Nighttime driving visual assistance method and related equipment

Abstract

The embodiment of the present invention provides a nighttime driving visual assistance method, comprising: when driving at night, acquiring a vehicle front image in real time, and detecting the light intensity of the vehicle front image; when detecting that the light intensity in the vehicle front image is greater than a first preset value, processing the vehicle front image through a preset light intensity processing model, so that the light intensity of the processed vehicle front image is less than the light intensity in the vehicle front image; sending the processed vehicle front image to a head-up display system, and projecting the processed vehicle front image to a designated position on the windshield through the head-up display system for display. This allows the driver to meet other vehicles by observing the display content at the designated position on the windshield when the light intensity in front of the vehicle is strong, thereby reducing the danger of oncoming vehicles with strong lights when meeting other vehicles at night, thereby improving the safety of nighttime driving.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving, and in particular to a nighttime driving visual assistance method and related equipment. Background Art

[0002] With the development of society, more and more roads are being built. Cars have become the transportation choice for most families. While it brings convenience, it also brings difficulties to traffic management. For example, when driving at night, a large number of lights are used to illuminate the road. The light intensity of high beams is high, but it will interfere with the vision of drivers of oncoming vehicles, which is easy to affect traffic safety driving. Because the driver of the oncoming vehicle is not paying attention or is too focused on driving, there may be improper use of high beams, which will interfere with the vision of the driver on the other side, thereby increasing the degree of danger of nighttime traffic. Summary of the invention

[0003] The embodiment of the present invention provides a nighttime driving visual assistance method and related equipment, which can detect the light intensity of an oncoming vehicle through an image in front of the vehicle when driving at night. When the light intensity in the image in front of the vehicle is relatively high, the image in front of the vehicle is processed to obtain an image with relatively low light intensity, and the image with relatively low light intensity is projected to a designated position on the windshield for display through a head-up display system, so that when the light intensity in front of the vehicle is relatively high, the driver of the own vehicle can meet the vehicle by observing the display content at the designated position on the windshield, thereby reducing the danger of oncoming vehicles with relatively strong lights when meeting at night, thereby improving the safety of driving at night.

[0004] In a first aspect, an embodiment of the present invention provides a nighttime driving visual assistance method, the method comprising:

[0005] When driving at night, real-time acquisition of the image in front of the vehicle and detection of the light intensity of the image in front of the vehicle are performed;

[0006] When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle;

[0007] The processed image in front of the vehicle is sent to a head-up display system, and the head-up display system projects the processed image in front of the vehicle onto a designated position on a windshield for display.

[0008] Optionally, the detecting of light intensity of the image in front of the vehicle includes:

[0009] Segmenting the image in front of the vehicle according to a preset ratio to obtain a corresponding number of segmented images;

[0010] The segmented image is input into a preset light intensity detection model, and the light intensity detection result of the image in front of the vehicle is obtained through processing by the light intensity detection model.

[0011] Optionally, segmenting the image in front of the vehicle according to a preset ratio to obtain a corresponding number of segmented images includes:

[0012] Tiling the image in front of the vehicle through a 10*10 grid;

[0013] Segment the image in front of the vehicle using the 6*6 area in the upper left corner as the first segmentation area to obtain a first segmentation image;

[0014] The lower left corner 6*6 of the image in front of the vehicle is segmented as the second segmentation area to obtain a second segmentation image;

[0015] Segment the image in front of the vehicle using the 6*6 area in the upper right corner as the third segmentation area to obtain a third segmentation image;

[0016] The lower right corner 6*6 of the image in front of the vehicle is used as the fourth segmentation area for segmentation to obtain a fourth segmentation image.

[0017] Optionally, the step of inputting the segmented image into a preset light intensity detection model and obtaining a light intensity detection result of the image in front of the vehicle through processing by the light intensity detection model includes:

[0018] The first segmented image, the second segmented image, the third segmented image and the fourth segmented image are simultaneously input into the preset light intensity detection model, and the light intensity detection results of the first segmented image, the second segmented image, the third segmented image and the fourth segmented image are obtained by processing with the preset light intensity detection model.

[0019] Optionally, when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, processing the image in front of the vehicle by using a preset light intensity processing model includes:

[0020] When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, an image to be processed is obtained according to the detection result, and the image to be processed is at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, in which the light intensity is greater than the first preset value;

[0021] The image to be processed is input into a preset light intensity processing model, and the image to be processed is processed by the preset light intensity processing model to obtain a target image corresponding to the image to be processed, wherein the light intensity of the target image is less than a first preset value.

[0022] Optionally, the preset light intensity processing model includes an image generation network, and the step of inputting the image to be processed into the preset light intensity processing model, processing the image to be processed by the preset light intensity processing model, and obtaining a target image corresponding to the image to be processed includes:

[0023] The image to be processed is input into a preset light intensity processing model, and a target image corresponding to the image to be processed is generated through an image generation network in the preset light intensity processing model.

[0024] Optionally, before sending the processed image in front of the vehicle to a head-up display system and projecting the processed image in front of the vehicle to a designated position on a windshield for display by the head-up display system, the method further includes:

[0025] When it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, a display area image is obtained according to the detection result, and the display area image is the one with the light intensity less than the second preset value and the smallest light intensity among the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, and the second preset value is less than the first preset value;

[0026] A designated position on the windshield is determined according to the position of the display area image in the vehicle front image.

[0027] In a second aspect, an embodiment of the present invention provides a nighttime driving visual aid device, the device comprising:

[0028] An acquisition module is used to acquire the image in front of the vehicle in real time when driving at night, and to detect the light intensity of the image in front of the vehicle;

[0029] a processing module, configured to process the image in front of the vehicle by using a preset light intensity processing model when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle;

[0030] The display module is used to send the processed image in front of the vehicle to a head-up display system, and project the processed image in front of the vehicle to a designated position on the windshield for display through the head-up display system.

[0031] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the night driving visual assistance method provided in an embodiment of the present invention when executing the computer program.

[0032] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the night driving visual assistance method provided in the embodiment of the invention are implemented.

[0033] In the embodiment of the present invention, when driving at night, the image in front of the vehicle is acquired in real time, and the light intensity of the image in front of the vehicle is detected; when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model so that the light intensity of the image in front of the vehicle after processing is less than the light intensity in the image in front of the vehicle; the image in front of the vehicle after processing is sent to a head-up display system, and the head-up display system projects the processed image in front of the vehicle to a designated position on the windshield for display. When driving at night, the light intensity of the oncoming vehicle can be detected by the image in front of the vehicle. When the light intensity in the image in front of the vehicle is large, the image in front of the vehicle is processed to obtain an image with a small light intensity, and the head-up display system projects the image with a small light intensity to a designated position on the windshield for display, so that when the light intensity in front of the vehicle is strong, the driver of the own party can meet the vehicle by observing the display content at the designated position on the windshield, thereby reducing the danger of the oncoming vehicle with strong lights when meeting at night, thereby improving the safety of driving at night. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0035] Figure 1 is a flow chart of a nighttime driving visual assistance method provided by an embodiment of the present invention;

[0036] Figure 2 is a structural schematic diagram of a nighttime driving visual aid device provided by an embodiment of the present invention;

[0037] Figure 3It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0039] See also Figure 1 , Figure 1 is a flow chart of a nighttime driving visual assistance method provided by an embodiment of the present invention. Figure 1 As shown, the nighttime driving visual assistance method comprises the following steps:

[0040] 101. When driving at night, obtain the image in front of the vehicle in real time and detect the light intensity of the image in front of the vehicle.

[0041] In an embodiment of the present invention, the above-mentioned night driving visual assistance method can be installed on a server or on a vehicle's onboard system. When the night driving visual assistance method is installed on a server, a large number of vehicles can be provided for access, and each vehicle can access the server through a user ID to obtain the night driving visual assistance service provided by the server. When the night driving visual assistance method is installed on a vehicle system, each vehicle can obtain the night driving visual assistance service through its own vehicle.

[0042] When driving at night, the on-board camera in the vehicle can be used to capture the image in front of the vehicle in real time, and then the light intensity of the image in front of the vehicle can be detected based on image detection technology to detect the light intensity in the image in front of the vehicle.

[0043] Furthermore, the vehicle camera may be disposed above the driver to capture an image of the vehicle in front of the driver having a similar field of view to the driver, thereby more accurately detecting the light intensity.

[0044] Furthermore, the detection result of the light detection on the image in front of the vehicle may be a light intensity value and a position where high-intensity light appears.

[0045] Specifically, the image in front of the vehicle can be segmented according to a preset ratio to obtain a corresponding number of segmented images; the segmented images are input into a preset light intensity detection model, and the light intensity detection result of the image in front of the vehicle is obtained through processing by the light intensity detection model.

[0046] In an embodiment of the present invention, the image in front of the vehicle is segmented according to a preset ratio, which can be an average segmentation. For example, the image in front of the vehicle is segmented into a "field" shape, and the image in front of the vehicle is divided into an upper left image, an upper right image, a lower left image, a lower right image, etc. It can also be segmented into a "river" shape, and the image in front of the vehicle is divided into a left image, a middle image, a right image, etc.

[0047] The preset light intensity detection model can be understood as a trained light intensity detection model. The trained light intensity detection model can output the light intensity detection result of the image. The light intensity detection model can be a model constructed based on a convolutional neural network. The preset light intensity detection model is obtained through supervised training with a first data set. The first data set includes first sample images and annotation data. One first sample image corresponds to one annotation data. The annotation data includes the expert's annotation of the light position and the light intensity. The annotation data can be understood as the true result. The first data set is divided into a first training set and a first test set. During the training process, the first sample images in the first training set are input into the light intensity detection model to be trained. The detection result of the first sample image is obtained through the light intensity detection model to be trained. The error between the detection result of the first sample image and the annotation data of the first sample image is calculated to obtain the error between the detection result and the true result. The light intensity detection model to be trained is adjusted through error backpropagation so that the detection result of the light intensity detection model to be trained is closer and closer to the true result. In this way, the light intensity detection model can learn to accurately detect the light intensity. When the light intensity detection model is tested in the first test set and the test results converge, the trained light intensity detection model can be obtained.

[0048] In an embodiment of the present invention, segmenting the image in front of the vehicle can reduce the size of the image in front of the vehicle. For the convolutional neural network in the light intensity detection model, this can improve the detection speed. However, the segmented images are all input into the preset light intensity detection model, and the global information of the image in front of the vehicle is still retained, without causing information loss. Since the light is generally on the driver's side and has locality, segmenting the image in front of the vehicle can also perform local detection more accurately, thereby obtaining a more accurate light intensity detection result.

[0049] Specifically, in the step of segmenting the image in front of the vehicle according to a preset ratio, the image in front of the vehicle can be tiled through a 10*10 grid; the image in front of the vehicle is segmented with the 6*6 area in the upper left corner as the first segmentation area to obtain a first segmented image; the image in front of the vehicle is segmented with the 6*6 area in the lower left corner as the second segmentation area to obtain a second segmented image; the image in front of the vehicle is segmented with the 6*6 area in the upper right corner as the third segmentation area to obtain a third segmented image; and the image in front of the vehicle is segmented with the 6*6 area in the lower right corner as the fourth segmentation area to obtain a fourth segmented image.

[0050] By tiling the image in front of the vehicle through a 10*10 grid and dividing the image in front of the vehicle into four areas with a 6*6 grid size, each area has an overlapping area with two adjacent areas. In this way, when performing convolution calculations on each area, the edge information of the adjacent areas can be taken into account, so that the information of each area is not isolated, thereby improving the detection accuracy of the light intensity detection model. For example, when high-intensity light is detected in the first segmented area, the light will diffuse, so that the second segmented area and the third segmented area can capture the light diffusion feature in the overlapping area, and the fourth segmented area can capture the light diffusion feature in the overlapping area in the upper corner, so that it can be more accurately judged that high-intensity light appears in the first segmented area.

[0051] After the segmentation area is determined, the first segmentation image is obtained by segmentation according to the first segmentation area, the second segmentation image is obtained by segmentation according to the second segmentation area, the third segmentation image is obtained by segmentation according to the third segmentation area, and the fourth segmentation image is obtained by segmentation according to the fourth segmentation area. The first segmentation image is the upper left corner image of the image in front of the vehicle, and the left edge information of the third segmentation image is included on the right side of the first segmentation image, the upper edge information of the second segmentation image is included on the lower side of the first segmentation image, and the upper right corner edge information of the fourth segmentation image is included in the lower right corner of the first segmentation image. Similarly, the second segmentation image is the lower left corner image of the image in front of the vehicle, and the left edge information of the fourth segmentation image is included on the right side of the second segmentation image, the lower edge information of the first segmentation image is included on the upper side of the second segmentation image, and the upper left corner edge information of the second segmentation image is included in the upper right corner of the second segmentation image. The third segmentation image is the upper right corner image of the image in front of the vehicle, and the right edge information of the first segmentation image is included on the left side of the third segmentation image, the upper edge information of the fourth segmentation image is included on the lower side of the third segmentation image, and the upper right corner edge information of the second segmentation image is included in the lower left corner of the third segmentation image. The fourth segmented image is the lower right corner image of the image in front of the vehicle. The left side of the fourth segmented image contains the right edge information of the second segmented image, the upper side of the fourth segmented image contains the lower edge information of the third segmented image, and the upper left corner of the fourth segmented image contains the lower right corner edge information of the first segmented image. In this way, when performing light intensity detection on each segmented image, the light diffusion characteristics in the edge information can be effectively extracted, thereby improving the accuracy of the light intensity detection model.

[0052] It should be noted that the preset light intensity detection model can process the segmented image in front of the vehicle when the first segmented image, the second segmented image, the third segmented image and the fourth segmented image are used as the input of the preset light intensity detection model. A second data set can be constructed to train the light intensity detection model, the second data set includes second sample images and annotation data, each second sample image includes the first segmented image, the second segmented image, the third segmented image and the fourth segmented image, and the segmentation method is as described in the above embodiment. Similarly, the second data set is divided into a second training set and a second test set, the light intensity detection model to be trained is trained by the second training set, and the light intensity detection model in the training process is tested by the second test set. After the test results converge, the trained light intensity detection model can be obtained.

[0053] After obtaining the trained light intensity detection model, the trained light intensity model is preset in the server or the vehicle system. After segmenting the image in front of the vehicle, the first segmented image, the second segmented image, the third segmented image and the fourth segmented image can be simultaneously input into the preset light intensity detection model, and the light intensity detection results of the first segmented image, the second segmented image, the third segmented image and the fourth segmented image can be obtained by processing with the preset light intensity detection model.

[0054] By performing light intensity detection on each segmented image through the trained light intensity detection model, the light diffusion characteristics in the edge information can be effectively extracted, thereby improving the accuracy of the light intensity detection model.

[0055] 102. When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed using a preset light intensity processing model so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle.

[0056] In the embodiment of the present invention, the light intensity detection result may include the occurrence position of the high-intensity light and the light intensity value, and the occurrence position of the high-intensity light may be at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image.

[0057] The image in front of the vehicle may be processed by performing light filtering on the image in front of the vehicle through image processing technology, thereby filtering high-intensity light in the image in front of the vehicle. The light intensity of the processed image in front of the vehicle will be lower than the light intensity of the image in front of the vehicle that has not been filtered. Since the light intensity of the processed image in front of the vehicle is low, the driver can reduce the interference of high-intensity light on the line of sight by observing the processed image in front of the vehicle.

[0058] Specifically, when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, an image to be processed is obtained according to the detection result, and the image to be processed may be at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, wherein the light intensity is greater than the first preset value; the image to be processed is input into a preset light intensity processing model, and the image to be processed is processed by the preset light intensity processing model to obtain a target image corresponding to the image to be processed, and the light intensity of the target image is less than the first preset value.

[0059] For example, when it is detected that the light intensity in one or more of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image is greater than the first preset value, it can be determined that the light intensity in the image in front of the vehicle is greater than the first preset value. The segmented images in which the light intensity is greater than the first preset value among the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image can be used as the images to be processed.

[0060] By taking the segmented image with high-intensity light as the image to be processed and then performing light filtering on the image to be processed, the high-intensity light in the image in front of the vehicle can be filtered, and the light intensity of the target image will be smaller than the light intensity in the image in front of the vehicle that has not been filtered. Since the light intensity of the target image is low, the driver can reduce the interference of high-intensity light on the line of sight by observing the target image.

[0061] Specifically, the preset light intensity processing model includes an image generation network. In the step of processing the image to be processed by the preset light intensity processing model to obtain a target image corresponding to the image to be processed, the image to be processed can be input into the preset light intensity processing model, and the target image corresponding to the image to be processed is generated by the image generation network in the preset light intensity processing model.

[0062] It should be noted that the preset light intensity processing model can be understood as a trained light intensity processing model. During the training process, the above-mentioned light intensity processing model is constructed based on a generative adversarial network. The generative adversarial network includes a generative network and a discriminative network. After the generative adversarial network training is completed, only the generative network preset in the server or vehicle system is taken. Through the generative network, the image to be processed is generated as a target image, thereby obtaining a target image with a light intensity less than a first preset value.

[0063] Further, a third data set is constructed, and the third data set includes a third sample image and a fourth sample image. The third sample image can be a segmented image of high-intensity light, and the fourth sample image can be a segmented image of low-intensity light. The third sample image and the fourth sample image only have the variable of light intensity. During the training process, the third sample image is input into the generative network to obtain a generated image. In the discriminative network, the generated image is compared with the fourth sample image, and the error and similarity between the generated image and the fourth sample image are calculated. The parameters of the generative network are adjusted by the error so that the generated image generated by the generative network gets a higher score in the discriminative network. The discriminative network is adjusted by the similarity so that the discriminative network gives a lower score to the generated image, and the game is completed, so that the generated image generated by the generative network based on the third sample image is closer and closer to the fourth sample image. When the discriminative network can no longer distinguish the generated image from the fourth sample image, the training of the generative network is completed, and the generative network can be preset in the server or the vehicle system. The image to be processed is generated by the generative network to obtain a target image with low light intensity.

[0064] 103. Send the processed image in front of the vehicle to a head-up display system, and project the processed image in front of the vehicle to a designated position on the windshield for display through the head-up display system.

[0065] In an embodiment of the present invention, the processed image in front of the vehicle can be sent to a head-up display system (HUD). Since the light intensity of the processed image in front of the vehicle is greatly reduced, the driver can observe the road condition in front of the vehicle through the processed image in front of the vehicle, thereby reducing the interference of high-intensity light in front of the vehicle on the driver's vision.

[0066] The designated position on the windshield may be a position to avoid high-intensity light, for example, when high-intensity light appears in the upper left corner, the designated position may be the lower right corner or the upper right corner. The head-up display system may control the projection direction and position through a rotatable gimbal.

[0067] Specifically, when it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, a display area image is obtained according to the detection result, and the display area image is one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image whose light intensity is less than the second preset value and has the smallest light intensity, and the second preset value is less than the first preset value; according to the position of the display area image in the image in front of the vehicle, the designated position on the windshield is determined.

[0068] It should be noted that the light detection results include the location where high-intensity light appears, the location where low-intensity light appears, and the corresponding light intensity. If the light intensity is less than the second preset value, it can be said that low-intensity light appears. The location where the low-intensity light appears can be determined as the designated location to project the target image, so that the image projected by the head-up display system can be made clearer, which is more conducive to strengthening personnel's observation of road conditions at night.

[0069] The position of a segmented image having a light intensity less than the second preset value and the smallest light intensity among the first segmented image, the second segmented image, the third segmented image and the fourth segmented image can be taken as the designated position, so as to project the target image at the designated position.

[0070] In the embodiment of the present invention, when driving at night, the image in front of the vehicle is acquired in real time, and the light intensity of the image in front of the vehicle is detected; when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model so that the light intensity of the image in front of the vehicle after processing is less than the light intensity in the image in front of the vehicle; the image in front of the vehicle after processing is sent to a head-up display system, and the head-up display system projects the processed image in front of the vehicle to a designated position on the windshield for display. When driving at night, the light intensity of the oncoming vehicle can be detected by the image in front of the vehicle. When the light intensity in the image in front of the vehicle is large, the image in front of the vehicle is processed to obtain an image with a small light intensity, and the head-up display system projects the image with a small light intensity to a designated position on the windshield for display, so that when the light intensity in front of the vehicle is strong, the driver of the own party can meet the vehicle by observing the display content at the designated position on the windshield, thereby reducing the danger of the oncoming vehicle with strong lights when meeting at night, thereby improving the safety of driving at night.

[0071] It should be noted that the nighttime driving visual assistance method provided in the embodiment of the present invention can be applied to devices such as smart phones, computers, servers, etc. that can provide nighttime driving visual assistance.

[0072] Optional, see Figure 2 , Figure 2 is a schematic diagram of the structure of a nighttime driving visual aid device provided by an embodiment of the present invention. Figure 2 As shown, the device comprises:

[0073] The acquisition module 201 is used to acquire the image in front of the vehicle in real time when driving at night, and to detect the light intensity of the image in front of the vehicle;

[0074] The processing module 202 is used to process the image in front of the vehicle by using a preset light intensity processing model when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle;

[0075] The display module 203 is used to send the processed image in front of the vehicle to a head-up display system, and project the processed image in front of the vehicle to a designated position on the windshield for display through the head-up display system.

[0076] Optionally, the acquisition module 201 includes:

[0077] A segmentation unit, used to segment the image in front of the vehicle according to a preset ratio to obtain a corresponding number of segmented images;

[0078] The first processing unit is used to input the segmented image into a preset light intensity detection model, and obtain the light intensity detection result of the image in front of the vehicle through processing by the light intensity detection model.

[0079] Optionally, a split unit, including:

[0080] A tiling subunit, used for tiling the image in front of the vehicle through a 10*10 grid;

[0081] A first segmentation subunit is used to segment the image in front of the vehicle using the upper left corner 6*6 as the first segmentation area to obtain a first segmented image;

[0082] A second segmentation subunit is used to segment the image in front of the vehicle using the lower left corner 6*6 as the second segmentation area to obtain a second segmented image;

[0083] A third segmentation subunit is used for segmenting the image in front of the vehicle with a 6*6 upper right corner as a third segmentation area to obtain a third segmentation image;

[0084] The fourth segmentation subunit is used to segment the image in front of the vehicle with the lower right corner of 6*6 as the fourth segmentation area to obtain a fourth segmentation image.

[0085] Optionally, the processing unit is also used to input the first segmented image, the second segmented image, the third segmented image and the fourth segmented image into the preset light intensity detection model at the same time, and obtain the light intensity detection results of the first segmented image, the second segmented image, the third segmented image and the fourth segmented image through the preset light intensity detection model.

[0086] Optionally, the processing module 202 includes:

[0087] a detection unit, configured to obtain an image to be processed according to the detection result when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, wherein the image to be processed is at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, in which the light intensity is greater than the first preset value;

[0088] The second processing unit is used to input the image to be processed into a preset light intensity processing model, process the image to be processed through the preset light intensity processing model, and obtain a target image corresponding to the image to be processed, wherein the light intensity of the target image is less than a first preset value.

[0089] Optionally, the processing unit is further used to input the image to be processed into a preset light intensity processing model, and generate a target image corresponding to the image to be processed through an image generation network in the preset light intensity processing model.

[0090] Optionally, before the display module 203, the device further includes:

[0091] a detection module, configured to obtain a display area image according to the detection result when it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, wherein the display area image is the one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image whose light intensity is less than the second preset value and has the smallest light intensity, and the second preset value is less than the first preset value;

[0092] The determination module is used to determine a designated position on the windshield according to the position of the display area image in the image in front of the vehicle.

[0093] It should be noted that the nighttime driving visual assistance device provided by the embodiment of the present invention can be applied to devices such as smart phones, computers, servers, etc. that can provide nighttime driving visual assistance.

[0094] The nighttime driving visual assistance device provided by the embodiment of the present invention can implement each process implemented by the nighttime driving visual assistance method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0095] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a nighttime driving visual assistance method stored in the memory 302 and executable on the processor 301, wherein:

[0096] The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps:

[0097] When driving at night, real-time acquisition of the image in front of the vehicle and detection of the light intensity of the image in front of the vehicle are performed;

[0098] When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle;

[0099] The processed image in front of the vehicle is sent to a head-up display system, and the head-up display system projects the processed image in front of the vehicle onto a designated position on a windshield for display.

[0100] Optionally, the processor 301 performs the light intensity detection on the image in front of the vehicle, including:

[0101] Segmenting the image in front of the vehicle according to a preset ratio to obtain a corresponding number of segmented images;

[0102] The segmented image is input into a preset light intensity detection model, and the light intensity detection result of the image in front of the vehicle is obtained through processing by the light intensity detection model.

[0103] Optionally, the processor 301 performs segmentation of the vehicle front image according to a preset ratio to obtain a corresponding number of segmented images, including:

[0104] Tiling the image in front of the vehicle through a 10*10 grid;

[0105] Segment the image in front of the vehicle using the 6*6 area in the upper left corner as the first segmentation area to obtain a first segmentation image;

[0106] The lower left corner 6*6 of the image in front of the vehicle is segmented as the second segmentation area to obtain a second segmentation image;

[0107] Segment the image in front of the vehicle using the 6*6 area in the upper right corner as the third segmentation area to obtain a third segmentation image;

[0108] The lower right corner 6*6 of the image in front of the vehicle is used as the fourth segmentation area for segmentation to obtain a fourth segmentation image.

[0109] Optionally, the processor 301 inputs the segmented image into a preset light intensity detection model, and obtains a light intensity detection result of the image in front of the vehicle through processing by the light intensity detection model, including:

[0110] The first segmented image, the second segmented image, the third segmented image and the fourth segmented image are simultaneously input into the preset light intensity detection model, and the light intensity detection results of the first segmented image, the second segmented image, the third segmented image and the fourth segmented image are obtained by processing with the preset light intensity detection model.

[0111] Optionally, the processor 301 performs, when detecting that the light intensity in the image in front of the vehicle is greater than a first preset value, processing the image in front of the vehicle by using a preset light intensity processing model, including:

[0112] When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, an image to be processed is obtained according to the detection result, and the image to be processed is at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, in which the light intensity is greater than the first preset value;

[0113] The image to be processed is input into a preset light intensity processing model, and the image to be processed is processed by the preset light intensity processing model to obtain a target image corresponding to the image to be processed, wherein the light intensity of the target image is less than a first preset value.

[0114] Optionally, the preset light intensity processing model executed by the processor 301 includes an image generation network, and the step of inputting the image to be processed into the preset light intensity processing model, processing the image to be processed by the preset light intensity processing model, and obtaining a target image corresponding to the image to be processed includes:

[0115] The image to be processed is input into a preset light intensity processing model, and a target image corresponding to the image to be processed is generated through an image generation network in the preset light intensity processing model.

[0116] Optionally, before the processor 301 sends the processed image in front of the vehicle to a head-up display system and projects the processed image in front of the vehicle to a designated position on the windshield for display through the head-up display system, the method further includes:

[0117] When it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, a display area image is obtained according to the detection result, and the display area image is the one with the light intensity less than the second preset value and the smallest light intensity among the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, and the second preset value is less than the first preset value;

[0118] A designated position on the windshield is determined according to the position of the display area image in the vehicle front image.

[0119] The electronic device provided in the embodiment of the present invention can implement each process implemented by the nighttime driving visual assistance method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0120] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements the various processes of the night driving visual assistance method or the application-side night driving visual assistance method provided by the embodiment of the present invention, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0122] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A nighttime driving visual assistance method, characterized in that: The following steps are involved: When driving at night, the image in front of the vehicle is acquired in real time, and the image in front of the vehicle is tiled using a 10*10 grid; The 6*6 upper left corner of the image in front of the vehicle is used as the first segmentation area for segmentation to obtain a first segmentation image; the 6*6 lower left corner of the image in front of the vehicle is used as the second segmentation area for segmentation to obtain a second segmentation image; the 6*6 upper right corner of the image in front of the vehicle is used as the third segmentation area for segmentation to obtain a third segmentation image; the 6*6 lower right corner of the image in front of the vehicle is used as the fourth segmentation area for segmentation to obtain a fourth segmentation image; the first segmentation image, the second segmentation image, the third segmentation image and the fourth segmentation image are simultaneously input into a preset light intensity detection model, and the light intensity detection results of the first segmentation image, the second segmentation image, the third segmentation image and the fourth segmentation image are obtained by processing with the preset light intensity detection model, the light detection results include the appearance position of high-intensity light, the appearance position of low-intensity light and the corresponding light intensity, the light intensity corresponding to the high-intensity light is greater than the first preset value, and the light intensity corresponding to the low-intensity light is less than the second preset value; When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle; When it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, a display area image is obtained according to the detection result, and the display area image is the one with the light intensity less than the second preset value and the smallest light intensity among the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, and the second preset value is less than the first preset value; determining a designated position on the windshield according to a position of the display area image in the image in front of the vehicle; The processed image in front of the vehicle is sent to a head-up display system, and the head-up display system projects the processed image in front of the vehicle onto a designated position on a windshield for display.

2. The method according to claim 1, characterized in that When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, the image in front of the vehicle is processed by a preset light intensity processing model, including: When it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, an image to be processed is obtained according to the detection result, and the image to be processed is at least one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image, in which the light intensity is greater than the first preset value; The image to be processed is input into a preset light intensity processing model, and the image to be processed is processed by the preset light intensity processing model to obtain a target image corresponding to the image to be processed, wherein the light intensity of the target image is less than a first preset value.

3. The method according to claim 2, characterized in that The preset light intensity processing model includes an image generation network, and the step of inputting the image to be processed into the preset light intensity processing model, processing the image to be processed by the preset light intensity processing model, and obtaining a target image corresponding to the image to be processed includes: The image to be processed is input into a preset light intensity processing model, and a target image corresponding to the image to be processed is generated through an image generation network in the preset light intensity processing model.

4. A nighttime driving visual aid device, characterized in that: The device comprises: An acquisition module is used to acquire the image in front of the vehicle in real time when driving at night, and to tile the image in front of the vehicle through a 10*10 grid; to segment the image in front of the vehicle using the 6*6 upper left corner as the first segmentation area to obtain a first segmentation image; to segment the image in front of the vehicle using the 6*6 lower left corner as the second segmentation area to obtain a second segmentation image; to segment the image in front of the vehicle using the 6*6 upper right corner as the third segmentation area to obtain a third segmentation image; to segment the image in front of the vehicle using the 6*6 lower right corner as the fourth segmentation area to obtain a fourth segmentation image; to input the first segmentation image, the second segmentation image, the third segmentation image and the fourth segmentation image into a preset light intensity detection model at the same time, and to obtain light intensity detection results of the first segmentation image, the second segmentation image, the third segmentation image and the fourth segmentation image through the preset light intensity detection model, wherein the light detection results include the occurrence position of high-intensity light, the occurrence position of low-intensity light and the corresponding light intensity, the light intensity corresponding to the high-intensity light is greater than the first preset value, and the light intensity corresponding to the low-intensity light is less than the second preset value; a processing module, configured to process the image in front of the vehicle by using a preset light intensity processing model when it is detected that the light intensity in the image in front of the vehicle is greater than a first preset value, so that the light intensity of the processed image in front of the vehicle is less than the light intensity in the image in front of the vehicle; a detection module, configured to obtain a display area image according to the detection result when it is detected that the light intensity in the image in front of the vehicle is less than a second preset value, wherein the display area image is the one of the first segmented image, the second segmented image, the third segmented image, and the fourth segmented image whose light intensity is less than the second preset value and has the smallest light intensity, and the second preset value is less than the first preset value; A determination module, configured to determine a designated position on the windshield according to a position of the display area image in the image in front of the vehicle; The display module is used to send the processed image in front of the vehicle to a head-up display system, and project the processed image in front of the vehicle to a designated position on the windshield for display through the head-up display system.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the nighttime driving visual assistance method as claimed in any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the nighttime driving visual assistance method according to any one of claims 1 to 3 are implemented.

Images