Q&A.md

Pipeline : Tricentis Proposed solution

Submission Requirment :

1. Writeup

2. Code (or a Jupyter notebook)

3. Example output images.

4. Output Video.

Acceptance Criteria :

End to end full working pipeline

Build Steps :

1. All steps are based on windows 10 environement.

2. Perform a Histogram of Oriented Gradients (HOG) feature extraction on a labeled training set of images and train a classifier Linear SVM classifier.

3. Optionally, you can also apply a color transform and append binned color features, as well as histograms of color, to your HOG       feature vector.

4. Note: for those first two steps don't forget to normalize your features and randomize a selection for training and testing.

5. Apply a perspective transform to rectify binary image ("birds-eye view").

6. Implement a sliding-window technique and use your trained classifier to search for vehicles in images.

7. Run your pipeline on a video stream (start with the test_video.mp4 and later implement on full project_video.mp4) and create a heat map of recurring detections frame by frame to reject outliers and follow detected vehicles.

8. Estimate a bounding box for vehicles detected.

Known Issues :

1.Set up is not done for personal Linux environment.

2.Some of package for python are installed manually.

3.AWS setup is not working as per support project so done locally.

4.Dataset is stord locally for fixing the Udacity project submisssion error.