Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios

TL;DR

This paper introduces a lidar-only vehicle detection and tracking system using a CNN for point cloud classification, demonstrating improved efficiency and competitive accuracy over traditional geometric methods in autonomous driving scenarios.

Contribution

The paper presents a novel lidar-based detection and tracking system employing CNNs for point cloud classification, with a thorough evaluation on the KITTI dataset.

Findings

CNN-based detector outperforms geometric approaches

Uses only 4% of data compared to image-based methods

Achieves competitive detection accuracy

Abstract

Vehicle detection and tracking is a core ingredient for developing autonomous driving applications in urban scenarios. Recent image-based Deep Learning (DL) techniques are obtaining breakthrough results in these perceptive tasks. However, DL research has not yet advanced much towards processing 3D point clouds from lidar range-finders. These sensors are very common in autonomous vehicles since, despite not providing as semantically rich information as images, their performance is more robust under harsh weather conditions than vision sensors. In this paper we present a full vehicle detection and tracking system that works with 3D lidar information only. Our detection step uses a Convolutional Neural Network (CNN) that receives as input a featured representation of the 3D information provided by a Velodyne HDL-64 sensor and returns a per-point classification of whether it belongs to a vehicle or not. The classified point cloud is then geometrically processed to generate observations for a multi-object tracking system implemented via a number of Multi-Hypothesis Extended Kalman Filters (MH-EKF) that estimate the position and velocity of the surrounding vehicles. The system is thoroughly evaluated on the KITTI tracking dataset, and we show the performance boost provided by our CNN-based vehicle detector over a standard geometric approach. Our lidar-based approach uses about a 4% of the data needed for an image-based detector with similarly competitive results.