# OpticalFlow

**Repository Path**: Lee_Chao/OpticalFlow

## Basic Information

- **Project Name**: OpticalFlow
- **Description**: A Python implementation of the Kanade–Lucas–Tomasi (KLT) feature tracker
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2019-11-12
- **Last Updated**: 2020-12-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Project 3b: Optical Flow & Visual Tracking

## Getting Started
### Dependency
 - OpenCV
 - numpy
 - scipy
 - scikit-image
### Usage

Run `objectTracking.py` to evaluate.

## Method
### Step1 Generate Feature Points
![feature detection](demo/features.png)

### Step2 Estimate Direction of Motion
![optical flow](demo/opticalflow.png)

### Step3 Estimate and Apply Geometric Transform
![affine transformation](demo/affinetransformation.png)

Reject outliers by thresholing.