Target detection and motion state estimation method based on vision and laser radar

Abstract

The invention discloses a target detection and motion state estimation method based on vision and laser radar, and the method comprises the following steps: 1, installing the positions of a camera andthe laser radar, carrying out the calibration between every two binocular cameras, and carrying out the combined calibration between a left camera in front of a vehicle and the laser radar; fusing and supplementing the sparse point clouds respectively generated by the stereoscopic vision system and the laser radar to form a global three-dimensional point cloud graph; 2, detecting the two-dimensional image and the three-dimensional point cloud by using a deep learning method, and fusing an image target three-dimensional motion state generated by stereoscopic vision with a laser radar three-dimensional point cloud target to obtain comprehensive target three-dimensional feature points; and 3, tracking the target by utilizing Kalman filtering according to the three-dimensional feature pointsof the target, and analyzing the motion state of the target. The key of the method lies in the fusion of vision and laser radar sensors, and improves the sensing capability of an intelligent automobile for the surrounding environment.

Description

technical field [0001] The invention belongs to the field of intelligent vehicle environment perception, and specifically designs a method for detecting vehicles, pedestrians and other targets and estimating motion states based on vision and laser radar under complex road conditions in mountainous areas. Background technique [0002] With the rapid development of artificial intelligence, machine vision and other fields in recent years, smart cars have become an important field of research and development in academia and industry. For smart cars, the ability to sense and understand the surrounding environment in real time cannot be missed. Only when the environment perception technology is accurate, real-time, and reliable, can the vehicle plan the correct traffic path, and then realize the safe automatic driving. Therefore, the environment perception technology is the basic requirement and prerequisite for the safe driving of smart cars. [0003] Environmental perception te...

AI Technical Summary

Problems solved by technology

For example, lidar has the advantages of long detection distance and high detection accuracy, but lidar does not have the function of visual recognition; while visual sensor makes up for the disadvantage of lidar in identifying objects, it can capture the details of objects, such as brightness, texture, etc. features, but the visual sensor is affected by the weather conditions, and can only detect and identify targets in good weather, and the detection distance of objects is limited, and the accuracy is not high

Images