Video Content Detection with Single Frame Level Accuracy Using Dynamic Thresholding Technique

Abstract

This paper proposes a video retrieval method that detects frame sections that correspond to shots in a query (video segment) with single frame level accuracy. The method adopts the coarse-to-fine strategy to decrease the processing time and the memory consumption; dynamic threshold with initial ranges for small segments is proposed to detect the exact beginning and end of each corresponding frame section to each shot in a query. Experiments on real videos show that our method can achieve accurate video detection with exact frame position while reducing processing time and memory consumption.

Quality assessment framework for video contextualisation of personal videos

“…Out of focus video is created when the details captured are not in the depth of field of camera capture capability, making the part of frame blurred. Motion blur [10, 14, 17] is usually created in a frame when the time of exposure is long relatively to the velocity of movement. Blur due to motion is a common phenomenon.…”

“…Finally, the two independent classifiers were combined into one classifier, SVMOR, through a logical OR operation. Mori et al [17] proposed a video retrieval method that detected frame sections corresponding to shots in a query (video segment) for single frame level accuracy. The method adopts the coarse‐to‐fine strategy to decrease the processing time and memory consumption.…”

Search-Based Content Analysis System on Online Collaborative Platform for Film Production

“…The normalized cross correlation is used as the similarity measure. Next, we set small windows to obtain a 1 Details of this method is presented in [10] threshold for each position with some overlap as shown in Fig 5. The adaptive threshold technique [11] using a variance ratio based on the discriminant analysis is applied to a segmented similarity pattern and a threshold is obtained for each window.…”