Advanced driver assistance systems (ADAS) become an integral part of almost all modern automotive systems. ADAS have been evolving over a decade and the expansion of vision-based ADAS is quite rapid mainly due to the recent advancements in camera technologies. Most of the vision-based ADAS applications have been developed focusing on structured environment parameters and being tested adequately for those environments whereas they cannot be applied with their current framework as such for non-structured environments due to various limitations. This study presents a comprehensive overview of challenges in expanding the vision-based ADAS for non-structured environments. The authors have proposed a segmentation detection method for pedestrians and cyclists in a non-structured road environment to improve the accuracy of the popular deep learning networks. This method uses upper body detection and a pairing technique that improves the average precision significantly without consuming much computational resources. This approach would help to transform the structured environment ADAS to non-structured environments with minimal modifications. With the proposed approach, they are able to increase the accuracy of certain object classes up to 49% for various popular deep learning networks.

中文翻译：

---

在非结构化环境中扩展基于视觉的ADAS

先进的驾驶员辅助系统（ADAS）成为几乎所有现代汽车系统的组成部分。ADAS已经发展了十多年，基于视觉的ADAS的发展相当迅速，这主要归功于摄像头技术的最新发展。大多数基于视觉的ADAS应用程序已针对结构化环境参数进行了开发，并已针对这些环境进行了充分的测试，但是由于各种限制，它们无法与当前框架一起用于非结构化环境。这项研究全面概述了在非结构化环境中扩展基于视觉的ADAS所面临的挑战。作者提出了一种在非结构化道路环境中针对行人和骑自行车者的分段检测方法，以提高流行的深度学习网络的准确性。此方法使用上身检测和配对技术，可在不消耗大量计算资源的情况下显着提高平均精度。这种方法将有助于以最小的修改将结构化环境ADAS转换为非结构化环境。通过提出的方法，对于各种流行的深度学习网络，它们能够将某些对象类别的准确性提高到49％。这种方法将有助于以最小的修改将结构化环境ADAS转换为非结构化环境。通过提出的方法，对于各种流行的深度学习网络，它们能够将某些对象类别的准确性提高到49％。这种方法将有助于以最小的修改将结构化环境ADAS转换为非结构化环境。通过提出的方法，对于各种流行的深度学习网络，它们能够将某些对象类别的准确性提高到49％。