Real-Time Car Detection-Based Depth Estimation Using Mono Camera
Real-Time Car Detection-Based Depth Estimation Using Mono Camera
复制标题
使用单色相机进行基于实时汽车检测的深度估计
DOI：
10.1109/icm.2018.8704024
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
H. Mostafa
中科院分区：
文献类型：
--
作者：
I. Mohamed Elzayat;M. Ahmed Saad;M. Mostafa;R. Mahmoud Hassan;Hossam Abd El Munim;M. Ghoneima;M. S. Darweesh;H. Mostafa
对象深度估计是许多视觉分析系统的基石。近年来，这一领域取得了长足的进展，但如何在真实视频中实现鲁棒、高效、精确的深度估计仍然是一个挑战。本文采用的方法是使用单镜头摄像机来估计周围汽车的距离。在检测过程中使用YOLO（You Only Look Once），通过生成围绕对象的边界框，然后确定距离与边界框的尺寸（高度，宽度）之间的反比相关性。得到研究变量之间的精确方程，因变量为距离，自变量为YOLO边界框的高度和宽度。在回归模型中，采用多元回归技术，以避免异方差和多重共线性问题。实现了每秒23帧的实时检测，深度估计精度为80.4%。
Object depth estimation is the cornerstone of many visual analytics systems. In recent years there is a considerable progress has been made in this area, while robust, efficient, and precise depth estimation in the real-world video remains a challenge. The approach utilized in this presented paper is to estimate the distance of surrounding cars using a mono camera. Using YOLO (You Only Look Once) in the detection process, by generating a boundary box surrounding the object, then an inversion proportional correlation between the distance and the boundary box’s dimensions (height, width) is ascertained. Getting the exact equation between the studied variables; the dependent variables are the distance, and independent variable is the height and width of YOLO boundary box. In the regression model, multiple regression techniques were acclimated to evade heteroskedasticity and multi-collinearity problems. Achieving a real-time detection with a 23 FPS (Frame Per Second) and depth estimation accuracy 80.4%.
DOI：
--
发表时间：
2005
期刊：
影响因子：
--
作者：
池山豊;永田靖;永田靖;永田 靖(編著);Yasushi Nagata(eds.)
通讯作者：
Yasushi Nagata(eds.)