欢迎访问《汽车安全与节能学报》,

汽车安全与节能学报 ›› 2020, Vol. 11 ›› Issue (3): 337-344.DOI: 10.3969/j.issn.1674-8484.2020.03.009

• • 上一篇    下一篇

用于 ADAS 实时目标车辆检测的改进 SSD 算法

焦鑫 1 ,杨伟东 1* ,刘全周 2 ,李占旗 2 ,贾鹏飞 2   

  1. (1. 河北工业大学 机械学院,天津 300130,中国; 2. 中国汽车技术研究中心有限公司,天津 300300,中国)
  • 收稿日期:2020-05-15 出版日期:2020-09-30 发布日期:2020-10-20
  • 通讯作者: 杨伟东,教授。E-mail :yangweidong@hebut.edu.cn。
  • 作者简介:第一作者 / First author : 焦鑫 (1995—),男(汉),河北,硕士研究生。E-mail :jiaoxin199501@163.com。
  • 基金资助:
    天津市科技计划项目(18YFCZZC00150);天津市科技计划项目(17YDLJGX00020)。

Improved SSD algorithm for real time target vehicle detection in ADAS

JIAO Xin1 , YANG Weidong1*, LIU Quanzhou2 , LI Zhanqi2 , JIA Pengfei2   

  1. (1. School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China; 2. China Automotive Technology and Research Center Co., Ltd, Tianjin 300300, China)
  • Received:2020-05-15 Online:2020-09-30 Published:2020-10-20

摘要: 以实际交通场景中存在重叠小目标车辆为重点,为提升汽车辅助驾驶系统(ADAS)对目标车 辆检测的准确性,建立了一种实时目标车辆检测改进算法 SSD-P。该算法基于 2 种方法:1) 通过增加 小目标特征的提取数量,提出了一种浅层特征图像分辨率重建的方法;2) 在非极大抑制中嵌入特征向 量进行二次判定方法,以克服单发多盒探测器 (SSD) 算法对小目标检测精度不高、重叠目标检测能力 弱的问题。在 PASCAL VOC2012 数据集、虚拟交通场景以及实际交通场景中,进行了相关实验验证。 结果表明:用该 SSD-P 算法进行目标车辆检测的平均精度(mAP)为 92.4%,比改进前的 SSD 算法 精度提升了4.8%。因此,该改进算法能够改善 ADAS 的准确性。

关键词: 汽车辅助驾驶系统(ADAS);实时车辆检测, 单发多盒探测器 (SSD) 算法;小目标;重叠目标

Abstract: An improved real-time target-vehicles detection algorithm SSD-P was developed focusing on overlapping small target-vehicles in actual traffic scenes to improve the detection accuracy using an advanced driver assistance system (ADAS). This algorithm was based on two methods: 1) a resolution reconstruction method of shallow feature image was proposed by increasing the number of small target feature extraction; 2) a quadratic determination method with embedded feature vector in non-maximal suppression to overcome the problems such as low precision and weak ability of overlapping target detection in a single shot multi-box detector (SSD) algorithm. Experiments were carried out in PASCAL VOC2012 data set, virtual traffic scene and real traffic scene. The results show that the mean accuracy precision (mAP) for target vehicle detection is 92.4% by using SSD-P algorithm, this is 4.8% higher than that by using the original SSD algorithm. Therefore, the SSD-P algorithm can improve the accuracy of ADAS.  

Key words: advanced driver assistance system, ADAS, real-time vehicle detections, single shot multi-box detector (SSD) algorithm, small targets, overlapping objectives, vehicle detections

中图分类号: