A method, system, device and readable storage medium for adjusting vehicle speed

Abstract

This invention provides a vehicle speed adjustment method, system, device, and readable storage medium, relating to the field of autonomous driving vehicle speed control technology. The method includes acquiring first information and second information. The first information includes distance information between a first vehicle and a target object, wherein the first vehicle is a vehicle in autonomous driving mode, and the second information includes weather condition information. The method further involves determining whether the first information contains errors based on the weather condition information, obtaining a judgment result, wherein if the judgment result indicates the presence of errors, first image information is acquired. The method also involves determining the actual distance between the first vehicle and the target object based on the weather condition information and the first image information; generating a target vehicle speed based on the actual distance between the first vehicle and the target object; and adjusting the speed of the first vehicle based on the target vehicle speed. This invention achieves accurate distance measurement under different weather conditions to generate a target speed for adjusting the vehicle speed.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving speed control technology, and more specifically, to a speed adjustment method, system, device, and readable storage medium. Background Technology

[0002] Currently, autonomous driving technology is becoming increasingly mature, and its intelligence level is also getting higher and higher. When autonomous driving is carried out in abnormal weather, the weather conditions will cause errors in the data collected by the in-vehicle sensors, which may lead to misjudgment of the distance between the vehicle and obstacles, resulting in safety accidents. Therefore, there is an urgent need for a vehicle speed adjustment method that can adjust the vehicle speed before the vehicle is taken over by humans in order to avoid safety accidents. Summary of the Invention

[0003] The purpose of this invention is to provide a vehicle speed adjustment method, system, device, and readable storage medium to improve the above-mentioned problems.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] On one hand, embodiments of this application provide a method for adjusting vehicle speed, the method comprising:

[0006] Acquire first information and second information. The first information includes distance information between a first vehicle and a target object. The first vehicle is a vehicle in autonomous driving mode, and the target object is an obstacle within the detection range of the first vehicle. The second information includes weather condition information.

[0007] Based on the weather conditions information, it is determined whether there is an error in the first information, and a judgment result is obtained. If the judgment result is that there is an error, the first image information is obtained. The first image information is an image of the target object taken by the vehicle-mounted device under the current weather conditions.

[0008] The actual distance between the first vehicle and the target is determined based on the weather conditions information and the first image information;

[0009] The target vehicle speed is generated based on the actual distance between the first vehicle and the target object;

[0010] The speed of the first vehicle is adjusted according to the target speed.

[0011] Secondly, embodiments of this application provide a vehicle speed adjustment system, the system comprising:

[0012] The acquisition module is used to acquire first information and second information. The first information includes distance information between a first vehicle and a target object. The first vehicle is a vehicle in an autonomous driving state, and the target object is an obstacle within the detection range of the currently driving vehicle. The second information includes weather condition information.

[0013] The judgment module is used to judge whether there is an error in the first information based on the weather condition information and obtain a judgment result. If the judgment result is that there is an error, the first image information is obtained. The first image information is a target image taken by the vehicle-mounted device under the current weather conditions.

[0014] The first processing module is used to determine the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information.

[0015] The second processing module is used to generate a target vehicle speed based on the actual distance between the first vehicle and the target object;

[0016] The adjustment module is used to adjust the speed of the first vehicle according to the target vehicle speed.

[0017] Thirdly, embodiments of this application provide a vehicle speed adjustment device, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the above-described vehicle speed adjustment method.

[0018] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described vehicle speed adjustment method.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention uses weather conditions to determine whether there is an error in the distance information between a first vehicle and a target object. When the weather is normal, the distance information collected by the sensor is error-free; when the weather is abnormal, the distance information collected by the sensor is error-free. This effectively takes into account the impact of weather on the vehicle's sensor ranging. In abnormal weather, the actual distance between the first vehicle and the target object is determined based on different weather conditions, effectively improving the ranging accuracy of the vehicle in different weather scenarios. This allows for the generation of an accurate target speed to adjust the vehicle's speed, avoiding safety accidents caused by using autonomous driving in abnormal weather.

[0021] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the vehicle speed adjustment method described in an embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the vehicle speed adjustment system described in an embodiment of the present invention.

[0025] Figure 3 This is a schematic diagram of the vehicle speed adjustment device described in an embodiment of the present invention.

[0026] The diagram is labeled as follows: 1. Acquisition module; 2. Judgment module; 3. First processing module; 4. Second processing module; 5. Adjustment module; 800. Vehicle speed adjustment device; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides a vehicle speed adjustment method. It can be understood that a scenario can be set up in this embodiment, such as: a vehicle in autonomous driving mode under abnormal weather conditions, where there are obstacles within its detection range, and the driver needs to take over the vehicle before a safety accident occurs.

[0031] See Figure 1 The figure shows that the method includes steps S1, S2, S3, S4, and S5, which are specifically as follows:

[0032] Step S1: Obtain first information and second information. The first information includes distance information between the first vehicle and the target object. The first vehicle is a vehicle in autonomous driving mode, and the target object is an obstacle within the detection range of the first vehicle. The second information includes weather condition information.

[0033] In this step, when the first vehicle is in autonomous driving mode, the initial distance between the first vehicle and the target object can be measured through the vehicle's onboard equipment, such as lidar. Weather condition information includes normal weather conditions and abnormal weather conditions. Normal weather conditions are sunny days, and abnormal weather conditions include rainy days, foggy days, etc.

[0034] It is understood that step S1 includes steps S11, S12, and S13, specifically as follows:

[0035] Step S11: Obtain second image information, wherein the second image information is a current weather image captured by the vehicle-mounted device;

[0036] In this step, the vehicle-mounted equipment takes pictures of the environment around the first vehicle to obtain the current weather image, which can be used to determine the current weather.

[0037] Step S12: Send the second image information to a convolutional neural network for feature extraction to obtain the first feature information;

[0038] It is understood that step S12 includes steps S121, S122, S123, S124, and S125, specifically as follows:

[0039] Step S121: Segment the second image information to obtain third image information and fourth image information. The third image information is a sky image under the current weather conditions, and the fourth image information is a road image under the current weather conditions.

[0040] In this step, the sky image and road surface image of the current environment are obtained by segmenting the second image information for subsequent processing.

[0041] Step S122: Send the second image information to the computer vision model to obtain the second feature information;

[0042] In this step, the computer vision model is the Mobilenet model. The global features of the second image information, i.e., the second feature information, are extracted by sending the second image information to the Mobilenet model. It can be understood that the Mobilenet model itself is a lightweight network result, and its construction process is a technical solution well known to those skilled in the art, so it will not be described in detail here.

[0043] Step S123: Send the third image information to the first convolutional neural network to obtain the third feature information;

[0044] In this step, the sky features in the weather image are extracted by sending the third image information to the first convolutional neural network.

[0045] It is understood that step S123 includes steps S1231 and S1232, which are specifically as follows:

[0046] Step S1231: Send the third image information to the convolutional layer to obtain the first feature vector;

[0047] In this step, the third image information obtained after segmenting the second image information is sent to the convolutional layer for downsampling to obtain the first feature vector. The size of the convolutional layer is 3×3, the number of convolutional kernels is 32, and the stride is 2×1.

[0048] Step S1232: Send the first feature vector to the depthwise separable convolutional layer to obtain the third feature information.

[0049] In this step, the depthwise separable convolutional layer includes four sets of depthwise separable convolutions, where the stride of each depthwise convolution is 2 and the stride of each pointwise convolution is 1. By sending the first feature vector to the four sets of depthwise separable convolutions for downsampling, the third feature information is obtained. By replacing the traditional standard convolution with depthwise separable convolutions, the network depth is increased while the number of model parameters is reduced, which greatly improves the computing speed and the efficiency of weather condition recognition.

[0050] Step S124: Send the fourth image information to the second convolutional neural network to obtain the fourth feature information;

[0051] In this step, the road surface features in the weather image are extracted by sending the fourth image information to the second convolutional neural network. It should be noted that the first and second convolutional neural networks have the same structure.

[0052] Step S125: Send the second feature information, the third feature information and the fourth feature information to the fusion layer for fusion to obtain the first feature information.

[0053] In this step, the Concatenate function can be used to fuse the second, third, and fourth feature information. By fusing sky features, road surface features, and global features in weather images using the Concatenate function, the expressive power of the network can be greatly improved, thus enhancing the accuracy of weather recognition.

[0054] Step S13: Send the first feature information to the classification layer to obtain the weather condition information.

[0055] In this step, the classification layer is a softmax classifier. After fusing the sky features, road features, and global features of the weather image to obtain the first feature information, it is then downsampled through a global average pooling layer to obtain a feature map. Finally, the weather map is identified through the softmax classifier to obtain weather condition information.

[0056] Step S2: Determine whether there is an error in the first information based on the weather condition information, and obtain a determination result. If the determination result is that there is an error, then obtain the first image information, which is an image of the target object taken by the vehicle-mounted device under the current weather conditions.

[0057] In this step, due to the potential for errors in target distance acquisition by lidar under abnormal weather conditions—for example, raindrops attenuate the laser signal emitted by the lidar during rainy weather, and multiple reflections from the laser signal result in a received signal containing multiple reflected signals—the depth information obtained by lidar ranging becomes complex, making it difficult to accurately identify and separate target objects. Using lidar for ranging in such conditions can easily lead to misjudgments of the distance to obstacles, causing safety accidents. Therefore, weather conditions are used to determine if there is an error in the initial information. When the weather conditions are normal, the determination is that there is no error, and lidar ranging can be used. When the weather conditions are abnormal, the determination is that there is an error, and lidar ranging cannot be used. In this case, the initial image information needs to be acquired for subsequent processing to accurately measure the actual distance between the vehicle and the target object, preventing safety accidents.

[0058] Step S3: Determine the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information;

[0059] It is understood that step S3 includes steps S31, S32, and S33, specifically as follows:

[0060] Step S31: When the weather conditions are rainy, the first image information is processed using wavelet transform to obtain the fifth image information, which includes the high-frequency region image in the first image information.

[0061] In this step, the wavelet mother function is expressed as:

[0062]

[0063] Where a is the scaling factor and b is the translation factor, the one-dimensional discrete wavelet expression is obtained by discretizing the scaling factor a and the translation factor b of the wavelet mother function:

[0064]

[0065] By performing one-dimensional discrete wavelet transforms on the rows and columns of the image respectively, we can obtain the two-dimensional wavelet transform of the image:

[0066]

[0067] Where ψ(x,y) is a separable scale and direction function, W ψThe scaling function and the direction function are defined as follows: when j is 0, it represents detailed features in the horizontal direction H; when j is 1, it represents detailed features in the vertical direction V; and when j is 2, it represents detailed features in the diagonal direction D. After performing a two-dimensional wavelet transform on the first image information, each level of decomposition divides the original image into four frequency bands. H, V, and D are high-frequency sub-bands that reflect the detailed content of the image, while L is the low-frequency part that includes the overall features of the image. At the same time, six high-frequency coefficients and one low-frequency coefficient are obtained. Since raindrop traces in the weather image exist in the high-frequency region of the image, the high-frequency coefficients corresponding to the three high-frequency sub-bands H, V, and D are selected. The extracted high-frequency coefficients are then subjected to an inverse wavelet transform to obtain the high-frequency region image of the image, i.e., the fifth image information.

[0068] Step S32: Send the fifth image information to the first enhancement model to obtain the sixth image information. The first enhancement model is used to remove the interference of rain on the image.

[0069] In this step, the first enhancement model has a nine-layer structure, where the first layer is a convolutional layer, the second layer is a batch normalization layer, the third to seventh layers are five densely connected residual blocks, the eighth layer is a convolutional layer, and the ninth layer is a batch normalization layer. By processing the fifth image information through the first enhancement model, the interference of raindrops on the image can be removed. By constructing the above network structure, the design advantages of dense convolutional network structure are fully utilized, so that the feature information extracted by different convolutional layers of the same image is utilized to the greatest extent. The design advantages of residual network are also fully utilized, reducing the training time of the model.

[0070] Step S33: Determine the actual distance between the first vehicle and the target object based on the sixth image information.

[0071] In this step, determining the actual distance between the first vehicle and the target object using the sixth image information is a technical solution well-known to those skilled in the art, and therefore will not be elaborated here.

[0072] It is understood that step S3 further includes steps S34, S35, S36, and S37, which are specifically as follows:

[0073] Step S34: When the weather conditions are foggy, the first image information is processed using a high-pass filtering algorithm to obtain the dark channel image corresponding to the first image information.

[0074] In this step, instead of using the traditional dark channel algorithm to obtain the dark channel image, a high-pass filtering algorithm is used to replace the dark channel prior algorithm as the scheme for extracting the dark channel image. This approach can retain the learning advantages of prior knowledge algorithms while combining the advantages of deep learning algorithms.

[0075] Step S35: Process the first image information and the dark channel image corresponding to the first image information to obtain the seventh image information;

[0076] In this step, subtracting the dark channel image corresponding to the first image information from the first image information yields the preliminary dehazed image, i.e., the seventh image information.

[0077] Step S36: Send the seventh image information to the second enhancement model to obtain the eighth image information. The second enhancement model is used to remove the interference of fog on the image.

[0078] In this step, the second enhancement model consists of 8 densely connected residual blocks, which can speed up the overall training of the network and effectively prevent overfitting. By sending the seventh image information to the second enhancement model, the interference of fog on the image can be removed.

[0079] Step S37: Determine the actual distance between the first vehicle and the target object based on the eighth image information.

[0080] Step S4: Generate the target vehicle speed based on the actual distance between the first vehicle and the target object;

[0081] It is understood that step S4 includes steps S41, S42, and S43, specifically as follows:

[0082] Step S41: Obtain takeover time and safe distance information, wherein the takeover time includes the time required for the driver to take over the driving authority of the vehicle;

[0083] In this step, since the weather conditions are abnormal, the takeover time is the maximum takeover time in the history, and the safety distance information is the safety distance set between the first vehicle and the target object, which is a preset value.

[0084] Step S42: Determine the safe takeover distance based on the actual distance between the first vehicle and the target object and the safe distance information;

[0085] In this step, the safe takeover distance can be obtained by subtracting the safe distance information from the actual distance between the first vehicle and the target object.

[0086] Step S43: Calculate the target vehicle speed based on the safe takeover distance and the takeover time.

[0087] In this step, the target vehicle speed can be obtained by dividing the safe takeover distance by the takeover time.

[0088] Step S5: Adjust the speed of the first vehicle according to the target vehicle speed.

[0089] In this step, by adjusting the current vehicle speed to the target speed, the driver can take over the vehicle before the distance between the first vehicle and the target object becomes less than the safe distance, thus enabling the driver to respond to emergencies and avoid accidents.

[0090] Example 2:

[0091] like Figure 2 As shown, this embodiment provides a vehicle speed adjustment system, which includes an acquisition module 1, a judgment module 2, a first processing module 3, a second processing module 4, and an adjustment module 5, specifically:

[0092] The acquisition module 1 is used to acquire first information and second information. The first information includes distance information between a first vehicle and a target object. The first vehicle is a vehicle in an autonomous driving state, and the target object is an obstacle within the detection range of the currently driving vehicle. The second information includes weather condition information.

[0093] The judgment module 2 is used to judge whether there is an error in the first information based on the weather condition information and obtain a judgment result. If the judgment result is that there is an error, the first image information is obtained. The first image information is a target image taken by the vehicle-mounted device under the current weather conditions.

[0094] The first processing module 3 is used to determine the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information.

[0095] The second processing module 4 is used to generate a target vehicle speed based on the actual distance between the first vehicle and the target object;

[0096] The adjustment module 5 is used to adjust the speed of the first vehicle according to the target vehicle speed.

[0097] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0098] Example 3:

[0099] Corresponding to the above method embodiments, this embodiment also provides a vehicle speed adjustment device. The vehicle speed adjustment device described below and the vehicle speed adjustment method described above can be referred to each other.

[0100] Figure 3 This is a block diagram illustrating a vehicle speed adjustment device 800 according to an exemplary embodiment. For example... Figure 3As shown, the vehicle speed adjustment device 800 may include: a processor 801 and a memory 802. The vehicle speed adjustment device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0101] The processor 801 controls the overall operation of the vehicle speed adjustment device 800 to complete all or part of the steps in the aforementioned vehicle speed adjustment method. The memory 802 stores various types of data to support the operation of the vehicle speed adjustment device 800. This data may include, for example, instructions for any application or method operating on the vehicle speed adjustment device 800, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the vehicle speed adjustment device 800 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0102] In an exemplary embodiment, the vehicle speed adjustment device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the vehicle speed adjustment method described above.

[0103] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the vehicle speed adjustment method described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the vehicle speed adjustment device 800 to complete the vehicle speed adjustment method described above.

[0104] Example 4:

[0105] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the vehicle speed adjustment method described above.

[0106] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the vehicle speed adjustment method described in the above method embodiments.

[0107] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0108] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0109] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for adjusting vehicle speed, characterized in that, include: Acquire first information and second information. The first information includes distance information between a first vehicle and a target object. The first vehicle is a vehicle in autonomous driving mode, and the target object is an obstacle within the detection range of the first vehicle. The second information includes weather condition information. Based on the weather conditions information, it is determined whether there is an error in the first information, and a judgment result is obtained. If the judgment result is that there is an error, the first image information is obtained. The first image information is an image of the target object taken by the vehicle-mounted device under the current weather conditions. The actual distance between the first vehicle and the target is determined based on the weather conditions information and the first image information; The target vehicle speed is generated based on the actual distance between the first vehicle and the target object; The speed of the first vehicle is adjusted according to the target speed.

2. The vehicle speed adjustment method according to claim 1, characterized in that, Obtaining the second information includes: Acquire second image information, which is a current weather image captured by the vehicle-mounted device; The second image information is sent to a convolutional neural network for feature extraction to obtain the first feature information; The first feature information is sent to the classification layer to obtain the weather condition information.

3. The vehicle speed adjustment method according to claim 2, characterized in that, The second image information is sent to a convolutional neural network for feature extraction to obtain the first feature information, including: The second image information is segmented to obtain a third image information and a fourth image information. The third image information is a sky image under the current weather conditions, and the fourth image information is a road image under the current weather conditions. The second image information is sent to the computer vision model to obtain the second feature information; The third image information is sent to the first convolutional neural network to obtain the third feature information; The fourth image information is sent to the second convolutional neural network to obtain the fourth feature information; The second feature information, the third feature information, and the fourth feature information are sent to the fusion layer for fusion to obtain the first feature information.

4. The vehicle speed adjustment method according to claim 3, characterized in that, The third image information is sent to the first convolutional neural network to obtain the third feature information, including: The third image information is sent to the convolutional layer to obtain the first feature vector; The first feature vector is sent to a depthwise separable convolutional layer to obtain the third feature information.

5. The vehicle speed adjustment method according to claim 1, characterized in that, Determining the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information includes: When the weather conditions are rainy, wavelet transform is used to process the first image information to obtain the fifth image information, which includes the high-frequency region image in the first image information. The fifth image information is sent to the first enhancement model to obtain the sixth image information. The first enhancement model is used to remove the interference of rain on the image. The actual distance between the first vehicle and the target object is determined based on the sixth image information.

6. The vehicle speed adjustment method according to claim 1, characterized in that, Determining the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information includes: When the weather conditions are foggy, the first image information is processed using a high-pass filtering algorithm to obtain the dark channel image corresponding to the first image information; The first image information and the dark channel image corresponding to the first image information are processed to obtain the seventh image information; The seventh image information is sent to the second enhancement model to obtain the eighth image information. The second enhancement model is used to remove the interference of fog on the image. The actual distance between the first vehicle and the target object is determined based on the eighth image information.

7. The vehicle speed adjustment method according to claim 1, characterized in that, Generating a target vehicle speed based on the actual distance between the first vehicle and the target object includes: Acquire takeover time and safe distance information, wherein the takeover time includes the time required for the driver to take over the driving authority of the vehicle; The safe takeover distance is determined based on the actual distance between the first vehicle and the target object and the safe distance information; The target vehicle speed is calculated based on the safe takeover distance and the takeover time.

8. A vehicle speed adjustment system, characterized in that, include: The acquisition module is used to acquire first information and second information. The first information includes distance information between a first vehicle and a target object. The first vehicle is a vehicle in an autonomous driving state, and the target object is an obstacle within the detection range of the currently driving vehicle. The second information includes weather condition information. The judgment module is used to judge whether there is an error in the first information based on the weather condition information and obtain a judgment result. If the judgment result is that there is an error, the first image information is obtained. The first image information is a target image taken by the vehicle-mounted device under the current weather conditions. The first processing module is used to determine the actual distance between the first vehicle and the target object based on the weather conditions information and the first image information. The second processing module is used to generate a target vehicle speed based on the actual distance between the first vehicle and the target object; The adjustment module is used to adjust the speed of the first vehicle according to the target vehicle speed.

9. A vehicle speed adjustment device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the vehicle speed adjustment method as described in any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the vehicle speed adjustment method as described in any one of claims 1 to 7.

Images