Optical flow techniques for estimation of camera motion parameters in sewer closed circuit television inspection videos

•A novel technique to analyze and track camera motion in sewer CCTV inspection videos•Optical flow algorithms are used to determine camera motion parameters.•Technique enables automated detection and extraction of regions of interest.•Technique enables reduction in computational costs required for analyzing CCTV videos.•Results from actual videos show robustness and accuracy of the proposed technique.

This paper discusses a novel approach for automated analysis and tracking of camera motion in sewer inspection closed circuit television (CCTV) videos. This approach represents an important building block for any system that supports automated analysis and defect detection of CCTV videos. The proposed approach employs optical flow techniques to automatically identify, locate, and extract a limited set of video segments, called regions of interest (ROI), which likely include defects, thus reducing the time and computational requirements needed for video processing. Tracking the camera motion parameters is used to recover the operator actions during the inspection session, which would provide important clues about the location and severity of the ROI. Techniques for estimating the camera travelling distance, position inside the sewer, and direction of motion from optical flow vectors are discussed. The proposed techniques were validated using a representative set of sewer CCTV videos obtained from the cities of Regina and Calgary, Canada.