A fast and sub-pixel detector for grid-like target in camera calibration(快速子像素精度直线目标检测方法)

论文标题：快速的子像素精度直线目标检测方法(A fast and sub-pixel detector for grid-like target in camera calibration)

Cite: Le-Jun Shen, Zhun-Yu Ke. A fast and sub-pixel detector for grid-like target in camera calibration[J]. The International Symposium on Photonics and Optoelectronics(SOPO), 2010.

论文摘要：

Sub-pixel detection of target points is the performance bottleneck in camera calibration. Traditional algorithms are computational expensive or low precision when we do camera calibration in sport video analysis. In this paper, we propose a new algorithm to detect the grid-like target (i.e. tennis court in TV broadcasting). It has 3 parts: (1) color histogram based interested point classifier making our method faster; (2) sub-pixel refinement by non-linear least squares method improving the accuracy; (3) extended line scan using interested point as the start/end point finding the final line parameters. Results indicate that our detector is faster (<9ms), more accurate and requires less memory than Hough based algorithms if target is grid-like: "straight lines link together".

对靶标的子像素检测，是摄像机标定的性能瓶颈。传统的算法计算量大且精度低，尤其是对体育视频分析。本文提出了一种网格状目标（如电视画面中的网球场）的靶标检测新方法。它包含3部分：（1）基于色彩直方图的特征点分类器，提高了算法整体速度；（2）基于非线性最小二乘法Levenberg-Marquardt method的子像素优化方法，提高了算法准确度；（3）扩展的线扫描算法，寻找直线的最终参数。实验结果显示，在检测网格型目标时，本文的检测器比基于霍夫变换的一系列直线检测算法，速度更快（每帧<9毫秒），更准确（子像素精度）。

图1算法对比，分别是霍夫变换（Hough transform）和本文的方法（Our method）。

（Hough transform 霍夫变换）

（Our method 本文的方法）

全文下载(Download fulltext paper )：

Click Me 点击此处(文件大小992KB)

演示视频和程序下载(Download demo video and program)：

Click Me 点击此处(文件大小13.4MB)
contains executable program and video, for readers to assess the real-time line detection algorithm. 压缩包含可执行程序和视频，用于读者评估实时直线检测算法

关键词：霍夫变换；子像素精度；基于模型的视频分析；体育视频处理；摄像机标定;

Keywords: Hough transform; sub-pixel; model-based video analysis; Sport video processing; camera calibration;

本站的相关文章：

[1].Levenberg -Marquardt method算法教程（by shenlejun）