Time-space domain obstacle detection method and system for complex road scene

Abstract

The invention discloses a time-space domain obstacle detection method and system for a complex road scene, and the method comprises the steps: collecting point cloud data and a detection result of a historical frame, and carrying out the preprocessing of the point cloud data; detecting the preprocessed point cloud data by adopting a deep learning method to obtain known type target information, and detecting by adopting a grid occupying method to obtain unknown type target information; performing spatial domain association fusion on the known type target and the unknown type target to obtain a detection result of the current frame; performing motion estimation on the detection result of the historical frame to obtain a motion estimation result of the historical frame; and performing time domain fusion based on the detection result of the current frame and the motion estimation result of the historical frame to update the detection result of the current frame target. According to the method, various obstacles of known types and unknown types appearing on the road can be better detected, and the method has better performance on detection of shielded targets, small-size targets and the like.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a time-space domain obstacle detection method and system for complex road scenes. Background technique [0002] One of the key technologies of autonomous driving is that the vehicle acquires and processes information about the surrounding environment through various sensors, so that the vehicle can plan an optimal path to reach the destination; in recent years, deep learning has been widely used in the field of autonomous driving perception. It has been widely used, and gradually shows the trend of replacing various traditional perception methods. [0003] Deep learning is data-driven, and replaces various feature extraction algorithms in traditional methods through model design, and shows good generalization performance; the most commonly used deep learning method in the field of perception is the supervised method, although such methods It is very mature, but there a...

AI Technical Summary

Problems solved by technology

[0003] Deep learning is data-driven, and replaces various feature extraction algorithms in traditional methods through model design, and shows good generalization performance; the most commonly used deep learning method in the field of perception is a supervised method, although such methods It is very mature, but there are also some shortcomings. For example, in the case of some rare samples, severe occlusion, etc., the model is usually difficult to give accurate results. The problem that the target cannot be effectively detected; in complex road scenes, there are often situations where vehicles block each other, which greatly increases the difficulty of target detection

Images