Deep Neural Networks that Reproduce Human Vision Perception While Driving
Deep Neural Networks that Reproduce Human Vision Perception While Driving
复制标题
驾驶时再现人类视觉感知的深度神经网络
DOI：
10.11351/jsaeronbun.53.1102
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
渡辺 英治
中科院分区：
文献类型：
--
作者：
江村 恒一;加藤 正隆;渡辺 英治
人的预测特性可能会影响交通事故因素，例如预测失败和对其他运动的疏忽。在本文中，我们提出了一种新的方法来模拟人类视觉如何在驾驶过程中预测驾驶环境，并使用包含预测编码的深度神经网络来阐明认知机制，预测编码是大脑皮层操作原理的领先理论之一。预测编码假设大脑的内部模型在任何时候都预测视觉世界，并且预测和实际感官输入之间的误差进一步完善了内部模型。
A human predictive characteristic may affect the traffic accident factors such as prediction failure and carelessness to other movements. In this paper, we propose a new approach to simulate how human vision predicts the driving environment during driving, and to clarify cognitive mechanisms, using deep neural networks that incorporate predictive coding, which is one of the leading theories as the operating principle of the cerebral cortex. Predictive coding assumes that the brain's internal models predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models.