A Method of Extracting Corner Features from Laser Point Cloud Data

With the development of robot technology, the requirement of target recognition accuracy for depalletizing robot based on lidar is constantly improved. In order to solve the problems of large data acquisition error and low target recognition accuracy caused by environmental interference during lidar operation, a new corner feature extraction method is proposed in this paper. Firstly, based on the anomaly detection LOF algorithm, a data preprocessing method is designed to improve the accuracy of lidar data acquisition.; Then, the Douglas-Pucker algorithm is used for data segmentation to obtain the straight line segment features and corner features of the stacking object boundary. The corner features are further determined by re-judgment method to improve the accuracy of corner features. Finally, this paper designs a comparative experiment based on the data collected by lidar, and the experimental results verify the feasibility of the improved algorithm in this paper in terms of outlier removal and corner feature extraction.

Hali tarjima qilinmagan