Project description
In this project, I implemented a pipeline to detect vehicles in images. The following steps were performed:
- Extract features using Histogram of Oriented Gradients (HOG) on a labeled training set of images
- Train a Linear Support Vector Machine classifier
- Implement a sliding-window technique and use the trained classifier to search for vehicles in images.
- Run the pipeline on a video stream and create a heat map of recurring detections frame by frame to reject outliers and follow detected vehicles.
- Estimate a bounding box for vehicles detected.
The end result is shown below, with the full code available in the jupyter notebook.
Training data
This project used labeled data for vehicle and non-vehicle examples to train the classifier. These example images come from a combination of the GTI vehicle image database, the KITTI vision benchmark suite, and examples extracted from the project video itself.
Technologies Used
