Image information acquisition method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an image information acquisition method and device, equipment and a storage medium. The method comprises the following steps: acquiring original image data acquired by different types of image sensors, identifying abnormal image data from the original image data based on configuration parameters corresponding to the image sensors, and uploading the abnormal image data to a cloud server. According to the technical scheme provided by the embodiment of the invention, the problem that the information processing efficiency of the unmanned vehicle cloud server is influenced due to different image information acquisition standards corresponding to different image sensors in the unmanned vehicle in the related technology is solved, and invalid image data needing to be processed by the cloud server is remarkably reduced; therefore, the communication pressure and the data processing pressure of the cloud server are remarkably reduced, the operation and maintenance efficiency of the cloud server is improved, and the overall information processing efficiency and accuracy are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of robot control technology, and in particular to an image information acquisition method, device, equipment and storage medium. Background Art

[0002] With the development of technologies in fields such as intelligent driving and robotics, unmanned vehicles are increasingly being researched and applied. Unmanned vehicles can collect images of the surrounding environment through image sensors to achieve their own positioning and control their own movement. At the same time, they can also identify the collected image data, promptly detect abnormal information that requires alarm, and transmit relevant information to the cloud, thereby realizing remote information collection and reporting.

[0003] In the related technology, unmanned vehicles are usually equipped with multiple image sensors. Each image sensor will transmit the collected image data to its own preset image processing server for processing, and then send the processed data to the unmanned vehicle cloud server. However, the corresponding image data reporting standards in each image processing server are different, and the adjustability is insufficient, resulting in a large amount of useless image data, false alarm events and other junk information frequently appearing in the unmanned vehicle cloud server, resulting in poor information processing efficiency and accuracy. Summary of the invention

[0004] The embodiments of the present disclosure provide an image information acquisition method, device, equipment and storage medium to solve the problem in the related art that different image sensors in unmanned vehicles correspond to different image information acquisition standards, which affects the information processing efficiency of the unmanned vehicle cloud server.

[0005] In a first aspect, an embodiment of the present disclosure provides an image information acquisition method, which is applied to a vehicle-mounted processor. The image information acquisition method includes:

[0006] Acquire raw image data collected by an image sensor, where there are at least two types of image sensors;

[0007] Based on configuration parameters corresponding to the image sensor, abnormal image data is identified from the original image data, and the configuration parameters correspond to the type of the image sensor;

[0008] Upload abnormal image data to the cloud server.

[0009] Optionally, based on the configuration parameters corresponding to the image sensor, abnormal image data is identified from the original image data, including: based on the configuration parameters corresponding to the image sensor, preprocessing the original image data to obtain processed image data corresponding to the original image data, the preprocessing including image size normalization; based on the image recognition algorithm, identifying abnormal image data in the processed image data.

[0010] Optionally, based on configuration parameters corresponding to the image sensor, the raw image data is preprocessed to obtain processed image data corresponding to the raw image data, including: based on the type of the image sensor, obtaining configuration parameters corresponding to the image sensor; based on a development toolkit and configuration parameters corresponding to the image sensor, the raw image data is preprocessed to obtain processed image data corresponding to the raw image data.

[0011] Optionally, the configuration parameters are obtained by the on-board processor from a cloud server.

[0012] Optionally, the cloud server is used to obtain a development toolkit from a sensor server corresponding to the image sensor based on a communication protocol corresponding to the image sensor, and determine configuration parameters corresponding to the image sensor.

[0013] Optionally, the configuration parameters include an IP address corresponding to the image sensor, an alarm type for identification, and a type of image data to be collected.

[0014] Optionally, the on-board processor stores a reference alarm image sent by the cloud server, and the reference alarm image corresponds to the alarm type.

[0015] Optionally, based on an image recognition algorithm, identifying abnormal image data in the processed image data includes: determining the similarity between the processed image data and a reference alarm image based on the image recognition algorithm; and determining the abnormal image data from the processed image data based on the similarity.

[0016] Optionally, based on the similarity, abnormal image data is determined from the processed image data, including: if the similarity between the processed image data and all reference alarm images is less than a set value, the processed image data is determined as irrelevant image data; and the processed image data other than the irrelevant image data is determined as abnormal image data.

[0017] In a second aspect, an embodiment of the present disclosure provides an image information acquisition device, which is applied to a vehicle-mounted processor. The image information acquisition device includes:

[0018] An acquisition module, used to acquire raw image data collected by an image sensor, and there are at least two types of image sensors;

[0019] A recognition module, used for identifying abnormal image data from the original image data based on configuration parameters corresponding to the image sensor, where the configuration parameters correspond to the type of the image sensor;

[0020] The processing module is used to upload abnormal image data to the cloud server.

[0021] Optionally, the recognition module is specifically used to identify abnormal image data from the original image data based on the configuration parameters corresponding to the image sensor, including: preprocessing the original image data based on the configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data, the preprocessing including image size normalization; based on the image recognition algorithm, identifying abnormal image data in the processed image data.

[0022] Optionally, the identification module is specifically used to obtain configuration parameters corresponding to the image sensor based on the type of the image sensor; based on the development toolkit and configuration parameters corresponding to the image sensor, pre-process the original image data to obtain processed image data corresponding to the original image data.

[0023] Optionally, the identification module specifically includes configuration parameters obtained by the on-board processor from the cloud server.

[0024] Optionally, the identification module specifically includes: the cloud server is used to obtain a development toolkit from a sensor server corresponding to the image sensor based on a communication protocol corresponding to the image sensor, and determine configuration parameters corresponding to the image sensor.

[0025] Optionally, the identification module specifically includes configuration parameters including an IP address corresponding to the image sensor, an alarm type for identification, and a type of image data to be collected.

[0026] Optionally, the identification module specifically includes: a reference alarm image sent by a cloud server is stored in the vehicle processor, and the reference alarm image corresponds to the alarm type.

[0027] Optionally, the recognition module is specifically used to determine the similarity between the processed image data and the reference alarm image based on an image recognition algorithm; and determine abnormal image data from the processed image data based on the similarity.

[0028] Optionally, the recognition module is specifically used to determine the processed image data as irrelevant image data if the similarity between the processed image data and all reference alarm images is less than a set value; and determine the processed image data other than the irrelevant image data as abnormal image data.

[0029] In a third aspect, an embodiment of the present disclosure further provides a control device, the control device comprising:

[0030] at least one processor;

[0031] and a memory communicatively coupled to the at least one processor;

[0032] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the control device to execute the image information acquisition method as described in the first aspect of the present disclosure.

[0033] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the image information acquisition method as described in the first aspect of the present disclosure.

[0034] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, which includes computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the image information acquisition method as in the first aspect of the present disclosure.

[0035] The image information acquisition method, device, equipment and storage medium provided by the embodiments of the present disclosure obtain the original image data collected by different types of image sensors, and based on the configuration parameters corresponding to the image sensors, identify abnormal image data from the original image data, and then upload the abnormal image data to the cloud server. As a result, the processing of the original image data collected by the image sensor can be integrated into the vehicle processor, so that the abnormal image data can be identified from the original image data using a unified standard, and then the abnormal image data can be uploaded to the cloud server. As a result, the status of the abnormal image data received by the cloud server can be unified, and the invalid image data that needs to be processed by the cloud server can be significantly reduced, thereby significantly reducing the communication pressure and data processing pressure of the cloud server, thereby improving the operation and maintenance efficiency of the cloud server, and improving the overall information processing efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0037] Figure 1 An application scenario diagram of the image information acquisition method provided by the embodiment of the present disclosure;

[0038] Figure 2 A flowchart of an image information acquisition method provided by an embodiment of the present disclosure;

[0039] Figure 3a A flowchart of an image information acquisition method provided by yet another embodiment of the present disclosure;

[0040] Figure 3b for Figure 3a A flow chart of a method for preprocessing raw image data provided in the illustrated embodiment;

[0041] Figure 3c for Figure 3a A flow chart of a method for identifying abnormal image data provided in the illustrated embodiment;

[0042] Figure 4 A schematic diagram of the structure of an image information acquisition device provided by another embodiment of the present disclosure;

[0043] Figure 5 A schematic diagram of the structure of a control device provided in one embodiment of the present disclosure.

[0044] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0046] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0047] With the development of technology in fields such as intelligent driving and robotics, unmanned vehicles have been increasingly studied and applied. Unmanned vehicles can use image sensors to collect images of the surrounding environment to achieve their own positioning and control their own movement. At the same time, by identifying the collected image data, it can promptly detect abnormal information that requires alarms, and transmit relevant information to the cloud, thereby realizing remote information collection and reporting. Unmanned vehicles are usually equipped with a variety of image sensors. Each image sensor will be configured by the corresponding manufacturer with its own dedicated image processing server and image processing parameters that support adjustment. After the image sensor collects the original image data, it will be uploaded to the corresponding image processing server through the on-board communication equipment. After the image processing server completes the processing, it will be transmitted to the cloud server corresponding to the unmanned vehicle.

[0048] In the related art, different types of image sensors and corresponding image processing servers support different image processing parameters and image processing algorithms. Even if each image sensor is configured with the type of image data that needs to be identified and uploaded, due to the differences in image processing algorithms and image processing parameters, there is also a large amount of invalid data in the abnormal image data transmitted from the image processing server to the cloud server, resulting in poor information processing efficiency and accuracy based on image data collected by unmanned vehicle image sensors.

[0049] In order to solve this problem, the embodiment of the present disclosure provides an image information acquisition method, which processes the data collected by different types of image sensors through a vehicle-mounted processor, identifies abnormal image data, and then uploads it to a cloud server, effectively solving the problem of information processing efficiency and accuracy of the unmanned vehicle corresponding to the cloud server.

[0050] The application scenarios of the embodiments of the present disclosure are explained below:

[0051] Figure 1 This is an application scenario diagram of the image information acquisition method provided by the embodiment of the present disclosure. Figure 1 As shown, after the image sensor 110 in the unmanned vehicle 100 collects the original image data, it will be transmitted to the on-board processor 120. After being processed by the on-board processor 120, the abnormal image data will be uploaded to the unmanned vehicle server 130, thereby completing the image information collection process.

[0052] It should be noted that Figure 1 In the scenario shown, only one unmanned vehicle, image sensor, on-board processor, and unmanned vehicle server is used as an example for illustration, but the present disclosure is not limited to this. In other words, the number of unmanned vehicles, image sensors, on-board processors, and unmanned vehicle servers can be arbitrary.

[0053] The image information acquisition method provided by the present disclosure is described in detail below through specific embodiments.

[0054] Figure 2 The following is a flow chart of an image information acquisition method provided by an embodiment of the present disclosure. Figure 2 As shown, the image information acquisition method provided in this embodiment is applied to a vehicle-mounted processor, and includes the following steps:

[0055] Step S201, obtaining original image data collected by an image sensor.

[0056] Among them, there are at least two types of image sensors.

[0057] Specifically, the unmanned vehicle includes multiple image sensors, which are set at various different positions, including sensors for obtaining images from various directions such as in front of the vehicle, on both sides, and under the vehicle. Due to the different shooting directions, the captured images are at different average distances from the unmanned vehicle (the image sensor shooting the bottom of the vehicle only needs to ensure that the bottom of the vehicle is safe and without faults, and its shooting distance is the range of the bottom of the vehicle, while the image sensor in front of the vehicle needs to shoot a longer distance in front of the vehicle to ensure the safety of the vehicle). Therefore, the performance of image sensors in different positions will be significantly different.

[0058] In order to ensure that the image sensor at each location has relatively excellent performance, different brands and models are usually selected for image sensors at different locations to optimize the image acquisition performance of the unmanned vehicle.

[0059] Therefore, the original image data collected by different image sensors will have differences in clarity, size, format, etc., so it is necessary to first transfer the original image data collected by different image processors to the on-board processor for unified processing so as to facilitate further processing and recognition.

[0060] In some embodiments, the vehicle-mounted processor referred to in the embodiments of the present disclosure is an entire processing system that includes the vehicle-mounted communication device, rather than a separate central processing unit or processing chip.

[0061] Step S202: based on the configuration parameters corresponding to the image sensor, abnormal image data is identified from the original image data.

[0062] The configuration parameters correspond to the types of image sensors.

[0063] Specifically, in order to ensure that images in different types of image sensors are processed to the same or similar state (such as normalization of size, format, etc.), it is necessary to process the original image based on the configuration parameters corresponding to each image sensor and identify abnormal image data therein.

[0064] The configuration parameters may include characteristic information of the original image data, such as clarity, size, format, etc., to determine how to normalize the original image data based on the characteristic information; they may also include parameters required for normalizing the original image data, such as scaling, cropping position and cropping amount.

[0065] After the normalization process, the original image data can be identified by methods such as image recognition algorithms to identify abnormal image data from the original image data.

[0066] Step S203: Upload the abnormal image data to the cloud server.

[0067] Specifically, the vehicle-mounted sensor identifies abnormal image data from the normalized image data, which can ensure that the identified abnormal image data has a unified standard and has a high recognition accuracy, significantly reducing the situation of abnormal image data being misidentified, thereby significantly reducing the amount of data uploaded to the cloud server, and thus making the data obtained by the cloud server for processing more reliable and accurate, thereby improving the data processing reliability and processing efficiency of the cloud server.

[0068] The image information acquisition method provided by the disclosed embodiment obtains the original image data collected by different types of image sensors, and based on the configuration parameters corresponding to the image sensors, identifies abnormal image data from the original image data, and then uploads the abnormal image data to the cloud server. As a result, the processing of the original image data collected by the image sensor can be integrated into the vehicle processor, so that the abnormal image data can be identified from the original image data using a unified standard, and then the abnormal image data is uploaded to the cloud server. As a result, the status of the abnormal image data received by the cloud server can be unified, and the invalid image data that needs to be processed by the cloud server can be significantly reduced, thereby significantly reducing the communication pressure and data processing pressure of the cloud server, thereby improving the operation and maintenance efficiency of the cloud server, and improving the overall information processing efficiency and accuracy.

[0069] Figure 3a The following is a flow chart of an image information acquisition method provided by an embodiment of the present disclosure. Figure 3a As shown, the image information acquisition method provided in this embodiment is applied to a vehicle-mounted processor, and includes the following steps:

[0070] Step S301, obtaining original image data collected by an image sensor.

[0071] Among them, there are at least two types of image sensors.

[0072] Specifically, the image sensor on the unmanned vehicle will directly transmit the collected data (that is, the original image data) to the on-board processor. The on-board processor is configured with an information collection and processing service to complete the processing of the original image data, including receiving the original image data from the image sensor, identifying abnormal image data from the original image data, and uploading the abnormal image data to the cloud server through the on-board communication device contained in the on-board processor.

[0073] Step S302 : pre-processing the original image data based on the configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data.

[0074] Among them, the preprocessing includes image size normalization.

[0075] Specifically, the on-board processor will pre-process the corresponding raw image data based on the configuration parameters corresponding to each image sensor obtained from the cloud server.

[0076] Preprocessing includes adjusting parameters such as image size and format, and may also include filtering raw image data that does not contain valid image data, such as directly filtering continuously repeated images.

[0077] Through preprocessing, it is ensured that the original image data corresponding to different image sensors maintain the maximum uniformity after processing, so as to improve the recognition accuracy when abnormal image data is identified based on the image recognition algorithm.

[0078] like Figure 3b As shown, it is a flow chart of the preprocessing method of raw image data, which includes the following steps:

[0079] Step S3021: Based on the type of the image sensor, obtain configuration parameters corresponding to the image sensor.

[0080] Specifically, the on-board processor can periodically obtain configuration parameters corresponding to different image sensors from the cloud server, or obtain configuration parameters from the cloud server when the image sensor is installed and started. The cloud server can also periodically or dynamically send configuration parameters corresponding to each image sensor to the on-board processor.

[0081] Furthermore, the configuration parameters are obtained by the onboard processor from the cloud server.

[0082] Specifically, the cloud server determines the corresponding configuration parameters based on the built-in parameter characteristics of different image sensors configured when they are produced by corresponding manufacturers and the characteristics of abnormal image data that need to be identified.

[0083] For example, if the abnormal image data to be identified is the license plate number of a passing vehicle, the image sensor needs to be adjusted to a state with an extremely short exposure time, and there needs to be requirements for the clarity of the collected original image data, but the image size of the abnormal image data needs to be smaller. At this time, the corresponding configuration parameters can be determined based on requirements such as limiting the size of the abnormal image data and ensuring its clarity and brightness.

[0084] Furthermore, the cloud server is used to obtain a development toolkit from a sensor server corresponding to the image sensor based on a communication protocol corresponding to the image sensor, and determine configuration parameters corresponding to the image sensor.

[0085] Specifically, the manufacturer corresponding to each image sensor will provide a corresponding software development kit (SDK). The cloud server can obtain the corresponding development kit from the sensor server based on the communication protocol corresponding to the image sensor and the communication address of the sensor server, so as to determine the characteristics of the original image data (such as the built-in parameters of the image sensor) according to the development kit, and then determine the configuration parameters.

[0086] Furthermore, the configuration parameters include an IP address corresponding to the image sensor, an alarm type for identification, and a type of image data to be collected.

[0087] Specifically, since each image sensor is configured by the manufacturer to send raw image data to a sensor server with a specific IP address for processing, it is necessary to send the IP address corresponding to each image sensor to the on-board processor to obtain the raw image data uploaded by the image sensor based on the IP address.

[0088] Therefore, the IP address in the configuration parameters is usually not updated after the type of the image sensor is determined.

[0089] The alarm type used for identification is the type corresponding to the abnormal data image that needs to be identified from the original image data, such as face image, license plate image, etc., so that the image recognition algorithm can perform targeted identification of the original image data corresponding to the image sensor based on the alarm type.

[0090] The type of image data to be collected is the file format into which the original image data needs to be converted when the original image is preprocessed (because the original image data obtained by different image sensors may have different formats, before targeted recognition based on the image recognition algorithm, these original image data need to be converted into a unified format.

[0091] In some embodiments, the alarm type and image data type in the configuration parameters will be dynamically updated by the cloud server and sent to the vehicle processor to be adjusted according to the tasks that the cloud server needs to process and the image information that needs to be recognized. This allows the unmanned vehicle and image sensor to be applicable to different types of image acquisition tasks, expands the scope and scenarios of unmanned vehicles, and improves versatility.

[0092] Step S3022: pre-process the original image data based on the development toolkit and configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data.

[0093] Specifically, the on-board processor will pre-process the raw image data according to the configuration parameters sent by the cloud server so that it can be subsequently recognized through the image recognition algorithm.

[0094] Step S303: identifying abnormal image data in the processed image data based on an image recognition algorithm.

[0095] Specifically, after the original image data is preprocessed, processed image data is obtained, and the processed image data is recognized based on the image recognition algorithm.

[0096] Since different image sensors correspond to different alarm types, it is necessary to identify corresponding types of abnormal image data from the processed image data corresponding to each image sensor, rather than directly identifying all types of abnormal image data from all processed image data, so as to improve the accuracy and efficiency of image recognition processing.

[0097] Furthermore, the on-board processor stores a reference alarm image sent by the cloud server, and the reference alarm image corresponds to the alarm type.

[0098] Specifically, the on-board processor includes an image database for storing reference alarm images sent by the cloud server, and each reference alarm image is for a specific type of alarm, such as a specific facial image that needs to be identified (such as a photo of a criminal suspect).

[0099] In some embodiments, the cloud server dynamically sends reference alarm images to the on-board processor to update the image database in the on-board processor to ensure the flexibility and accuracy of abnormal image recognition based on the reference alarm images.

[0100] Furthermore, if Figure 3c As shown, it is a flow chart of a method for identifying abnormal image data, which includes the following steps:

[0101] Step S3031: Based on the image recognition algorithm, determine the similarity between the processed image data and the reference alarm image.

[0102] Specifically, based on the type of image sensor corresponding to the processed image data, the on-board processor will determine the type of alarm that needs to be identified from the processed image data, and then determine the corresponding reference alarm image in the image database, and then determine whether there is abnormal image data by comparing the processed image data with these reference alarm images.

[0103] Step S3032: Based on the similarity, determine abnormal image data from the processed image data.

[0104] Specifically, determining whether the processed image data is abnormal image data can be achieved based on the similarity between images. If the similarity between the processed image data and a reference alarm image is greater than a set threshold, the processed image data can be considered to be abnormal image data, thereby obtaining abnormal image data from the processed image data.

[0105] In some embodiments, the identification of abnormal image data based on similarity can be as follows: if the similarity between the processed image data and all reference alarm images is less than a set value, the processed image data is determined as irrelevant image data; then the processed image data other than the irrelevant image data is determined as abnormal image data.

[0106] Specifically, since the reference alarm images may be relatively similar, it is possible that a processed image data is similar to multiple reference alarm images at the same time. At this time, although it cannot be clearly determined that the processed image data corresponds to each reference alarm image, the processed image data can also be determined as abnormal image data.

[0107] In contrast, if a processed image data is not similar to any reference alarm image, it can be regarded as irrelevant image data and directly filtered out to reduce the amount of data transmitted to the cloud server.

[0108] At the same time, if other processed image data after filtering out irrelevant image data are at least similar to a reference alarm image, then these processed image data can be directly uploaded to the cloud server for subsequent processing.

[0109] Step S304, uploading the abnormal image data to the cloud server.

[0110] Specifically, by determining abnormal image data on the on-board processor and then uploading it to the cloud server, rather than having each sensor server process it separately and then upload it to the cloud server, the time required for data transmission between servers is reduced, thereby significantly improving the operation and maintenance efficiency and accuracy of the cloud server, and effectively avoiding interference from useless images and false alarm information.

[0111] The image information acquisition method provided by the disclosed embodiment sends configuration parameters to the vehicle-mounted processor through the cloud server. The vehicle-mounted processor pre-processes the raw image data collected by different types of image sensors based on the configuration parameters, and then identifies the abnormal image data based on the image recognition algorithm and uploads it to the cloud server. As a result, it is not limited by the type of image sensor, and the vehicle-mounted processor uniformly completes the pre-processing of the raw image data, thereby improving the freedom and flexibility of image sensor selection. At the same time, it can be applied to the configuration of image sensors of multiple categories and brands, improving the production flexibility of unmanned vehicles. In addition, only the abnormal image data is uploaded to the cloud server, which can greatly reduce the amount of junk data uploaded to the cloud, thereby significantly reducing the operation and maintenance workload of the cloud server and improving the overall information processing efficiency and accuracy.

[0112] Figure 4 This is a schematic diagram of the structure of an image information acquisition device provided by an embodiment of the present disclosure. Figure 4As shown, the image information acquisition device 400 is applied to a vehicle-mounted processor, and includes: an acquisition module 410, a recognition module 420 and a processing module 430. Among them:

[0113] An acquisition module 410 is used to acquire raw image data collected by an image sensor, and there are at least two types of image sensors;

[0114] An identification module 420, configured to identify abnormal image data from the original image data based on configuration parameters corresponding to the image sensor, wherein the configuration parameters correspond to the type of the image sensor;

[0115] The processing module 430 is used to upload the abnormal image data to the cloud server.

[0116] Optionally, the identification module 420420 is specifically used to identify abnormal image data from the original image data based on the configuration parameters corresponding to the image sensor, including: preprocessing the original image data based on the configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data, the preprocessing including image size normalization; based on the image recognition algorithm, identifying abnormal image data in the processed image data.

[0117] Optionally, the identification module is specifically used to obtain configuration parameters corresponding to the image sensor based on the type of the image sensor; based on the development toolkit and configuration parameters corresponding to the image sensor, pre-process the original image data to obtain processed image data corresponding to the original image data.

[0118] Optionally, the identification module 420 specifically includes configuration parameters obtained by the vehicle-mounted processor from the cloud server.

[0119] Optionally, the identification module 420 specifically includes: the cloud server is used to obtain a development toolkit from a sensor server corresponding to the image sensor based on a communication protocol corresponding to the image sensor, and determine configuration parameters corresponding to the image sensor.

[0120] Optionally, the identification module 420 specifically includes configuration parameters including an IP address corresponding to the image sensor, an alarm type for identification, and a type of image data to be collected.

[0121] Optionally, the identification module 420 specifically includes: a reference alarm image sent by a cloud server is stored in the vehicle-mounted processor, and the reference alarm image corresponds to the alarm type.

[0122] Optionally, the recognition module 420 is specifically configured to determine, based on an image recognition algorithm, the similarity between the processed image data and the reference alarm image; and determine abnormal image data from the processed image data based on the similarity.

[0123] Optionally, the identification module 420 is specifically configured to determine the processed image data as irrelevant image data if the similarity between the processed image data and all reference alarm images is less than a set value; and determine the processed image data other than the irrelevant image data as abnormal image data.

[0124] The principles and technical effects of the image information acquisition device have been fully described in the aforementioned embodiments and will not be repeated here.

[0125] Figure 5 A schematic diagram of the structure of a control device provided by an embodiment of the present disclosure, such as Figure 5 As shown, the control device 500 includes: a memory 510 and a processor 520 .

[0126] The memory 510 stores a computer program that can be executed by at least one processor 520. The computer program is executed by at least one processor 520 to enable the control device to implement the material removal method provided in any of the above embodiments or the image information acquisition method provided in any of the above embodiments.

[0127] The memory 510 and the processor 520 may be connected via a bus 530 .

[0128] The relevant instructions can be understood by referring to the relevant descriptions and effects corresponding to the method embodiments, which will not be repeated here.

[0129] The relevant instructions can be understood by referring to the relevant descriptions and effects corresponding to the method embodiments, which will not be repeated here.

[0130] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement a material removal method as provided in any of the above method embodiments or an image information acquisition method as provided in any of the above embodiments.

[0131] Among them, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0132] An embodiment of the present disclosure provides a computer program product, which includes computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the material removal method in the above method embodiment or the image information acquisition method provided in any of the above embodiments.

[0133] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0134] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0135] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for collecting image information, characterized in that: Applied to an on-board processor, the image information acquisition method includes: Acquire raw image data collected by an image sensor, wherein the image sensor has at least two types; Based on configuration parameters corresponding to the image sensor, abnormal image data is identified from the original image data, wherein the configuration parameters correspond to the type of the image sensor; The abnormal image data is uploaded to a cloud server.

2. The method according to claim 1, characterized in that: The identifying abnormal image data from the original image data based on the configuration parameters corresponding to the image sensor includes: Preprocessing the original image data based on configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data, wherein the preprocessing includes image size normalization processing; Based on an image recognition algorithm, abnormal image data in the processed image data is identified.

3. The method according to claim 2, characterized in that The preprocessing of the original image data based on the configuration parameters corresponding to the image sensor to obtain processed image data corresponding to the original image data includes: Based on the type of the image sensor, acquiring configuration parameters corresponding to the image sensor; Based on the development toolkit corresponding to the image sensor and the configuration parameters, the raw image data is preprocessed to obtain processed image data corresponding to the raw image data.

4. The method according to claim 1, characterized in that: The configuration parameters are obtained by the on-board processor from the cloud server.

5. The method according to claim 4, characterized in that The cloud server is used to obtain a development toolkit from a sensor server corresponding to the image sensor based on a communication protocol corresponding to the image sensor, and determine configuration parameters corresponding to the image sensor.

6. The method according to any one of claims 2 to 5, characterized in that The configuration parameters include the IP address corresponding to the image sensor, the alarm type used for identification, and the type of image data to be collected.

7. The method according to claim 6, characterized in that The vehicle-mounted processor stores a reference alarm image sent by the cloud server, and the reference alarm image corresponds to the alarm type.

8. The method according to claim 7, characterized in that The step of identifying abnormal image data in the processed image data based on an image recognition algorithm includes: Based on an image recognition algorithm, determining the similarity between the processed image data and a reference alarm image; Based on the similarity, the abnormal image data is determined from the processed image data.

9. The method according to claim 8, characterized in that The determining the abnormal image data from the processed image data based on the similarity comprises: If the similarity between the processed image data and all reference alarm images is less than a set value, the processed image data is determined as irrelevant image data; The processed image data other than the irrelevant image data is determined as the abnormal image data.

10. An image information acquisition device, characterized in that: Applied to an on-board processor, the image information acquisition device comprises: An acquisition module, used to acquire raw image data collected by an image sensor, wherein the image sensor has at least two types; an identification module, configured to identify abnormal image data from the original image data based on configuration parameters corresponding to the image sensor, wherein the configuration parameters correspond to the type of the image sensor; The processing module is used to upload the abnormal image data to a cloud server.

11. A control device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the control device to perform the image information acquisition method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the image information acquisition method according to any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product comprises computer-executable instructions, which are used to implement the image information acquisition method according to any one of claims 1 to 9 when executed by a processor.

Images