obendidi/Tracking-with-darkflow

support for KCF

Open

#15 opened on Nov 14, 2017

View on GitHub
 (8 comments) (2 reactions) (0 assignees)Python (523 stars) (179 forks)batch import
help wanted

Description

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?

Contributor guide

Tech stack
pythontensorflow
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PythonOpenCV basicsYOLO v2TensorFlow
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
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.