This project was cloned from Udacity and modified by me(olala7846@gmail.com).
Created a vehicle detection and tracking pipeline with OpenCV, histogram of oriented gradients (HOG), and support vector machines (SVM). Optimized and evaluated the model on video data from a automotive camera taken during highway driving.
- Calibrate the camera using OpenCV with chessboard images
- Detect lane lines using perspective transform and edge detection, the result capable of detecting lanes roughly 10 meters ahead and calculates the curvature of the current lane.
Detect vehicles using computer vision (HOG) with machine learning (SVM) skills. Track the vehicle using sliding window and smooth the result using temporal a heatmap.
- To run the project, first setup environment using Udacity Starter Kit
- To view more detail about this project, please reference My Report
- To generate the combined (Vehicle detection and Lane line detection) video please see image_pipeline.py