人間の注意に基づくグラフ畳み込みネットワークを用いた歩行者軌道予測
AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention
視線データから学習した注意重みと視野制約をGCNに組み込み、混雑度が異なる群衆シーンでの歩行者軌道予測を高精度化した研究。
著者: Congcong Liu, Yuying Chen, Ming Liu, Bertram E. Shi
分類: cs.CV, cs.RO
原文アブストラクト
Pedestrian trajectory prediction is a critical yet challenging task, especially for crowded scenes. We suggest that introducing an attention mechanism to infer the importance of different neighbors is critical for accurate trajectory prediction in scenes with varying crowd size. In this work, we propose a novel method, AVGCN, for trajectory prediction utilizing graph convolutional networks (GCN) based on human attention (A denotes attention, V denotes visual field constraints). First, we train an attention network that estimates the importance of neighboring pedestrians, using gaze data collected as subjects perform a bird's eye view crowd navigation task. Then, we incorporate the learned attention weights modulated by constraints on the pedestrian's visual field into a trajectory prediction network that uses a GCN to aggregate information from neighbors efficiently. AVGCN also considers the stochastic nature of pedestrian trajectories by taking advantage of variational trajectory prediction. Our approach achieves state-of-the-art performance on several trajectory prediction benchmarks, and the lowest average prediction error over all considered benchmarks.
