An obstacle recognition and target vehicle positioning system based on FPGA
By using FPGA development board and binocular camera on the target vehicle to identify obstacles, calculate relative distance and contact time, and adjust the accelerator and brake automatically, the problem of insufficient obstacle avoidance ability when driving at high speed is solved, and safety and intelligence are improved degree of transformation.
Patent Information
- Application Number
- CN202211011303.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-23
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-08-23
AI Technical Summary
When the target vehicle is driving at high speed, the user has limited reaction ability and it is difficult to avoid obstacles in time, resulting in collisions or traps in bullet craters, affecting training safety.
Design an obstacle recognition and target vehicle positioning system based on FPGA, collect environmental image information through the vehicle-mounted control module, use the FPGA development board to convert images, calculate the relative distance and estimated contact time of obstacles, and transfer it to the remote through the data transmission module. If there is no timely command, the control terminal will automatically adjust the accelerator and brake pedal and perform the steering wheel action to bypass obstacles.
It improves the obstacle avoidance ability of the target vehicle when driving at high speed and enhances safety. Especially when the user responds slowly or cannot control it in time, the system can independently avoid obstacles, which improves the safety and intelligence of training.
Smart Images

Figure CN115361421B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of target vehicles, and in particular relates to an obstacle recognition and target vehicle positioning system based on FPGA. Background Art
[0002] During the use of the target vehicle in the military shooting training, the mobile target vehicle is driving in a specific shooting range. Considering the characteristics of the surrounding environment of the shooting range, which is generally ups and downs and uneven terrain, when the target vehicle drives near a crater and gravel that is difficult to cross during training, the user needs to use the camera to identify the road conditions in front of the target vehicle, remotely control the driving direction of the target vehicle to avoid obstacles, and continue to complete the shooting training task. At present, this obstacle avoidance control method is relatively simple, and only uses the human eye to recognize the video image in front of the target vehicle transmitted to the host computer by the image transmission radio to judge the driving environment. When the target vehicle is driving at a high speed (≥90km / h), the user's reaction ability is limited, which may cause the target vehicle to collide with obstacles or fall into a crater, affecting the user's remote control and the military shooting training. Summary of the invention
[0003] In order to solve the problem of the single obstacle avoidance capability of the current high-speed target vehicle, the present invention provides an obstacle recognition and target vehicle positioning system based on FPGA, which can enable the on-board control module to independently judge the obstacle information ahead when the target vehicle is traveling at high speed, thereby improving the safety of the target vehicle in actual use.
[0004] An obstacle recognition and target vehicle positioning system based on FPGA, comprising a vehicle control module, a data transmission module and a remote control terminal;
[0005] When the target vehicle's driving speed is greater than a set value and there is an obstacle in front of the target vehicle, the on-board control module obtains the relative distance and estimated contact time of the obstacle relative to the target vehicle by collecting original image information of the target vehicle's surrounding environment and performing image conversion operations; the on-board control module transmits the relative distance and estimated contact time to the remote control terminal through the data transmission module for the user to observe, and determines whether the user's control command is not received within the set time and the relative distance is greater than the preset warning distance and the estimated contact time is less than the set threshold. If so, the on-board control module reduces the target vehicle's speed by adjusting the accelerator pedal opening and the brake pedal opening. When the target vehicle's speed is reduced to the set value, the on-board control module executes a steering wheel turning action to eventually bypass the obstacle.
[0006] Furthermore, the vehicle control module includes an FPGA development board, a binocular camera and a dual-antenna GPS board;
[0007] The binocular camera is used to collect original image information of the target vehicle's surrounding environment in real time; when the target vehicle's driving speed is greater than a set value and there is an obstacle in front of the target vehicle, the FPGA development board performs an image conversion operation on the original image information of the target vehicle's surrounding environment to obtain the relative distance and estimated contact time of the obstacle relative to the target vehicle, and then transmits the relative distance and estimated contact time to the remote control terminal through the data transmission module for the user to observe, and then determines whether the user's control command is not received within the set time and the relative distance is greater than the preset warning distance and the estimated contact time is less than the set threshold. If so, the FPGA development board reduces the target vehicle's speed by adjusting the accelerator pedal opening and the brake pedal opening. When the target vehicle's speed is reduced to the set value, the FPGA development board performs a steering wheel turning action to eventually bypass the obstacle;
[0008] The dual-antenna GPS board performs differential positioning on the target vehicle through dual antennas, and transmits the differential positioning information to the FPGA development board;
[0009] The FPGA development board also obtains the target vehicle status information by connecting to the target vehicle's electronic control unit, and transmits the target vehicle status information, differential positioning information, and the relative distance of the obstacle to the target vehicle and the estimated contact time to the remote control terminal through the data transmission module for the user to view at any time.
[0010] Furthermore, the image conversion operation is as follows: the FPGA development board uses a filtering algorithm to perform filtering processing on the original image information of the target vehicle's surrounding environment and Modelsim waveform simulation to obtain the relative distance of the obstacle to the target vehicle and the estimated contact time.
[0011] Furthermore, the front antenna and the rear antenna of the dual-antenna GPS board are respectively fixed at the front and rear positions of the central axis of the target vehicle roof and are parallel to the target vehicle body.
[0012] Furthermore, the data transmission module includes a vehicle-mounted image transmission radio and a remote-controlled image transmission radio, wherein the vehicle-mounted image transmission radio is connected to the FPGA development board via an RS232 interface, and the remote-controlled image transmission radio is connected to the remote control terminal via an RS232 interface.
[0013] Furthermore, the obstacle is a crater boundary or rubble that is larger than the maximum ground clearance of the target vehicle.
[0014] Beneficial effects:
[0015] 1. The present invention provides an obstacle recognition and target vehicle positioning system based on FPGA. When no control command from the remote control terminal is received within a set time period and the relative distance of the obstacle to the target vehicle is greater than the preset warning distance and the estimated contact time of the obstacle to the target vehicle is less than a set threshold, the on-board control module comprehensively processes relevant data and autonomously executes relevant action instructions to bypass the obstacle, thereby ensuring the safety of the target vehicle. It can be seen that in the present invention, when the user is unable to respond quickly due to a high vehicle speed or other factors that affect the remote control terminal displaying the video information in front of the target vehicle, the on-board control module receives the obstacle information and autonomously controls the target vehicle to avoid obstacles. The system has a higher degree of intelligence and improves the safety of the target vehicle in actual use.
[0016] 2. The present invention provides an obstacle recognition and target vehicle positioning system based on FPGA. By utilizing the advantages of FPGA such as high real-time performance, low power consumption, parallel processing, and strong scalability, the machine vision algorithm hardware is transplanted into FPGA, so that the on-board control module of the target vehicle can independently judge the obstacle information in front and receive GPS positioning information in real time when the target vehicle is traveling at high speed, and finally realize the functions of obstacle detection in the shooting range, target tracking, and real-time position transmission of the target vehicle, and the processing speed is faster, which solves the problem of slow speed of obstacle avoidance data analysis of high-speed target vehicles. Therefore, without significantly increasing the cost, the system can effectively assist the user to remotely control the target vehicle in actual target vehicle shooting training, thereby improving the safety of the target vehicle.
[0017] 3. The present invention provides an obstacle recognition and target vehicle positioning system based on FPGA, which uses a dual-antenna GPS board to perform differential positioning on the target vehicle, and can improve the accuracy of the heading angle and longitude and latitude coordinates during the driving process of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A principle block diagram of an obstacle recognition and target vehicle positioning system based on FPGA provided by the present invention. DETAILED DESCRIPTION
[0019] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0020] Taking into account the necessity of the current target vehicle design process, and considering the safety and security of the target vehicle, the present invention designs an obstacle recognition and target vehicle positioning system based on FPGA. Figure 1 As shown, it is mainly achieved through the following technical solutions:
[0021] The FPGA-based obstacle recognition and target vehicle positioning system includes a vehicle-mounted control module, a data transmission module and a remote control module, wherein the vehicle-mounted control module includes an FPGA development board, a binocular camera and a dual-antenna GPS board.
[0022] The binocular camera is used to collect original image information of the target vehicle's surrounding environment in real time; when the target vehicle's driving speed is greater than a set value and there is an obstacle in front of the target vehicle, the FPGA development board performs an image conversion operation on the original image information of the target vehicle's surrounding environment, that is, the FPGA development board uses a filtering algorithm to filter the original image information of the target vehicle's surrounding environment and performs Modelsim waveform simulation to obtain the relative distance and expected contact time of the obstacle relative to the target vehicle, and then transmits the relative distance and the expected contact time to the remote control terminal through a data transmission module for the user to observe, and then determines whether the user's control command is not received within a set time period and the relative distance is greater than a preset warning distance and the expected contact time is less than a set threshold. If so, the FPGA development board reduces the target vehicle's speed by adjusting the accelerator pedal opening and the brake pedal opening. When the target vehicle's speed is reduced to a set value, the FPGA development board performs a steering wheel turning action to eventually bypass the obstacle; wherein the obstacle is a crater boundary or gravel greater than the maximum ground clearance of the target vehicle.
[0023] The front antenna and rear antenna of the dual-antenna GPS board are respectively fixed at the front and rear positions of the central axis of the target vehicle roof and are parallel to the target vehicle body. At the same time, the dual-antenna GPS board is installed in the vehicle and connected to the FPGA development board; due to the characteristics of FPGA parallel processing, the FPGA development board can also receive GPS information in real time during obstacle avoidance. Specifically, the function of the dual-antenna GPS board is: differential positioning of the target vehicle position through the dual antennas, and transmitting the differential positioning information to the FPGA development board; the FPGA development board also obtains the target vehicle status information by connecting to the electronic control unit of the target vehicle, and transmits the target vehicle status information, differential positioning information, and the relative distance and estimated contact time of the obstacle relative to the target vehicle to the remote control terminal through the data transmission module, so that the user can check and grasp the target vehicle status at any time, and then complete the target shooting training task of the troops. Among them, the target vehicle status information includes vehicle information such as the current gear position, speed, lights, engine speed, steering wheel rotation angle, etc. of the target vehicle.
[0024] It should be noted that the vehicle control module is a system for controlling the movement of the target vehicle based on the FPGA development board. The development board chip model is Altera CycloneⅣ, and the peripheral interfaces are relatively rich, including camera interface, USB interface, RS232, 485 serial port, CAN port, etc. Among them, the camera interface is connected to the binocular camera, the RS232 serial port is connected to the dual-antenna GPS board, and the CAN port is connected to the original ECU (electronic control unit) of the target vehicle. When the target vehicle is in the process of driving, the binocular camera collects the image data in front of the vehicle body. After the camera position is fixed, it detects and tracks the obstacles in front of the target vehicle, and identifies obstacles such as gravel or craters through deep learning algorithms. After filtering / processing waves, the relative speed and time of the obstacles are formed. When the vehicle speed is too fast and the user cannot react, the FPGA development board automatically outputs deceleration, braking and turning commands to bypass obstacles; at the same time, the FPGA development board is connected to the dual-antenna GPS board, which can simultaneously receive and process the current target vehicle position information and transmit it to the remote control module.
[0025] Further, the binocular camera of the present invention is connected to the FPGA development board through the camera interface, and learns to identify obstacles in the pre-deep learning. In the actual test, the gravel and crater obstacles in front of the target vehicle can be directly identified; the FPGA development board receives data and parses it, and the dual-antenna GPS board is connected to the development board through the RS232 interface. The FPGA development board receives the protocol of GPVTG and GPHPD, and its content is the current latitude and longitude coordinate value, heading, speed, etc. of the target vehicle after differential; in addition, the FPGA development board is connected to the target vehicle ECU through the CAN bus to communicate, receive the current gear position, speed, lights, engine speed, steering wheel rotation angle and other vehicle information of the target vehicle, and send relevant control instructions to the relevant control unit of the target vehicle. The data transmission module includes a vehicle-mounted image transmission radio and a remote control image transmission radio, wherein the high-power vehicle-mounted image transmission radio is connected to the FPGA development board through RS232, and the self-organizing network remote control image transmission radio is connected to the remote control module through USB to RS232, and can transmit up to 15KM, and the transmission content includes the current status information of the target vehicle and the control message. The remote control module includes a host PC that runs the control program. The MFC interface of the program can read the target vehicle status information and display it in real time. Ignition, starting, braking, turning and other control commands can be issued remotely through the interface buttons.
[0026] It can be seen that by adopting the above technical solution of the present invention, the vehicle-mounted control module can autonomously judge the obstacle information ahead and receive GPS positioning information in real time when the target vehicle is traveling at high speed. By utilizing the advantages of FPGA such as high real-time performance, low power consumption, parallel processing, and strong scalability, the machine vision algorithm hardware is transplanted into FPGA, and finally the functions of target range obstacle detection, target tracking, and target vehicle real-time position transmission are realized. Under the premise of not significantly increasing the cost, the present invention can assist the user to remotely control the target vehicle in actual target vehicle shooting training, thereby improving the safety of the target vehicle.
[0027] Of course, the present invention may have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may certainly make various corresponding changes and modifications based on the present invention, but these corresponding changes and modifications should all fall within the scope of protection of the claims attached to the present invention.
Claims
1. An obstacle recognition and target vehicle positioning system based on FPGA, It is characterized in that Including vehicle control module, data transmission module and remote control terminal; When the target vehicle's speed is greater than the set value and there is an obstacle in front of the target vehicle, the on-board control module acquires the original image information of the target vehicle's surrounding environment and performs image conversion operations to obtain the relative distance of the obstacle to the target vehicle and the estimated contact time; The on-board control module transmits the relative distance and the estimated contact time to the remote control terminal through the data transmission module for the user to observe, and determines whether the user's control command is not received within the set time and the relative distance is greater than the preset warning distance and the estimated contact time is less than the set threshold. If so, the on-board control module reduces the speed of the target vehicle by adjusting the accelerator pedal opening and the brake pedal opening. When the target vehicle speed is reduced to the set value, the on-board control module executes the steering wheel turning action and finally bypasses the obstacle.
2. The FPGA-based obstacle recognition and target vehicle positioning system according to claim 1, It is characterized in that The vehicle control module includes an FPGA development board, a binocular camera and a dual-antenna GPS board; The binocular camera is used to collect original image information of the target vehicle's surrounding environment in real time; when the target vehicle's driving speed is greater than a set value and there is an obstacle in front of the target vehicle, the FPGA development board performs an image conversion operation on the original image information of the target vehicle's surrounding environment to obtain the relative distance and estimated contact time of the obstacle relative to the target vehicle, and then transmits the relative distance and estimated contact time to the remote control terminal through the data transmission module for the user to observe, and then determines whether the user's control command is not received within the set time and the relative distance is greater than the preset warning distance and the estimated contact time is less than the set threshold. If so, the FPGA development board reduces the target vehicle's speed by adjusting the accelerator pedal opening and the brake pedal opening. When the target vehicle's speed is reduced to the set value, the FPGA development board performs a steering wheel turning action to eventually bypass the obstacle; The dual-antenna GPS board performs differential positioning on the target vehicle through dual antennas, and transmits the differential positioning information to the FPGA development board; The FPGA development board also obtains the target vehicle status information by connecting to the target vehicle's electronic control unit, and transmits the target vehicle status information, differential positioning information, and the relative distance of the obstacle to the target vehicle and the estimated contact time to the remote control terminal through the data transmission module for the user to view at any time.
3. An obstacle recognition and target vehicle positioning system based on FPGA as claimed in claim 2, It is characterized in that The image conversion operation is as follows: the FPGA development board uses a filtering algorithm to perform filtering processing on the original image information of the target vehicle's surrounding environment and Modelsim waveform simulation to obtain the relative distance of the obstacle to the target vehicle and the estimated contact time.
4. The FPGA-based obstacle recognition and target vehicle positioning system as claimed in claim 2, It is characterized in that The front antenna and the rear antenna of the dual-antenna GPS board are respectively fixed at the front and rear positions of the central axis of the target vehicle roof and are parallel to the target vehicle body.
5. An obstacle recognition and target vehicle positioning system based on FPGA as claimed in any one of claims 2 to 4, It is characterized in that The data transmission module includes a vehicle-mounted image transmission radio and a remote-controlled image transmission radio, wherein the vehicle-mounted image transmission radio is connected to the FPGA development board via an RS232 interface, and the remote-controlled image transmission radio is connected to the remote control terminal via an RS232 interface.
6. An obstacle recognition and target vehicle positioning system based on FPGA as claimed in any one of claims 1 to 4, It is characterized in that The obstacle is a crater boundary or gravel larger than the maximum ground clearance of the target vehicle.
