Title :
Compressed domain moving object detection by spatio-temporal analysis of H.264/AVC syntax elements
Author :
Laumer, Marcus ; Amon, Peter ; Hutter, Andreas ; Kaup, Andre
Author_Institution :
Multimedia Commun. & Signal Process., Friedrich-Alexander-Univ. Erlangen-Nurnberg (FAU), Erlangen, Germany
fDate :
May 31 2015-June 3 2015
Abstract :
In this paper, we present a novel moving object detection algorithm for H.264/AVC-compressed video streams. The algorithm does not require full decoding up to the pixel domain but only parsing the compressed bit streams. Thereby, only syntax elements for reconstructing (sub-)macroblock types and quantization parameters are extracted. These features are used to segment the video frames into foreground and background and, according to this segmentation, to identify regions containing moving objects. In a first step, (sub-)macroblock types are analyzed to create initial maps indicating for each block the “weight” for the presence of a moving object. These maps serve as input for our novel spatio-temporal detection algorithm to refine the weight indicating the level of motion for each block. Finally, quantization parameters of macroblocks are used to apply individual thresholds to the block weights to segment the video frames. Experimental results show that our approach efficiently identifies regions containing moving objects and that the presented algorithm is suitable for processing a large number of video streams in parallel.
Keywords :
data compression; feature extraction; image motion analysis; image reconstruction; image segmentation; object detection; quantisation (signal); video coding; video streaming; H.264/AVC syntax elements; H.264/AVC-compressed video streams; block weights; compressed bit stream parsing; compressed domain moving object detection algorithm; macroblock type reconstruction; quantization parameter extraction; spatio-temporal analysis; spatio-temporal detection algorithm; video frame segmentation; Accuracy; Algorithm design and analysis; Image coding; Object detection; Streaming media; Syntactics; Video coding;
Conference_Titel :
Picture Coding Symposium (PCS), 2015
Conference_Location :
Cairns, QLD
DOI :
10.1109/PCS.2015.7170091