全天候対応の統合知覚:自律走行車のためのデータ関連付け・追跡・分類
All Weather Perception: Joint Data Association, Tracking, and Classification for Autonomous Ground Vehicles
自律走行車向けに、データ関連付け・物体追跡・物体分類をリアルタイムで同時に解く確率的知覚アルゴリズムを提案し、カメラ・LiDAR・レーダーを統合して悪天候・悪照明下での性能を実験的に評価した。
著者: Peter Radecki, Mark Campbell, Kevin Matzen
分類: eess.SY, cs.CV, cs.LG, cs.RO, cs.SY
原文アブストラクト
A novel probabilistic perception algorithm is presented as a real-time joint solution to data association, object tracking, and object classification for an autonomous ground vehicle in all-weather conditions. The presented algorithm extends a Rao-Blackwellized Particle Filter originally built with a particle filter for data association and a Kalman filter for multi-object tracking (Miller et al. 2011a) to now also include multiple model tracking for classification. Additionally a state-of-the-art vision detection algorithm that includes heading information for autonomous ground vehicle (AGV) applications was implemented. Cornell's AGV from the DARPA Urban Challenge was upgraded and used to experimentally examine if and how state-of-the-art vision algorithms can complement or replace lidar and radar sensors. Sensor and algorithm performance in adverse weather and lighting conditions is tested. Experimental evaluation demonstrates robust all-weather data association, tracking, and classification where camera, lidar, and radar sensors complement each other inside the joint probabilistic perception algorithm.
