不確実で部分観測可能な環境における能動的多カメラ監視のための意思決定論的協調制御
Decision-Theoretic Coordination and Control for Active Multi-Camera Surveillance in Uncertain, Partially Observable Environments
POMDPに基づき、遮蔽のある環境で複数の移動目標を追跡するため、能動カメラ群の協調制御を行う手法を提案し、実機カメラで有効性を示した論文。
著者: Prabhu Natarajan, Trong Nghia Hoang, Kian Hsiang Low, Mohan Kankanhalli
分類: cs.AI, cs.MA, cs.MM, cs.RO
原文アブストラクト
A central problem of surveillance is to monitor multiple targets moving in a large-scale, obstacle-ridden environment with occlusions. This paper presents a novel principled Partially Observable Markov Decision Process-based approach to coordinating and controlling a network of active cameras for tracking and observing multiple mobile targets at high resolution in such surveillance environments. Our proposed approach is capable of (a) maintaining a belief over the targets' states (i.e., locations, directions, and velocities) to track them, even when they may not be observed directly by the cameras at all times, (b) coordinating the cameras' actions to simultaneously improve the belief over the targets' states and maximize the expected number of targets observed with a guaranteed resolution, and (c) exploiting the inherent structure of our surveillance problem to improve its scalability (i.e., linear time) in the number of targets to be observed. Quantitative comparisons with state-of-the-art multi-camera coordination and control techniques show that our approach can achieve higher surveillance quality in real time. The practical feasibility of our approach is also demonstrated using real AXIS 214 PTZ cameras
