Luminance Level of Histogram-Based Scene-Change Detection for Frame Rate Up-Conversion

Abstract

This paper proposes a new scene-change detection method that uses analysis of luminance level of the histograms for frame rate up-conversion (FRUC). The histogram luminance level refers to the statistical average luminance value obtained from the generated histograms for each region. Existing histogram-based scene change methods calculate the difference between optimal threshold values using an automatic thresholding technique or extract the difference between the histogram shape to detect the scene change. The automatic thresholding method uses iterative operations-the difference between the histogram shape is simply a method of calculating the luminance difference for the current and previous frames. Thus, it requires many computational resources and incorrectly detects a scene change because calculating the histogram shape cannot reflect regional image characteristics. The proposed method addresses these problems using histogram luminance levels for each region in the given frames. It calculates the level differences between the previous and current frames to detect the initial scene change regions. Moreover, the proposed method refines the initial scene change regions by analyzing the distribution of surrounding detected regions and uses refinement to enhance scene-change detection accuracy. In the experimental results, the proposed method increased the average F1 score to 0.4816 (a 122.51% improvement) compared with the benchmark methods. The average computation time per pixel of the proposed method also decreased to 13.5323 μs (a 87.06% reduction) compared with the benchmark methods.

Scene Change aware Inter-Frame Forgeries Detection Technique for Surveillance Videos Based on Similarities Analysis

“…To enhance the performance of Anas et al, (2022) scheme, Chandra and Dolley (2016) scene change detection mechanism will be replaced with a robust and efficient mechanism developed by Lee and Cho (2022). The newly incorporated scheme is chosen to reduce computational intensity of the overall scheme as well as increase the precision and accuracy.…”

“…However, the used data set is too biased and also the scheme uses histogram shape difference only which is not efficient enough to reflect the features of regional shape and also computationally demanding. To mitigate this intrinsic flaw, Lee and Cho (2022) proposed a mechanism which uses histogram luminance level for every region within the given frame. The scheme outperforms Chandra and Dolley (2016) and other traditional schemes with 122.5% improvement and 87% reduction in complexity.…”

“…However, histogram shape difference only do not reflect the features of regional shape, it is also an iterative process which result in false detection and high computational intensity respectively. To increase the efficiency of Anas et al, (2022) scheme and also to reduce its complexity, a robust and efficient scheme developed by Lee and Cho (2022) is proposed to replace the scene change detection scheme by Chandra and dolley (2016).…”