<title>Compressed-domain video parsing using energy histograms of the lower-frequency DCT coefficients</title>

Abstract

As an increasing amount of audio-visual data is stored, distributed, and used in the compressed form, compressed-domain techniques will be favorable. However, as conventional features may not be directly accessible in the compressed domain, exploration of new compressed domain features will become mandatory. Studies have shown that the DC coefficients of a DCT-compressed video can be used to detect shot transitions for relatively simple video sequences. In this work, the use of the energy histogram of the lower frequency DCT coefficients as features for video parsing was examined. The experimental results show an improvement over those obtained by the DC coefficients alone.

Multimedia Database Retrieval

“…In particular, research has shown that the DC coefficients can be used to detect shot transitions in MPDG [184]. Previous work using Motion-JPEG indicated that AC coefficients could be used to detect scene changes [185]. This section presents a new method called Twin-Window Amplification Method (TWAM) [181,182] for detecting scene changes.…”

Motion based video content indexing

“…Coefficients in the 8x8 DCT block can be classified into frequency bands that roughly correspond to smooth area, horizontal and vertical edges, and noisy areas [34]. Bao et al [35] use energy histogram of low frequency coefficients as the matching features for video frame similarity. This feature can been seen as a rough description of the global texture pattern in the video frame.…”