Identify vehicles in a video from a front-facing camera on a car using image classifiers such as SVMs and HOG.
- Perform a Histogram of Oriented Gradients (HOG) feature extraction on a labeled training set of images and train a classifier Linear SVM classifier
- Apply a color transform and append binned color features, as well as histograms of color, to the HOG feature vector.
- 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.
train.pyto train the Linear SVM model with set parameters. The training data and parameters are saved in a pickle file for later use.extract.pyto extract features using hog sub-sampling and make predictions.box.pyto store windows found over a set number of frames, get heatmap, and return image with final bounding boxvideo.pyto produce the video with bounding boxes and number of detected vehicles displayed.project_video_output.mp4is the final video with smoother detection by accounting for previous frames
View the video on Youtube