Tracking Learning Detecting-TLD 学习笔记1

来源：互联网发布：大数据时代读后感5000 编辑：程序博客网时间：2024/05/17 20:02

上学期就从某位大神（http://blog.csdn.net/zouxy09/article/details/7893011）的CSDN博客中看到TLD算法，感觉挺不错的，一直关注着，现在需要做视频目标跟踪了，现在开始正式研究它，国内有不少朋友，在看ZK的TLD算法，算是自己不寂寞了。这里写下的权当自己学习经历。

这是TLD1.0版本的介绍，地址https://github.com/arthurv/OpenTLD

TLD 1.0 (Predator)----------------------------------------------------------------------------TLD is an algorithm for tracking of unknown objects in unconstrained video streams. The object of interest is defined by a bounding box in a single frame. TLD simultaneously tracks the object, learns its appearance and detects it whenever it appears in the video.1. License: GPL 2. Project: http://info.ee.surrey.ac.uk/Personal/Z.Kalal/tld.html3. Wiki: https://github.com/zk00006/OpenTLD/wiki.4. Group: http://groups.google.com/group/opentld. @article{Kalal2012, author = {Kalal, Z and Mikolajczyk, K and Matas, J}, journal = {Pattern Analysis and Machine Intelligence}, title {Tracking-learning-detection}, year = {2012}}----------------------------------------------------------------------------(c) 2011 Zdenek Kalal

0 0