MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning
MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning
复制标题
DOI：
10.1109/iccv48922.2021.01293
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Sonia Baee;Erfan Pakdamanian;Inki Kim;Lu Feng;Vicente Ordonez;Laura Barnes
中科院分区：
文献类型：
--
作者：
Sonia Baee;Erfan Pakdamanian;Inki Kim;Lu Feng;Vicente Ordonez;Laura Barnes
受人类视觉注意力的启发，我们提出了一种新颖的逆强化学习公式，使用最大熵深度逆强化学习（MEDIRL）来预测驾驶员在容易发生事故的情况下的视觉注意力。 MEDIRL 通过从专注的驾驶员记录的眼睛注视模式中学习任务敏感的奖励函数来预测可带来最大奖励的注视位置。此外，我们还推出了 EyeCar，这是一个针对事故多发情况的新驾驶员注意力数据集。我们进行了全面的实验，以在三个常见基准上评估我们提出的模型：（DR(eye)VE、BDD-A、DADA-2000）和我们的 EyeCar 数据集。结果表明，MEDIRL 优于现有的注意力预测模型，并实现了最先进的性能。我们提出了广泛的消融研究，以提供对我们提出的模型的不同特征的更多见解。1
Inspired by human visual attention, we propose a novel inverse reinforcement learning formulation using Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) for predicting the visual attention of drivers in accident-prone situations. MEDIRL predicts fixation locations that lead to maximal rewards by learning a task-sensitive reward function from eye fixation patterns recorded from attentive drivers. Additionally, we introduce EyeCar, a new driver attention dataset in accident-prone situations. We conduct comprehensive experiments to evaluate our proposed model on three common benchmarks: (DR(eye)VE, BDD-A, DADA-2000), and our EyeCar dataset. Results indicate that MEDIRL outperforms existing models for predicting attention and achieves state-of-the-art performance. We present extensive ablation studies to provide more insights into different features of our proposed model.1