http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김수연(Suyeon Kim),권순웅(Sunwoong Kwon),김명준(Myungjoon Kim),김정하(Jungha Kim) 한국자동차공학회 2019 한국자동차공학회 학술대회 및 전시회 Vol.2019 No.11
Autonomous vehicles requires quick and accurate perception of the surrounding environment. Thus many researches on perception system for autonomous vehicles using various sensors such as LiDAR, RADAR, and Camera are being conducted. In this paper, we propose a LiDAR based vehicle classification method using deep learning for autonomous vehicles. The proposed classification method firstly eliminates the ground data of the raw point cloud to reduce the amount of data. After that, an squeezeseg v2 algorithm is conducted for the classification of vehicle and euclidean clustering is applied to robustly correct the classified vehicle data. As a result, we have classified the vehicles robustly using this algorithm, and it can be used in the situation such as highway.