/Vehicle-detection-and-Tracking

Detect and track all the vehicles in the video

Primary LanguageJupyter Notebook

Vehicle-detection-and-Tracking

The goals / steps of this project are the following:

  1. Perform feature extraction on a labeled training set of images, this includes HOG (Histogram of Oriented Gradients) feature and color feature
  2. Train SVM classifier
  3. Implement a sliding window technique and use the trained classifier to search for vehicles in images
  4. Run the tracking pipeline on a video stream. Create a heat map of recurring detections frame by frame to reject outliers and follow detected vehicles
  5. Estimate a bounding box for vehicles detected.

For more details please refer the report.