Road detection method, device, equipment and storage medium based on deep learning

Abstract

The present invention discloses a road detection method, device, equipment and storage medium based on deep learning. The method includes obtaining an original image data set of a road, marking the road information in the road image data set, obtaining a training image data set including a first road real frame and a second road real frame; inputting the training image data set into a road detection model, obtaining a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss value between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; thereby realizing road detection of the image data to be detected. The present invention trains the road detection model by calculating the loss value between the detection frame corresponding to the lane line and the stop line, and the detection frame corresponding to the road sign and the corresponding real frame, and at the same time completes the detection and distinction of drivable roads, thereby improving the accuracy of road detection.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a road detection method, device, equipment and storage medium based on deep learning. Background Art

[0002] Autonomous driving technology is an important area of ​​artificial intelligence. It refers to a car that can drive with little or no human presence.

[0003] Now, autonomous driving or assisted driving not only needs to analyze the position of lane lines, but also needs to know the attributes of lane lines (straight ahead, left turn, bus lane, etc.). The usual method is to detect lane lines and road signs separately, and then merge them. This method determines the drivable area completely based on the logic of two lane lines and road signs, and has low fault tolerance. Therefore, how to improve the accuracy of road detection is a technical problem that needs to be solved urgently.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a road detection method, device, equipment and storage medium based on deep learning, aiming to solve the technical problem of low accuracy of current road detection.

[0006] To achieve the above object, the present invention provides a road detection method based on deep learning, the method comprising the following steps:

[0007] Acquire an original image dataset of a road, and mark the road information in the road image dataset to obtain a training image dataset; wherein the training image dataset includes a first road real frame and a second road real frame;

[0008] Inputting the training image data set into a road detection model to obtain a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame;

[0009] When the image data to be detected is received, the image data to be detected is input into a road detection model to obtain a drivable lane in the image to be detected.

[0010] Optionally, the first road real frame includes a lane line real frame and a stop line real frame, and the second road real frame includes a road sign real frame.

[0011] Optionally, before the step of inputting the training image data set into the road detection model, the method further includes:

[0012] Sampling lane lines and stop lines in the training image data set to obtain lane line sampling points and stop line sampling points;

[0013] According to the lane line sampling points and the stop line sampling points, the shape of the first road real frame is adjusted to a polygon.

[0014] Optionally, the step of sampling lane lines and stop lines in the training image data set specifically includes:

[0015] Performing vertical uniform sampling on the lane lines in the training image data set to obtain lane line sampling points;

[0016] The stop lines in the training image data set are sampled at uniform intervals in the horizontal direction to obtain stop line sampling points.

[0017] Optionally, the first road detection frame includes a lane line detection frame and a stop line detection frame, and the second road detection frame includes a road sign detection frame.

[0018] Optionally, the step of completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame, specifically includes:

[0019] Obtain a first loss value between the first road detection frame and the first road real frame and a second loss value between the second road detection frame and the second road real frame;

[0020] The first loss value and the second loss value are combined according to a preset rule, and the road detection model is trained.

[0021] Optionally, the first loss value is a loss value between the first road detection frame and the first road real frame regarding an anchor algorithm, and the second loss value is a loss value between the second road detection frame and the second road real frame regarding an anchor free algorithm.

[0022] In addition, in order to achieve the above-mentioned purpose, the present invention also provides a road detection device based on deep learning, and the road detection device based on deep learning includes:

[0023] An acquisition module is used to acquire an original image dataset of a road, and mark the road information in the road image dataset to obtain a training image dataset; wherein the training image dataset includes a first road real frame and a second road real frame;

[0024] A training module, used for inputting the training image data set into a road detection model, obtaining a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame;

[0025] The detection module is used to input the image data to be detected into the road detection model when receiving the image data to be detected, so as to obtain the drivable lane in the image to be detected.

[0026] In addition, in order to achieve the above-mentioned purpose, the present invention also provides a deep learning-based road detection device, and the deep learning-based road detection device includes: a memory, a processor, and a deep learning-based road detection program stored in the memory and executable on the processor, and the deep learning-based road detection program, when executed by the processor, implements the steps of the deep learning-based road detection method as described above.

[0027] In addition, in order to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a deep learning-based road detection program is stored. When the deep learning-based road detection program is executed by a processor, the steps of the deep learning-based road detection method as described above are implemented.

[0028] The embodiment of the present invention proposes a road detection method, device, equipment and storage medium based on deep learning. The method includes obtaining an original image data set of a road, and marking the road information in the road image data set to obtain a training image data set; wherein the training image data set includes a first road real frame and a second road real frame; inputting the training image data set into a road detection model to obtain a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss value between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; when receiving the image data to be detected, inputting the image data to be detected into the road detection model to obtain the drivable lane in the image to be detected. The present invention trains the road detection model by calculating the loss value between the detection frame corresponding to the lane line and the stop line, and the detection frame corresponding to the road sign and the corresponding real frame, and at the same time completes the detection and distinction of the drivable roads, thereby improving the accuracy of road detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a structural schematic diagram of a road detection device based on deep learning in an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of a process flow of an embodiment of a road detection method based on deep learning of the present invention;

[0031] Figure 3 4 is a structural block diagram of a road detection device based on deep learning in an embodiment of the present invention.

[0032] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0033] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0034] Autonomous driving technology is an important area of ​​artificial intelligence. It refers to a car that can drive with little or no human presence.

[0035] Now, autonomous driving or assisted driving not only needs to analyze the position of lane lines, but also needs to know the attributes of lane lines (straight ahead, left turn, bus lane, etc.). The usual method is to detect lane lines and road signs separately, and then merge them. This method determines the drivable area completely based on the logic of two lane lines and road signs, and has low fault tolerance. Therefore, how to improve the accuracy of road detection is a technical problem that needs to be solved urgently.

[0036] In order to solve this problem, various embodiments of the road detection method based on deep learning of the present invention are proposed. The present invention provides a road detection method, device, equipment and storage medium based on deep learning. The method includes obtaining an original image data set of a road, marking the road information in the road image data set, and obtaining a training image data set including a first road real frame and a second road real frame; inputting the training image data set into a road detection model to obtain a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss value between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; thereby realizing road detection of the image data to be detected. The present invention trains the road detection model by calculating the loss value of the detection frame corresponding to the lane line and the stop line, and the detection frame corresponding to the road sign with the corresponding real frame, and at the same time completes the detection and distinction of the drivable roads, thereby improving the accuracy of road detection.

[0037] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a road detection device based on deep learning involved in an embodiment of the present invention.

[0038] The device may be a user equipment (UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing device connected to a wireless modem, a mobile station (MS), etc. The device may be called a user terminal, a portable terminal, a desktop terminal, etc.

[0039] Typically, the device includes: at least one processor 301, a memory 302, and a deep learning-based road detection program stored in the memory and executable on the processor, wherein the deep learning-based road detection program is configured to implement the steps of the deep learning-based road detection method as described above.

[0040] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. The processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process road detection operations based on deep learning, so that the road detection model based on deep learning can be trained and learned autonomously to improve efficiency and accuracy.

[0041] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 801 to implement the road detection method based on deep learning provided in the method embodiment of the present application.

[0042] In some embodiments, the terminal may further optionally include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected via a bus or a signal line. Each peripheral device may be connected to the communication interface 303 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304, a display screen 305 and a power supply 306.

[0043] The communication interface 303 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. The communication interface 303 is used to receive the movement trajectories and other data of multiple mobile terminals uploaded by users through the peripheral device. In some embodiments, the processor 301, the memory 302 and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302 and the communication interface 303 can be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0044] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals, so as to obtain the movement trajectory and other data of multiple mobile terminals. The radio frequency circuit 304 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 304 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0045] The display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. When the display screen 305 is a touch display screen, the display screen 305 also has the ability to collect touch signals on the surface or above the surface of the display screen 305. The touch signal can be input to the processor 301 as a control signal for processing. At this time, the display screen 305 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 305 can be one, the front panel of the electronic device; in other embodiments, the display screen 305 can be at least two, respectively arranged on different surfaces of the electronic device or in a folding design; in some further embodiments, the display screen 305 can be a flexible display screen, arranged on a curved surface or a folding surface of the electronic device. Even, the display screen 305 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 305 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0046] The power supply 306 is used to power various components in the electronic device. The power supply 306 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 306 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0047] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation of the deep learning-based road detection device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0048] The embodiment of the present invention provides a road detection method based on deep learning, referring to Figure 2 , Figure 2 Schematic diagram of the flow chart of the first embodiment of the road detection method based on deep learning of the present invention.

[0049] In this embodiment, the road detection method based on deep learning includes the following steps:

[0050] Step S100, obtaining an original image dataset of a road, and marking the road information in the road image dataset to obtain a training image dataset; wherein the training image dataset includes a first road real frame and a second road real frame.

[0051] Specifically, after the original image data of the road is acquired, the road information in the original image data is marked to obtain training image data having a first road real frame and a second road real frame.

[0052] It should be noted that, in this embodiment, the roads in the original image data set are marked to obtain a training image data set, wherein the first road real frame includes a lane line real frame and a stop line real frame, and the second road real frame includes a road sign real frame.

[0053] Furthermore, before inputting the training image data set into the road detection model step, the lane lines and stop lines in the training image data set may be sampled to obtain lane line sampling points and stop line sampling points; and according to the lane line sampling points and the stop line sampling points, the shape of the first road real frame is adjusted to a polygon.

[0054] It is easy to understand that the lane lines and stop lines in the training image data set can be sampled by uniformly sampling the lane lines in the training image data set vertically to obtain lane line sampling points; and uniformly sampling the stop lines in the training image data set horizontally to obtain stop line sampling points.

[0055] Step S200: input the training image data set into the road detection model to obtain a first road detection frame and a second road detection frame, and complete the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame.

[0056] Specifically, after obtaining a training image data set having a first road real frame and a second road real frame, the training image data set is input into a road detection model to obtain a first road detection frame and a second road detection frame.

[0057] Furthermore, according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame, the training of the road detection model is completed by obtaining a first loss value between the first road detection frame and the first road real frame and a second loss value between the second road detection frame and the second road real frame; the first loss value and the second loss value are merged according to a preset rule, and the road detection model is trained.

[0058] It should be noted that, in this embodiment, the first loss value is the loss value of the first road detection frame and the first road real frame with respect to the anchor algorithm, and the second loss value is the loss value of the second road detection frame and the second road real frame with respect to the anchor free algorithm.

[0059] Finally, the road detection model is trained using the loss values ​​of the first road true frame and the first road predicted frame, the second road true frame and the second road detection frame of each training image until the model converges and the training process is completed.

[0060] Step S300: When receiving the image data to be detected, the image data to be detected is input into a road detection model to obtain a drivable lane in the image to be detected.

[0061] Specifically, after obtaining the trained road detection model, wait for the input of the image data to be detected. If the image data to be detected is received, the image data to be detected is input into the trained road detection model to obtain the drivable lanes in the output image to be detected.

[0062] In this embodiment, a road detection method based on deep learning is provided, by acquiring an original image data set of a road, and marking the road information in the road image data set, obtaining a training image data set including a first road real frame and a second road real frame; inputting the training image data set into a road detection model, obtaining a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss value between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; thereby realizing road detection of the image data to be detected. The present invention trains the road detection model by calculating the loss value between the detection frame corresponding to the lane line and the stop line, and the detection frame corresponding to the road sign and the corresponding real frame, and at the same time completing the detection and distinction of drivable roads, thereby improving the accuracy of road detection.

[0063] Reference Figure 3 , Figure 3 This is a structural block diagram of an embodiment of a road detection device based on deep learning of the present invention.

[0064] like Figure 3 As shown, the road detection device based on deep learning proposed in an embodiment of the present invention includes:

[0065] The acquisition module 10 is used to acquire an original image dataset of a road, and mark the road information in the road image dataset to obtain a training image dataset; wherein the training image dataset includes a first road real frame and a second road real frame;

[0066] A training module 20 is used to input the training image data set into a road detection model, obtain a first road detection frame and a second road detection frame, and complete the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame;

[0067] The detection module 30 is used to input the image data to be detected into the road detection model when receiving the image data to be detected, so as to obtain the drivable lane in the image to be detected.

[0068] As an implementation manner, in the acquisition module 10, the first road real frame includes a lane line real frame and a stop line real frame, and the second road real frame includes a road sign real frame.

[0069] As an embodiment, the deep learning-based road detection device also includes an adjustment module 40, which is used to sample the lane lines and stop lines in the training image data set to obtain lane line sampling points and stop line sampling points; according to the lane line sampling points and the stop line sampling points, the shape of the first road real frame is adjusted to a polygon.

[0070] As an implementation manner, the adjustment module 40 is further used to perform vertical uniform sampling of lane lines in the training image data set to obtain lane line sampling points; and perform horizontal uniform sampling of stop lines in the training image data set to obtain stop line sampling points.

[0071] As an implementation manner, in the training module 20, the first road detection frame includes a lane line detection frame and a stop line detection frame, and the second road detection frame includes a road sign detection frame.

[0072] As an implementation mode, the training module 20 is also used to obtain a first loss value between the first road detection frame and the first road real frame and a second loss value between the second road detection frame and the second road real frame; merge the first loss value and the second loss value according to a preset rule, and train the road detection model.

[0073] As an implementation manner, in the training module 20, the first loss value is the loss value of the first road detection frame and the first road real frame regarding the anchor algorithm, and the second loss value is the loss value of the second road detection frame and the second road real frame regarding the anchor free algorithm.

[0074] The road detection device based on deep learning provided in this embodiment obtains the original image data set of the road and marks the road information in the road image data set to obtain a training image data set including a first road real frame and a second road real frame; the training image data set is input into the road detection model to obtain the first road detection frame and the second road detection frame, and the road detection model is trained according to the loss value between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; and then the road detection of the image data to be detected is realized. The present invention trains the road detection model by calculating the loss value between the detection frame corresponding to the lane line and the stop line, and the detection frame corresponding to the road sign and the corresponding real frame, and at the same time completes the detection and distinction of the drivable roads, thereby improving the accuracy of road detection.

[0075] Other embodiments or specific implementations of the road detection device based on deep learning of the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0076] In addition, an embodiment of the present invention further proposes a storage medium, on which a road detection program based on deep learning is stored, and when the road detection program based on deep learning is executed by a processor, the steps of the road detection method based on deep learning as described above are implemented. Therefore, it will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0077] 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 above-mentioned 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. Among them, the above-mentioned storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0078] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without creative work.

[0079] Through the description of the above implementation mode, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present invention, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

Claims

1. A road detection method based on deep learning, characterized in that: The method comprises the following steps: Acquire an original image dataset of a road, and mark the road information in the road image dataset to obtain a training image dataset; wherein each training image in the training image dataset includes a first road real frame and a second road real frame; The first road real frame includes a lane line real frame and a stop line real frame, the second road real frame includes a road sign real frame, and the road sign includes a straight sign, a left turn sign, and a bus lane sign; Inputting the training image data set into a road detection model to obtain a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; When the image data to be detected is received, the image data to be detected is input into a road detection model to obtain a drivable lane in the image to be detected.

2. The road detection method based on deep learning as claimed in claim 1, characterized in that: Before the step of inputting the training image data set into the road detection model, the method further comprises: Sampling lane lines and stop lines in the training image data set to obtain lane line sampling points and stop line sampling points; According to the lane line sampling points and the stop line sampling points, the shape of the first road real frame is adjusted to a polygon.

3. The road detection method based on deep learning as claimed in claim 2, characterized in that: The step of sampling the lane lines and stop lines in the training image data set specifically includes: Performing vertical uniform sampling on the lane lines in the training image data set to obtain lane line sampling points; The stop lines in the training image data set are sampled at uniform intervals in the horizontal direction to obtain stop line sampling points.

4. The road detection method based on deep learning as claimed in claim 1, characterized in that: The first road detection frame includes a lane line detection frame and a stop line detection frame, and the second road detection frame includes a road sign detection frame.

5. The road detection method based on deep learning as claimed in claim 1, characterized in that: The step of completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame, specifically includes: Obtain a first loss value between the first road detection frame and the first road real frame and a second loss value between the second road detection frame and the second road real frame; The first loss value and the second loss value are combined according to a preset rule, and the road detection model is trained.

6. The road detection method based on deep learning as claimed in claim 5, characterized in that: The first loss value is a loss value between the first road detection frame and the first road real frame regarding the anchor algorithm, and the second loss value is a loss value between the second road detection frame and the second road real frame regarding the anchor free algorithm.

7. A road detection device based on deep learning, characterized in that: The road detection device based on deep learning includes: An acquisition module is used to acquire an original image dataset of a road, and mark the road information in the road image dataset to obtain a training image dataset; wherein each training image in the training image dataset includes a first road real frame and a second road real frame; The first road real frame includes a lane line real frame and a stop line real frame, the second road real frame includes a road sign real frame, and the road sign includes a straight sign, a left turn sign, and a bus lane sign; A training module, used for inputting the training image data set into a road detection model, obtaining a first road detection frame and a second road detection frame, and completing the training of the road detection model according to the loss values ​​between the first road detection frame and the first road real frame, and between the second road detection frame and the second road real frame; The detection module is used to input the image data to be detected into the road detection model when receiving the image data to be detected, so as to obtain the drivable lane in the image to be detected.

8. A road detection device based on deep learning, characterized in that: The deep learning-based road detection device includes: a memory, a processor, and a deep learning-based road detection program stored in the memory and executable on the processor. When the deep learning-based road detection program is executed by the processor, the steps of the deep learning-based road detection method as described in any one of claims 1 to 6 are implemented.

9. A storage medium, characterized in that: The storage medium stores a deep learning-based road detection program, which, when executed by a processor, implements the steps of the deep learning-based road detection method as described in any one of claims 1 to 6.

Images