The invention discloses an obstacle recognition method applied to automatic parking. The conception of the method is that multi-dimensional image features are extracted from pictures shot by a fisheye camera, and a plurality of established obstacle types are recognized in combination with a classification algorithm in a machine learning mechanism. According to the method, the problem that the recognition rate of obstacle detection in an existing scheme is low is effectively avoided, the application scene of automatic parking is widened to a certain extent, and the function experience of automatic parking is improved.
本发明公开了一种应用于自动泊车的障碍物识别方法,本发明的构思在于,从鱼眼相机拍摄的图片中提取多维度的图像特征,并结合机器学习机制中的分类算法识别出既定的若干种障碍物类型。本发明有效规避了现有方案对于障碍物检测的识别率较低的问题,并且在一定程度上扩宽了自动泊车的应用场景,改善了自动泊车的功能体验。
Obstacle identification method applied to automatic parking
应用于自动泊车的障碍物识别方法
2021-08-17
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
Obstacle identification method and device in automatic parking process
European Patent Office | 2024
|Automatic parking obstacle identification method and device, electronic equipment and medium
European Patent Office | 2023
|Automatic parking dynamic obstacle detection method and device
European Patent Office | 2024
|Obstacle collision avoidance method based on automatic parking system
European Patent Office | 2020
|