Collision distance calculation method and system based on fusion of ultrasound wave and camera

Abstract

The invention provides a collision distance calculation method and system based on fusion of an ultrasound wave and a camera. On the basis of obstacle detection based on ultrasound and camera fusion,different types of obstacles such as vehicles and pedestrians, pure ultrasound waves are obtained; collision distances are calculated respectively according to vehicle parameters, turning radiuses, vehicle speeds, and different types of obstacle information; areas of interest are selected in different driving directions and turning directions; and distance of all obstacles in the areas of interest are minimized to obtain the fused collision distances. According to the invention, with the existing ultrasonic sensor, all-around CMOS camera, integrated parking controller and all-around controller in a current vehicle, the relative position accuracy of detection is improved and the obstacle detection reliability and detection distances are enhanced. The collision distance calculation methodand system have advantages of reliable detection, high accuracy, high scene adaptability, and moderate cost; and the adaptability of the low-speed auxiliary system is improved effectively.

Description

technical field [0001] The invention relates to a low-speed assisted driving system, in particular to a collision distance calculation strategy for low-speed automatic emergency braking based on ultrasonic and camera fusion. Background technique [0002] The automatic emergency braking function in the low-speed driving assistance system can perform emergency braking on the relative relationship between the vehicle and obstacles below 10km / h to avoid collisions. The control process is mainly distance control, so the calculation of the distance is very important. An inaccurate distance calculation can lead to the braking being triggered by mistake, or the braking being triggered too late to avoid the risk of a collision. At present, the main method to solve this problem is to use the ultrasonic sensors installed on the front and rear bumpers of the car to send ultrasonic waves in real time. When the ultrasonic waves are reflected by obstacles, they are received by adjacent se...

AI Technical Summary

Problems solved by technology

[0005] 1. Based on dual CCD cameras + multi-single-line lidar for high-speed control, the actual ultrasonic sensor does not participate in the fusion of camera and lidar information

[0006] 2. Only use ultrasonic radar information for low-speed collision avoidance protection, fail to identify the type of obstacles, and have the defects of weed braking or pedestrian braking

[0007] 3. The laser radar, binocular ranging sensor, CCD camera, and processor used in the system are costly, and are mainly used in the operation of small batches and limited sites, which is not conducive to the promotion and application of mass production;

[0008] 4. Applied in limited scenarios such as high-speed driving, drones, etc., without considering the different complex scenarios of actual vehicle driving (rural early grass, cobblestones, traffic congestion, ground and underground and other different lighting effects have a great impact on the detection results)

[0009] 5. The high-speed collision time algorithm only considers the collision between the center point of the vehicle and the obstacle tracking point, and does not consider the influence of different collision positions such as rear-end collisions, side collisions, and oblique collisions that may occur at low speeds on the control;

[0010] 6. Does not consider the impact of the driver's manipulation on the collision distance and collision time

Images