一种新型的基于行人检测与行走方向识别的辅助驾驶安全系统的设计与开发

Road traffic accidents are a serious problem around the world, where the cost of human life is impossible to evaluate, and cause massive and continuous government expenditure. Different solutions have been proposed to reduce the effects of accidents, one of which, Driver Assistance Systems, as their name suggest, assist the driver by providing vital information about the traffic environment or by acting under specific circumstances to safeguard the occupants of the vehicle, or to facilitate driving. In this research, we present a practical approach to the problem. Pedestrian protection is a crucial component of driver assistance systems. Our aim is to develop a video-based driver assistance system for the detection of the potential dangerous situation, in order to warn the driver. We address the problem of detecting pedestrian in real-world scenes and estimating walking direction with camera from a moving vehicle. The challenge is of considerable complexity due to the varying appearance of people (e.g., clothes, size, pose, shape, etc.), and the unstructured moving environments that urban scenarios represent. In addition, the required performance is demanding both in terms of computational time and detection rates. Considering all the available cues for predicting the possibility of collision is very important. The "direction" in which the pedestrian is facing is one of the most important cues to predict where the pedestrian may move in the future. Consequently, we construct and propose a five-stage method: (i) pedestrian detection, (ii) orientation estimation for single-frame.(iii) walking direction estimation for multi-frame.(ⅳ) pedestrian walking direction prediction. (ⅴ) calculation the probability of the collision between the pedestrian and the vehicle.

随着汽车数量的激增，交通事故呈不断上升趋势，交通安全越来越受到广泛关注，尤其汽车-行人相撞引起交通事故是导致行人死亡的一个主要原因。因此，研究汽车辅助驾驶安全系统，为汽车提供智能的辅助驾驶功能，从而为减少常规车辆因驾驶员主观因素造成的交通事故提供智能技术保障。 在本研究中，为了能够实现智能汽车辅助驾驶系统的普及，我们致力于装备价格更低廉的单眼摄像头，开发一个基于行人检测与行走方向预测的，具有实时性的汽车辅助驾驶安全系统，用来预测汽车-行人相撞的潜在危险，以及时提示给驾驶员，避免交通事故的发生。 为此，我们构建一个5层级联金字塔模型。(i) 基于单帧的行人检测, (ii)基于单帧的行人方向识别 (iii)基于视频序列的行人行走方向分析 (ⅳ) 预测行人未来的行走方向 (ⅴ)预测汽车-行人碰撞的潜在危险。整合这5层级联模型，设计与开发一个新型的基于行人检测与行走方向识别的辅助驾驶安全系统。

针对汽车辅助驾驶安全系统中运动目标识别的特征挖掘和识别分类等关键难点问题，本项目以车载视频中行人为对象，开展基于机器学习的汽车辅助驾驶安全技术中行人识别及行人行走方向分析的研究，通过研究，建立运动目标识别机理与机器学习分类算法的本征关系，提出结合行人行走方向信息的耦合新模型。本项目对于揭示汽车辅助驾驶安全技术中的运动目标识别中的特征提取等关键基础问题，发展运动目标识别理论与方法具有重要意义，研究成果在军事和民用领域具有重要的应用参考价值。