Lidar based Detection and Classification of Pedestrians and Vehicles\n Using Machine Learning Methods

2019/06/11 by Farzad Shafiei Dizaji, Dizaji, Farzad Shafiei
Engineering · Computer Science · Physics and Astronomy · #Autonomous Vehicle Technology and Safety #Advanced Neural Network Applications #Advanced Optical Sensing Technologies

paper · pdf · doi:10.48550/arxiv.1906.11899

Abstract

The goal of this paper is to classify objects mapped by LiDAR sensor into\ndifferent classes such as vehicles, pedestrians and bikers. Utilizing a\nLiDAR-based object detector and Neural Networks-based classifier, a novel\nreal-time object detection is presented essentially with respect to aid\nself-driving vehicles in recognizing and classifying other objects encountered\nin the course of driving and proceed accordingly. We discuss our work using\nmachine learning methods to tackle a common high-level problem found in machine\nlearning applications for self-driving cars: the classification of pointcloud\ndata obtained from a 3D LiDAR sensor.\n

Related

• Combining LiDAR Space Clustering and Convolutional Neural Networks for\n Pedestrian Detection
• Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving
• Real-Time And Robust 3D Object Detection with Roadside LiDARs
• MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views
• High-level camera-LiDAR fusion for 3D object detection with machine learning