Content Based Indexing and Retrieval  from Vehicle Surveillance Videos Using  Optical Flow Method

Shruti V Kamath; Mayank Darbari; Dr. Rajashree Shettar

Volume : II, Issue : IV, April - 2013

Content Based Indexing and Retrieval from Vehicle Surveillance Videos Using Optical Flow Method

Shruti V Kamath, Mayank Darbari, Dr. Rajashree Shettar

Abstract :

Visual vehicle surveillance is widely used and produces a huge amount of video data which are stored for future or immediate use. To find an interesting vehicle from these videos because of car crashes, illegal U-turns, speeding or anything that the user may be interested in, is a common case. This would be a very labor intensive process, if there is not an effective method for the indexing and retrieval of vehicles. In the proposed approach, a surveillance video from a highway is taken. Then shots are detected using color histogram method. Key frames are extracted to avoid redundancy in a shot. After key frames are extracted from the input video, vehicles are detected and tracked using Optical Flow. The proposed method extracts vehicles and classifies them based on area and colour. Unsupervised clustering is performed on the vehicles extracted using k-means and SOM (Self Organizing Map) algorithms. Clustering is done based on size (small, medium, large) and color (red, white, grey) of the vehicles. Using the clustering results, a matching matrix is computed for these two clustering algorithms, with respect to the object tracking method. The proposed system gives an accuracy of up to 99% (with respect to size) and 90% (with respect to color)