SVM classifier to detect adjacent video frames



An attempt to use Support Vector Machine (SVM) to quantify the weight of each metric in determining the likelihood of frames being adjacent was done with mixed success. Originally a classifier was trained to determine if frames were adjacent but due to the highly skewed set of training examples (only two adjacent frames out of a set of n examples) the classifier had poor performance.

Train an SVM classifier to determine if frames are adjacent

steps of the Code :

Detect features in video frames

Calculate match metrics between all frames

Calculate metrics from matched features

Calculate classes for adjacent frames

Restructure data for classification training

Train SVM to classify adjacent frames

Check model

Classify test data and evaluate performance

Save SVM model

Use SVM classifier to detect adjacent frames

Order by algorithm :

1) Pick random starting frame

2) Find nearest neighbor (top percentage of matches then pick min distance)

3) Check if closer to start or end of constructed sequence

4) If closer to the end append the frame

5) Otherwise start the search from the start of the sequence and build backwards

6) Continue until all frames sorted

Practical mobile slide-to-lecture-video search system

Licence plate detection in video file

MATLAB code for video reconstruction


There are no reviews yet.

Be the first to review “SVM classifier to detect adjacent video frames”

Your email address will not be published. Required fields are marked *