, which is not specifically limited here. In this solution, the parking camera is installed at the bottom of the basket, and the shooting angle is toward the ground. Since the basket is fixedly installed on the steering mechanism of the shared vehicle, the parking camera and the wheels of the shared vehicle have a fixed relative position relationship. Figure 1 is a flow chart of the abnormality detection method for a parking camera of a shared vehicle provided by the present invention, such as Figure 1 As shown, the method includes:

[0049] Step 100, obtaining a plurality of groups of images to be detected collected by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0050] Step 200, identifying inherent features in the image to be detected; the inherent features are used to characterize the target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0051] Step 300: Detect whether there is any abnormality in the camera according to the inherent characteristics.

[0052] First, multiple groups of images to be detected are acquired by the camera to be detected, where the images to be detected are acquired by the camera when the vehicle state of the shared vehicle meets the preset self-test condition. Optionally, after the shared vehicle enters the order state, the vehicle state is matched with the preset self-test condition, and when the vehicle state meets the preset self-test condition, the self-test process of the camera is started.

[0053] Optionally, the preset self-test conditions include that the shared vehicle is in operation and the driving speed is lower than a preset speed threshold. Optionally, when the shared vehicle is driving at a low speed, the camera collects images at a preset time interval to obtain multiple sets of images to be detected. Optionally, any set of images to be detected is a plurality of images collected within the same image acquisition cycle. Image acquisition when the vehicle is driving at a low speed can avoid excessive camera shaking and ensure that clear images can be captured even when the vehicle is moving. Using multiple sets of images can avoid misjudgment due to similar ground surfaces.

[0054] Furthermore, the inherent features in the image to be detected are identified, and the inherent features are used to characterize the target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle. The inherent features are also the feature information corresponding to the target part of the shared vehicle in the image to be detected. The inherent features specifically mean that the camera has a fixed relative position relationship with the target part of the shared vehicle based on the installation position on the shared vehicle. Therefore, the collected image to be detected contains the inherent features corresponding to the target part of the shared vehicle. Exemplarily, if the camera is installed under the basket of the shared vehicle, the target part of the shared vehicle that can be photographed is the part directly in front of the wheels, and the part directly in front of the wheels refers to the driving direction of the shared vehicle.

[0055] According to the identified inherent features, detect whether the camera is abnormal. Optionally, determine whether the captured inherent features are complete based on the similarity between the identified inherent features and the inherent feature template, so as to determine whether the camera is abnormal. If the inherent features are not identified, or the shape, posture and size of the identified inherent features are different from the inherent feature template, the camera is abnormal.

[0056] In this embodiment, multiple groups of images to be detected are acquired by the camera to be detected when the vehicle state of the shared vehicle meets the preset self-test conditions, and the inherent features in the images to be detected are identified, and the camera is detected to see if there is an abnormality based on the identified inherent features. By using the inherent features as a criterion for determining whether the camera is abnormal, the abnormality detection of the camera is realized, and the abnormality of the camera can be discovered in time, reducing the impact on the user's return of the vehicle, and avoiding the impact of the camera abnormality on the user's normal return of the vehicle.

[0057] In one embodiment, when there is an abnormality in the camera, its fault type includes position offset and equipment contamination. Among them, since the camera installation position is fixed, and it is necessary to judge the parking posture of the shared vehicle according to the relative position relationship between the camera and the shared vehicle and the position of the identified parking sign. Therefore, position offset type abnormalities will affect the judgment of the parking posture of the shared vehicle, and it is impossible to accurately judge whether the user has parked in accordance with the requirements. Equipment contamination type abnormalities will block the image collected by the camera, affecting the recognition of the parking sign, and it is also impossible to accurately judge whether the user has parked in accordance with the requirements.

[0058] In step 300, detecting whether there is an abnormality in the camera according to the inherent characteristics includes:

[0059] Step 311, obtaining a first position of the inherent feature in the image to be detected, and obtaining a second position of the inherent feature in a reference image; the reference image is collected by the camera when there is no abnormality;

[0060] Step 312, comparing the first position with the second position to determine the displacement of the inherent feature in the image to be detected;

[0061] Step 313: Determine whether the camera has a positional deviation abnormality according to the displacement.

[0062] First, a first position of the inherent feature in the image to be detected is obtained, and a second position of the inherent feature in the reference image is obtained, where the reference image is an image captured by the camera when there is no abnormality. The first position is compared with the second position to determine the displacement of the inherent feature in the image to be detected, and based on the displacement, it is determined whether the camera has a positional deviation abnormality.

[0063] Optionally, if the displacement is 0, the camera does not have a position offset abnormality, otherwise, if the displacement is greater than 0, the camera has a position offset abnormality. Alternatively, if the displacement is less than a preset value, the camera does not have a position offset abnormality, otherwise, if the displacement is greater than or equal to the preset value, the camera has a position offset abnormality.

[0064] The shared vehicle stores a reference image, which records the location of the shared vehicle's inherent features. Since the relative position between the camera and the shared vehicle's inherent features (such as the front wheel cover, etc.) is fixed, the inherent features will be in the same position in the image whenever the image is captured, that is, the inherent features will be in the same position in the camera image. Therefore, in a set of images to be detected, the ground features will change dynamically due to the movement of the shared vehicle, but the inherent features are basically the same.

[0065] Therefore, by identifying the inherent features in the image to be detected, the position of the inherent features in the image to be detected can be determined, and then the relative relationship between the position of the inherent features in the image to be detected and its initial position in the reference image can be compared to determine whether the camera has a positional offset abnormality. The position of the inherent feature in the image to be detected and its position in the reference image include the following situations. There are obvious differences in the positions in different images to be detected. In this case, it means that the relative position between the camera and the inherent feature is changing, so the camera has a positional offset caused by looseness. If the fixed feature is not identified, or there is a difference between the position of the inherent feature in the image to be detected and its position in the reference image, it means that the camera has been significantly offset relative to the initial installation position, and the camera has a positional offset such as falling off from the initial installation position.

[0066] In one embodiment, determining whether the camera has an abnormality of device contamination according to the identified inherent features, in step 300, detecting whether the camera has an abnormality according to the inherent features further includes:

[0067] Step 321, based on any group of the images to be detected, calculating the difference between any two adjacent frames of images to obtain a plurality of difference images;

[0068] Step 322, performing binarization processing on each of the difference images to obtain a binarized image corresponding to each of the difference images;

[0069] Step 323: Detect whether the camera has an abnormality of device contamination according to the position of the inherent feature in the binary image.

[0070] For any group of images to be detected among the multiple groups of images to be detected, the difference between any two adjacent frames is calculated to obtain multiple difference images corresponding to the group of images to be detected, and each difference image is binarized to obtain a binarized image corresponding to each difference image. According to the position of the inherent features in the binarized image, the camera is detected to see if there is an abnormality of equipment contamination.

[0071] Optionally, the inherent features are removed from the binary image according to their positions in the binary image. After the inherent features are removed, if there are still areas in the binary image with pixel values ​​similar to those of the inherent features, they can be determined as damaged areas, and the camera has an abnormality of device damage.

[0072] In one embodiment, the binarization of the difference image is implemented based on a preset threshold. In step 322, each difference image is binarized to obtain a binarized image corresponding to each difference image, including:

[0073] Step 3201, obtaining the initial pixel value of each pixel point in the target difference image; the target difference image is any one of the difference images;

[0074] Step 3202, setting the pixel value of the first pixel point as the first eigenvalue, and setting the pixel value of the second pixel point as the second eigenvalue, so as to perform binarization processing on the target difference image to obtain a binarized image of the target difference image;

[0075] The first pixel point is a pixel point in the target difference image whose initial pixel value is greater than a preset threshold, and the second pixel point is a pixel point in the target difference image whose initial pixel value is less than or equal to the preset threshold.

[0076] First, the initial pixel value of each pixel in the target difference image is obtained, wherein the target difference image is any one of the difference images. The pixel value of the first pixel in the target difference image is set to the first eigenvalue, and the pixel value of the second pixel in the target difference image is set to the second eigenvalue, thereby implementing a binarization process on the target difference image to obtain a corresponding binarized image. The first pixel is a pixel in the target difference image whose initial pixel value is greater than a preset threshold, and the second pixel is a pixel in the target difference image whose initial pixel value is less than or equal to the preset threshold. In this way, each difference image is binarized to obtain a binarized image corresponding to each difference image.

[0077] Exemplarily, the first eigenvalue is 1, the second eigenvalue is 0, the preset threshold is the threshold of binary segmentation, the pixel values ​​of pixels in the difference image whose pixel values ​​are less than or equal to the threshold are set to 0, and the pixel values ​​of pixels in the difference image whose pixel values ​​are greater than the threshold are set to 1.

[0078] Furthermore, in step 323, based on the position of the inherent feature in the binary image, detecting whether the camera has an abnormality of device contamination specifically includes:

[0079] Step 301, performing an OR operation on each of the binary images pixel by pixel, to obtain a connected region in the binary image;

[0080] Step 302, obtaining a third position of the connected region in the binary image, and obtaining a fourth position of the inherent feature in the binary image;

[0081] Step 303, comparing the fourth position with the third position to determine the relative position relationship between the connected region and the inherent feature in the binary image;

[0082] Step 304: Determine whether the camera has an abnormality of device contamination according to the relative position relationship.

[0083] Perform bitwise or pixel-by-pixel OR operations on each binary image to obtain a connected area in the binary image, which includes one or more connected areas and may also include areas corresponding to inherent features. Then obtain the third position of the connected area in the binary image, and obtain the fourth position of the inherent feature in the binary image, and compare the fourth position with the third position to determine the relative position relationship between the connected area and the inherent feature in the binary image. Further determine whether the connected area belongs to the area where the inherent feature is located based on the relative position relationship, so as to determine whether the camera has an abnormality of equipment contamination.

[0084] Optionally, if the connected area in the binary image belongs to the area where the inherent feature is located, the connected area can be determined as the inherent feature, and the camera does not have the abnormality of equipment contamination. If the connected area in the binary image does not belong to the area where the inherent feature is located, or if the connected area in the binary image does not all belong to the area where the inherent feature is located, the area of ​​the connected area other than the inherent feature can be determined as the contaminated area, and the camera has the abnormality of equipment contamination.

[0085] In one embodiment, firstly, according to the position of the inherent feature in the image to be detected, it is determined whether the camera has a positional deviation abnormality. If the camera does not have a positional deviation, the difference between any two adjacent frames in each group of images to be detected is calculated to obtain a plurality of difference images corresponding to each group of images to be detected. Figure 2 As shown, the difference between two adjacent frame images P1 and P2 is made to obtain the corresponding difference image.

[0086] Then, each difference image is binarized to filter out pixels with relatively small differences. Based on the set binary segmentation threshold, the pixel values ​​of pixels less than or equal to the threshold are set to 0, and the pixel values ​​of pixels greater than the threshold are set to 1. Then, multiple binarized difference images are bitwise ORed to obtain one or more connected areas. If the connected area does not belong to the location where the inherent feature is located, it is determined to be a contaminated area.

[0087] Among them, by taking the difference of adjacent images and binarizing them, similar pixels in the same position in the two images and dissimilar pixels in the same position can be distinguished. In order to enhance the difference, multiple groups of binarized difference images are bitwise ORed. For the contaminated area, it is in a masked state under different backgrounds. Therefore, in each binarized difference image, its shape and position are basically the same. Through the OR operation, the ground background area that is mistakenly judged as a contaminated area in a group of images to be detected can be filtered out.

[0088] Optional, such as Figure 3 As shown, the binary difference image 1 and the binary difference image 2 are bitwise ORed to filter out the connected areas in the binary image with pixel values ​​similar to the inherent features, and the remaining connected areas are candidate contaminated areas. The positions of the candidate contaminated areas are compared with the positions of the inherent features. In each candidate contaminated area, the connected areas that are different from the positions of the inherent features are contaminated areas, and the connected areas that are the same as the positions of the inherent features are inherent features and do not belong to contaminated areas. After the binary difference image is ORed, if there is a connected area that is different from the position of the inherent features, it can be determined that the camera has an abnormality of device contamination.

[0089] Furthermore, after detecting whether the camera is abnormal according to the inherent characteristics, if the camera is abnormal, the fault information is reported to the server, and the server can generate an operation and maintenance work order according to the fault information reported by the shared vehicle. Therefore, after step 300, the following may also be included:

[0090] Step 401: if the camera has an abnormality, generate fault information of the camera; the fault information includes the fault type and fault level;

[0091] Step 402, reporting the fault information to the server; the server generates an operation and maintenance work order based on the fault information, and configures the return strategy of the shared vehicle to the backup return strategy corresponding to the fault information; wherein the operation and maintenance urgency of the operation and maintenance work order is determined based on the fault information.

[0092] If there is an abnormality with the camera, fault information of the camera will be generated, which includes the fault type and fault level. The fault types include position offset and device damage. For position offset type abnormalities, the fault level can be divided according to the degree of camera position offset. For device damage type abnormalities, the fault level can be divided according to the size of the damaged area and / or the position of the damaged area.

[0093] The generated fault information is reported to the server, and the server generates an operation and maintenance work order based on the fault information, and configures the return policy of the shared vehicle to the backup return policy corresponding to the fault information. The operation and maintenance urgency of the operation and maintenance work order is determined based on the fault information, specifically, based on the fault level in the fault information. The higher the fault level, the higher the operation and maintenance urgency of the operation and maintenance work order.

[0094] Optionally, the backup return strategy is used to relax the return conditions of the shared vehicle. The backup return strategy is determined based on the fault information, specifically the fault type and fault level. Different fault types and / or different fault levels correspond to different backup return strategies. For example, for equipment contamination anomalies, if the area of ​​the contaminated area is small, and / or the degree of obstruction of the parking sign caused by the location of the contaminated area is small, then the matching degree of the parking sign can be appropriately relaxed in the return strategy; for position offset anomalies, since the relative position relationship between the camera and the shared vehicle has changed, and the change is unpredictable, the return conditions can be set based on the electronic fence, and the recognition and matching of the parking sign can be stopped in the backup return strategy.

[0095] Furthermore, after reporting the fault information to the server, the following steps may also be performed:

[0096] Step 403, receiving a vehicle lock instruction from the server; the vehicle lock instruction is generated by the server according to a received vehicle return request of the shared vehicle when it is determined that the shared vehicle satisfies the backup vehicle return strategy;

[0097] When the server detects that the shared vehicle has been returned, if it is determined according to the fault information that the shared vehicle needs to be deactivated, the server sets the vehicle state of the shared vehicle to a disabled state.

[0098] Receive a vehicle lock instruction issued by the server, which is generated by the server based on the received shared vehicle return request when it is determined that the shared vehicle meets the backup return policy. When the server detects that the shared vehicle has completed the return according to the backup return policy, it determines whether the shared vehicle needs to be deactivated based on the fault information. When it is determined that the shared vehicle needs to be deactivated, the vehicle status of the shared vehicle is set to a disabled state.

[0099] Optionally, for a shared vehicle in a disabled state, when an unlocking request from a user terminal is detected, a prompt message indicating that the vehicle is faulty and unavailable can be sent to the user terminal, thereby prompting the user that the shared vehicle is currently unavailable, thereby avoiding the situation where the user cannot return the vehicle normally after use or cannot identify whether the user has parked properly.

[0100] In some embodiments, a shared vehicle can report multiple groups of images to be detected captured by the camera to a server, and the server will execute the steps of the shared vehicle parking camera anomaly detection method described in the above embodiments. That is, the shared vehicle parking camera anomaly detection method provided in an embodiment of the present invention can also be applied to the server.

[0101] In other embodiments, the shared vehicle parking camera anomaly detection method provided in the embodiments of the present invention can also be applied to the camera, where the camera collects multiple sets of images to be detected for self-inspection when the vehicle status of the shared vehicle meets preset self-inspection conditions.

[0102] The server's process of detecting camera abnormalities and the camera's self-inspection process can be referenced with the steps of the shared vehicle parking camera abnormality detection method described in the above embodiments, and will not be repeated here.

[0103] In this embodiment, abnormality detection is performed on the camera of the shared vehicle to determine whether the camera is offset or damaged, and when an abnormality is detected in the camera, fault information is reported to the server. The server relaxes the return conditions for the shared vehicle based on the reported fault information, ensuring that the user can return the vehicle normally in the event of a camera abnormality, thereby avoiding the situation where the user is unable to return the vehicle in the event of a camera abnormality.

[0104] Furthermore, the server can also generate an operation and maintenance work order based on the reported fault information and determine whether the shared vehicle needs to be deactivated. While improving the timeliness of the operation and maintenance of the camera, it prevents users from using shared vehicles with faults, reduces the situation where users are unable to return the vehicle normally or cannot identify whether the user has parked properly, and improves the effectiveness of shared vehicle management.

[0105] The shared vehicle parking camera anomaly detection device provided by the present invention is described below. The shared vehicle parking camera anomaly detection device described below and the shared vehicle parking camera anomaly detection method described above can be referenced to each other.

[0106] Reference Figure 4 , the shared vehicle parking camera anomaly detection device provided by the embodiment of the present invention includes:

[0107] The image acquisition module 10 is used to obtain a plurality of groups of images to be detected acquired by the camera to be detected; the images to be detected are acquired by the camera when the vehicle state of the shared vehicle meets the preset self-test conditions;

[0108] A feature recognition module 20, for recognizing inherent features in the image to be detected; the inherent features are used to characterize a target portion of the shared vehicle that can be captured by the camera at the installation position on the shared vehicle;

[0109] The abnormality detection module 30 is used to detect whether there is an abnormality in the camera according to the inherent characteristics.

[0110] In one embodiment, when the camera is abnormal, the fault type includes position offset; the abnormality detection module 30 is further used to:

[0111] Acquire a first position of the inherent feature in the image to be detected, and acquire a second position of the inherent feature in a reference image; the reference image is acquired by the camera when there is no abnormality;

[0112] Comparing the first position with the second position to determine the displacement of the inherent feature in the image to be detected;

[0113] Determine whether the camera has a positional deviation abnormality according to the displacement.

[0114] In one embodiment, the fault type when the camera is abnormal includes device contamination; the abnormality detection module 30 is further used to:

[0115] Based on any group of the images to be detected, calculating the difference between any two adjacent frames of images to obtain a plurality of difference images;

[0116] Performing binarization processing on each of the difference images to obtain a binarized image corresponding to each of the difference images;

[0117] According to the position of the inherent feature in the binary image, it is detected whether the camera has an abnormality of device contamination.

[0118] In one embodiment, the anomaly detection module 30 is further used to:

[0119] Performing bitwise OR operation on each of the binary images pixel by pixel to obtain connected areas in the binary images;

[0120] Obtaining a third position of the connected region in the binary image, and obtaining a fourth position of the inherent feature in the binary image;

[0121] Comparing the fourth position with the third position to determine the relative position relationship between the connected region and the inherent feature in the binary image;

[0122] Determine whether the camera has an abnormality of equipment contamination based on the relative position relationship.

[0123] In one embodiment, the anomaly detection module 30 is further used to:

[0124] Obtaining an initial pixel value of each pixel point in a target difference image; the target difference image is any one of the difference images;

[0125] Setting the pixel value of the first pixel point as the first eigenvalue and the pixel value of the second pixel point as the second eigenvalue to perform binarization processing on the target difference image to obtain a binarized image of the target difference image;

[0126] The first pixel point is a pixel point in the target difference image whose initial pixel value is greater than a preset threshold, and the second pixel point is a pixel point in the target difference image whose initial pixel value is less than or equal to the preset threshold.

[0127] In one embodiment, the shared vehicle parking camera anomaly detection device further includes an anomaly processing module for:

[0128] If the camera is abnormal, generate fault information of the camera; the fault information includes fault type and fault level;

[0129] Report the fault information to the server; the server generates an operation and maintenance work order according to the fault information, and configures the return strategy of the shared vehicle to the backup return strategy corresponding to the fault information; wherein the operation and maintenance urgency of the operation and maintenance work order is determined according to the fault information.

[0130] In one embodiment, the exception handling module is further used to:

[0131] receiving a vehicle locking instruction from the server; the vehicle locking instruction is generated by the server according to a received vehicle return request of the shared vehicle when it is determined that the shared vehicle satisfies the backup vehicle return strategy;

[0132] When the server detects that the shared vehicle has been returned, if it is determined according to the fault information that the shared vehicle needs to be deactivated, the server sets the vehicle state of the shared vehicle to a disabled state.

[0133] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the steps of the shared vehicle parking camera abnormality detection method, for example including:

[0134] Acquire multiple groups of images to be detected captured by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0135] Identifying inherent features in the image to be detected; the inherent features are used to characterize a target portion of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0136] Whether the camera is abnormal is detected according to the inherent characteristics.

[0137] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0138] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps of the shared vehicle parking camera anomaly detection method provided by the above methods, for example, including:

[0139] Acquire multiple groups of images to be detected captured by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0140] Identifying inherent features in the image to be detected; the inherent features are used to characterize a target portion of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0141] Whether the camera is abnormal is detected according to the inherent characteristics.

[0142] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the steps of the shared vehicle parking camera anomaly detection method provided by the above methods, for example, including:

[0143] Acquire multiple groups of images to be detected captured by the camera to be detected; the images to be detected are collected by the camera when the vehicle state of the shared vehicle meets a preset self-test condition;

[0144] Identifying inherent features in the image to be detected; the inherent features are used to characterize a target portion of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle;

[0145] Whether the camera is abnormal is detected according to the inherent characteristics.

[0146] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0147] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting anomalies of a shared vehicle parking camera, characterized in that: include: Acquire multiple groups of images to be detected captured by the camera to be detected; The image to be detected is collected by the camera when the vehicle state of the shared vehicle meets the preset self-checking condition; Identifying inherent features in the image to be detected; The inherent feature is used to characterize the target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle; the camera is installed at the bottom of the basket of the shared vehicle; Detecting whether the camera has an abnormality according to the inherent characteristics; If the camera is abnormal, generate fault information of the camera; reporting the fault information to a server; and configuring the return strategy of the shared vehicle to be a backup return strategy corresponding to the fault information by the server; The fault type when the camera is abnormal includes position offset; and detecting whether the camera is abnormal according to the inherent characteristics includes: Acquire a first position of the inherent feature in the image to be detected, and acquire a second position of the inherent feature in a reference image; the reference image is acquired by the camera when there is no abnormality; Comparing the first position with the second position to determine the displacement of the inherent feature in the image to be detected; Determine whether the camera has a positional deviation abnormality according to the displacement; The fault type when the camera is abnormal includes device contamination; and detecting whether the camera is abnormal according to the inherent characteristics includes: Based on any group of the images to be detected, calculating the difference between any two adjacent frames of images to obtain a plurality of difference images; Performing binarization processing on each of the difference images to obtain a binarized image corresponding to each of the difference images; According to the position of the inherent feature in the binary image, it is detected whether the camera has an abnormality of device contamination.

2. The shared vehicle parking camera anomaly detection method according to claim 1, characterized in that: The detecting, according to the position of the inherent feature in the binary image, whether the camera has an abnormality of device contamination includes: Performing bitwise OR operation on each of the binary images pixel by pixel to obtain connected areas in the binary images; Obtaining a third position of the connected region in the binary image, and obtaining a fourth position of the inherent feature in the binary image; Comparing the fourth position with the third position to determine the relative position relationship between the connected region and the inherent feature in the binary image; Determine whether the camera has an abnormality of equipment contamination based on the relative position relationship.

3. The shared vehicle parking camera anomaly detection method according to claim 1, characterized in that: The binarization process is performed on each of the difference images to obtain a binarized image corresponding to each of the difference images, including: Obtaining an initial pixel value of each pixel point in a target difference image; the target difference image is any one of the difference images; Setting the pixel value of the first pixel point as the first eigenvalue and the pixel value of the second pixel point as the second eigenvalue to perform binarization processing on the target difference image to obtain a binarized image of the target difference image; The first pixel point is a pixel point in the target difference image whose initial pixel value is greater than a preset threshold, and the second pixel point is a pixel point in the target difference image whose initial pixel value is less than or equal to the preset threshold.

4. The shared vehicle parking camera anomaly detection method according to claim 1, characterized in that: After reporting the fault information to the server, the server generates an operation and maintenance work order according to the fault information; wherein the fault information includes a fault type and a fault level, and the operation and maintenance urgency of the operation and maintenance work order is determined according to the fault information.

5. The shared vehicle parking camera anomaly detection method according to claim 1, characterized in that: After reporting the fault information to the server, the method further includes: receiving a vehicle locking instruction from the server; the vehicle locking instruction is generated by the server according to a received vehicle return request of the shared vehicle when it is determined that the shared vehicle satisfies the backup vehicle return strategy; When the server detects that the shared vehicle has been returned, if it is determined according to the fault information that the shared vehicle needs to be deactivated, the server sets the vehicle state of the shared vehicle to a disabled state.

6. A shared vehicle parking camera anomaly detection device, characterized in that: include: An image acquisition module, used to obtain multiple groups of images to be detected acquired by the camera to be detected; The image to be detected is collected by the camera when the vehicle state of the shared vehicle meets the preset self-checking condition; A feature recognition module, used to recognize inherent features in the image to be detected; The inherent feature is used to characterize the target part of the shared vehicle that can be photographed by the camera at the installation position on the shared vehicle; the camera is installed at the bottom of the basket of the shared vehicle; An abnormality detection module, used for detecting whether the camera has an abnormality according to the inherent characteristics; The shared vehicle parking camera anomaly detection device further includes an anomaly processing module for: If the camera is abnormal, generate fault information of the camera; reporting the fault information to a server; and configuring the return strategy of the shared vehicle to be a backup return strategy corresponding to the fault information by the server; When the camera is abnormal, the fault type includes position offset; the abnormality detection module is further used for: Acquire a first position of the inherent feature in the image to be detected, and acquire a second position of the inherent feature in a reference image; the reference image is acquired by the camera when there is no abnormality; Comparing the first position with the second position to determine the displacement of the inherent feature in the image to be detected; Determine whether the camera has a positional deviation abnormality according to the displacement; When the camera is abnormal, the fault type includes device contamination; the abnormality detection module is further used for: Based on any group of the images to be detected, calculating the difference between any two adjacent frames of images to obtain a plurality of difference images; Performing binarization processing on each of the difference images to obtain a binarized image corresponding to each of the difference images; According to the position of the inherent feature in the binary image, it is detected whether the camera has an abnormality of device contamination.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the shared vehicle parking camera anomaly detection method as described in any one of claims 1 to 5 are implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the shared vehicle parking camera anomaly detection method as described in any one of claims 1 to 5 are implemented.

Images