obendidi/Tracking-with-darkflow

support for KCF

Open

#15 创建于 2017年11月14日

在 GitHub 查看
 (8 评论) (2 反应) (0 负责人)Python (523 star) (179 fork)batch import
help wanted

描述

TODO : add support for opencv trackers (MIL,KCF,TLD,MEDIANFLOW) Thank you very much for releasing code. Could you give me some introductions about it? image Should I just embed the KCF to here?

贡献者指南

技术栈
pythontensorflow
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
PythonOpenCV basicsYOLO v2TensorFlow
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
30
研究方向
The issue asks to add support for OpenCV trackers (MIL, KCF, TLD, MEDIANFLOW) to the existing tracking system. The user posted a screenshot hinting at a specific location in the code to embed KCF. Currently, the repository uses YOLO v2 and deep sort with TensorFlow. To proceed, examine the current tracking pipeline in the codebase, likely in Python files. Look for the tracker integration point suggested in the screenshot. Review the existing comments for any guidance or unresolved questions. Then implement a solution to call OpenCV's tracker.create() with the desired tracker type and integrate it with the existing detection pipeline.