Traffic control and efficient use of existing infrastructure are key challenges in recent time. This work carries out comparative analysis of various corner detection methods in different conditions, to detect presence of parked vehicles in street lanes. Different algorithmic implementations are used, to detect corners over targets in video stream and then classify them over a spatio-temporal analysis maps to identify parked vehicles. The system has been evaluated using i-Lids public dataset and has proven to be robust against common difficulties found in Closed Circuit Television (CCTV) such as high noise levels, varying illumination and the presence of momentary occlusion by other vehicles. This could be used to detect illegal and double-parked vehicles in metropolitan areas and to detect incidents on roads with lanes. This paper implemented three corner detection algorithms, Harris, SIFT and FAST and analyzed the comparative performances of all three implementations over different parameters viz. precision, recall, false alarm and then conclude on best performing algorithm. The comparative results are presented.
Shot change detection is a significant step in content based video indexing and retrieval. There are different types of transitions between the shots. Most of the shot change detection algorithms deal with these transitions separately. In this paper, we have carried out the analysis of shot change detection methods like pixel difference, histogram difference and Chi-square test and our proposed method. The proposed shot change detection method is integration of pre-processing and KLT (Kanade-Lucas-Tomasi) corner detection technique. In the pre-processing stage, adaptive local thresholding is used to eliminate non-boundary segments and only candidate segments are retained. The candidate segments are refined using bisection-based comparisons to eliminate non-boundary frames. Only refined candidate segments are preserved for further detections; hence, the speed of shot change detection is improved. KLT corner detection approach is used for obtaining key points in the frames from candidate segments. Shot change is detected if the key points between successive frames are not matching. Experimental results indicate that the proposed method is effective in terms accuracy and also helps in accelerating the shot change detection process, which can lead to better and fast retrieval of video.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.