《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (3): 909-915.DOI: 10.11772/j.issn.1001-9081.2023040416

• 多媒体计算与计算机仿真 • 上一篇    下一篇

自适应地平线约束下的车辆三维检测

王伟, 赵春辉(), 唐心瑶, 席刘钢   

  1. 长安大学 信息工程学院,西安 710018
  • 收稿日期:2023-04-13 修回日期:2023-06-30 接受日期:2023-07-05 发布日期:2023-12-04 出版日期:2024-03-10
  • 通讯作者: 赵春辉
  • 作者简介:王伟(1984—),男,江苏徐州人,讲师,博士,主要研究方向:计算机视觉、三维重建
    唐心瑶(1996—),女,江苏苏州人,博士研究生,主要研究方向:计算机视觉
    席刘钢(1999—),男,山西临汾人,硕士研究生,主要研究方向:计算机视觉。
  • 基金资助:
    国家自然科学基金资助项目(52002031);陕西省科技计划项目(2023-JC-YB-600);中央高校研究生教育教学研究校级项目(300103131033)

3D vehicle detection with adaptive horizon line constraints

Wei WANG, Chunhui ZHAO(), Xinyao TANG, Liugang XI   

  1. School of Information Engineering,Chang’an University,Xi’an Shaanxi 710018,China
  • Received:2023-04-13 Revised:2023-06-30 Accepted:2023-07-05 Online:2023-12-04 Published:2024-03-10
  • Contact: Chunhui ZHAO
  • About author:WANG Wei, born in 1984,Ph. D., lecturer. His research interests include computer vision, 3D reconstruction.
    TANG Xinyao, born in 1996, Ph. D. candidate. Her research interests include computer vision.
    XI Liugang, born in 1999, M. S. candidate. His research interests include computer vision.
  • Supported by:
    National Natural Science Foundation of China(52002031);Shaanxi Provincial Science and Technology Plan(2023-JC-YB-600);Central University Project for Graduate Education and Teaching Research at School Level(300103131033)

摘要:

目前较为常用的基于单目视觉的车辆三维检测方法是目标检测结合几何约束的方法,但是几何约束中消失点的位置对结果影响很大。为了获取更加准确的约束条件,提出一种基于地平线检测的车辆三维检测算法。首先,利用车辆图片获取消失点的相对位置,将车辆图片预处理至合适大小;然后,将经过预处理的车辆图片送入消失点检测网络,获得消失点信息热力图组,回归出消失点信息,并计算得出地平线信息;最后,根据地平线信息构建几何约束,在约束空间内对车辆初始尺寸迭代优化计算精确的车辆三维信息。实验结果表明,所述地平线求解算法能够获得更准确的地平线,与随机森林的方法相比,曲线下面积(AUC)提升1.730个百分点;同时,所提地平线约束能够有效地限制车辆三维信息,与使用对角线和消失点约束的算法相比,车辆三维信息的平均精度提升2.201个百分点。可见地平线可以作为几何约束在路侧单目相机的场景下求解车辆三维信息。

关键词: 目标检测, 车辆三维检测, 钻石空间变换, 消失点, 地平线

Abstract:

The commonly used monocular vision-based vehicle 3D detection method at present combines object detection with geometric constraint. However, the position of the vanishing point in the geometric constraint has a significant impact on the results. To obtain more accurate constraint conditions, a 3D vehicle detection algorithm based on horizon line detection was proposed. First, the relative position of the vanishing point was obtained using the vehicle image, and the vehicle image was preprocessed to an appropriate size. Then, the preprocessed vehicle image was fed into a vanishing point detection network to obtain a set of heatmaps indicating the vanishing point information. The vanishing point information was regressed, and the horizon information was calculated. Finally, geometric constraint was constructed based on the horizon line information, and the initial dimensions of the vehicle were iteratively optimized within the constrained space to calculate the precise 3D information of the vehicle. The experimental results demonstrate that the proposed horizon line solving algorithm obtains more accurate horizon lines. Compared to the random forest method, there is an AUC (Area Under Curve) improvement of 1.730 percentage points. Simultaneously, the introduced horizon line constraint effectively restricts the 3D vehicle information, resulting in an average precision improvement of 2.201 percentage points compared to the algorithm using diagonal and vanishing point constraint. It can be observed that the horizon line serves as a geometric constraint for solving vehicle 3D information in the context of roadside monocular camera perspectives.

Key words: object detection, 3D vehicle detection, diamond space transformation, vanishing point, horizon line

中图分类号: