You can use this file as a template for your writeup if you want to submit it as a markdown file, but feel free to use some other method and submit a pdf if you prefer.
Vehicle Detection Project
The goals / steps of this project are the following:
- Perform a Histogram of Oriented Gradients (HOG) feature extraction on a labeled training set of images and train a classifier Linear SVM classifier
- Optionally, you can also apply a color transform and append binned color features, as well as histograms of color, to your HOG feature vector.
- Note: for those first two steps don't forget to normalize your features and randomize a selection for training and testing.
- Implement a sliding-window technique and use your trained classifier to search for vehicles in images.
- 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.
- Estimate a bounding box for vehicles detected.
Rubric Points
Here I will consider the rubric points individually and describe how I addressed each point in my implementation.
1. Provide a Writeup / README that includes all the rubric points and how you addressed each one. You can submit your writeup as markdown or pdf. Here is a template writeup for this project you can use as a guide and a starting point.
You're reading it!
1. Explain how (and identify where in your code) you extracted HOG features from the training images.
The code for this step is contained in the In [7] code cell of the IPython notebook Car-Detection.ipynb
I started by reading in all the vehicle and non-vehicle images. Here is an example of one of each of the vehicle and non-vehicle classes:
I then explored different color spaces and different skimage.hog() parameters (orientations, pixels_per_cell, and cells_per_block). I grabbed random images from each of the two classes and displayed them to get a feel for what the skimage.hog() output looks like.
Here is an example using the YCrCb color space and HOG parameters of orientations=8, pixels_per_cell=(8, 8) and cells_per_block=(2, 2):
I tried various combinations of parameters and tried running SVM classifier on it.Finally the results were satisfying with following parameters giving test accuracy rate above 98%
color_space = 'YCrCb'
orient = 9
pix_per_cell = 8
cell_per_block = 2
hog_channel = "ALL"
spatial_size = (16, 16)
hist_bins = 16
spatial_feat = True
hist_feat = True
hog_feat = True
3. Describe how (and identify where in your code) you trained a classifier using your selected HOG features (and color features if you used them).
I trained a linear SVM using spatial bin, color histogram features and HOG features. The code for training is in block In [12].
1. Describe how (and identify where in your code) you implemented a sliding window search. How did you decide what scales to search and how much to overlap windows?
For searching purpose I only considered lower half of image since the cars cannot be observerd in sky. In the bottom half I used a method Sub-Sampling window search.In which a box of 96*96 px slides with an offset fo 16 px in x and y directions. Example is as below
2. Show some examples of test images to demonstrate how your pipeline is working. What did you do to optimize the performance of your classifier?
Ultimately I searched on two scales using YCrCb 3-channel HOG features plus spatially binned color and histograms of color in the feature vector, which provided a nice result. Here are some example images:
1. Provide a link to your final video output. Your pipeline should perform reasonably well on the entire project video (somewhat wobbly or unstable bounding boxes are ok as long as you are identifying the vehicles most of the time with minimal false positives.)
Here's a link to my video result
2. Describe how (and identify where in your code) you implemented some kind of filter for false positives and some method for combining overlapping bounding boxes.
I recorded the positions of positive detections in each frame of the video. From the positive detections I created a heatmap and then thresholded that map to identify vehicle positions. I then used scipy.ndimage.measurements.label() to identify individual blobs in the heatmap. I then assumed each blob corresponded to a vehicle. I constructed bounding boxes to cover the area of each blob detected.
Here's an example result showing the heatmap from a series of frames of video, the result of scipy.ndimage.measurements.label() and the bounding boxes then overlaid on the last frame of video:
Here is the output of scipy.ndimage.measurements.label() on the integrated heatmap from all six frames:
1. Briefly discuss any problems / issues you faced in your implementation of this project. Where will your pipeline likely fail? What could you do to make it more robust?
After making the whole pipline I tested my solution on test video and project video. And I found that there is an issue with false positives. To reduce this effect I used a technique to save the identified windows of previous n frames and then add it to the current heat of image. This allowed me to increase the threshold of heat and make correct guesses. Even after applying this technique I was not able to get the results where there are tree shadows. So I marked those portions and croped those frames to add it to training set. This helped me to remove the false positives. This pipline will fail where there is no enough light or if there is a vehicle other than car. So my steps would be to collect such dataset and add it to training set to make it more robust. Also in future I would try deeplearning techniques like YOLO to overcome the limitations of this technique making it realtime.