Search - tracker

Search - tracker - List

[Video Capture] LaserFollowingCamera DL : 1: object tracker laser
Date : 2026-01-10 Size : 476kb User : mohamed
[Video Capture] opengazer-0.1.2.tar DL : 0: 眼球跟踪程序，使用普通的家用摄像头，编译环境为debian或ubuntu，或参考README安装必要的包，opensuse也测试通过-Eye tracker, using ordinary household camera, build environment to debian or ubuntu, or the README to install the necessary packages, opensuse also tested by
Date : 2026-01-10 Size : 133kb User : fengDragon
[Video Capture] OpenTLD-master DL : 0: TLD算法代码。TLD(Tracking-Learning-Detection)是英国萨里大学的一个捷克籍博士生Zdenek Kalal在其攻读博士学位期间提出的一种新的单目标长时间（long term tracking）跟踪算法。该算法与传统跟踪算法的显著区别在于将传统的跟踪算法和传统的检测算法相结合来解决被跟踪目标在被跟踪过程中发生的形变、部分遮挡等问题。同时，通过一种改进的在线学习机制不断更新跟踪模块的“显著特征点”和检测模块的目标模型及相关参数，从而使得跟踪效果更加稳定、鲁棒、可靠。-The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object s location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning and detection. The tracker follows the object frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates detector s errors and updates it to avoid these errors in the future. We study how to identify detector s errors and learn them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of experts : (i) P-expert estimates missed detections, and (ii) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time
Date : 2026-01-10 Size : 16.72mb User :
[Video Capture] colortracker DL : 0: color tracker in qt, can detect defferent colar objects and track them
Date : 2026-01-10 Size : 2.25mb User : kiezer