Fast Compressed Domain Motion Detection in H.264 Video Streams for Video Surveillance Applications

Szczerba, Krzysztof; Forchhammer, Søren; Stottrup-Andersen, Jesper; Eybye, Peder Tanderup

doi:10.1109/avss.2009.78

Cited by 21 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MV accumulation and the statistical region growing algorithm exploited in the MV accumulation approach [17] are time-consuming and not good for the real-time application with high video resolutions. From the comparisons, our purposed approach outperforms the counterparts substantially in the foreground detection accuracy and the computational cost is similar to the MV confidence [8] approach and the MV voting [7] approach. The low computational cost of the proposed approach surpasses the requirement of real-time processing and is capable of processing the huge H.264 video archives efficiently.…”

Section: E Extract Moving Objects and Information Feedbackmentioning

confidence: 82%

“…We manually labeled the video blocks belonging the real moving objects to obtain the "ground-truth" of 30 frames for each video sequence. We compare the results with the MRF-based [4], the MV voting [7], the MV accumulation [17] and the MV confidence [8] approaches to evaluate the performance of the proposed structure. The MRF-based approach [4] is based on variable block sizes and the basic unit of other counterparts is the 4 × 4 block.…”

Section: E Extract Moving Objects and Information Feedbackmentioning

confidence: 99%

“…Various clustering approaches, including meanshift [3], Markov Random Field (MRF) model [4], and ant colony [5], are proposed to segment moving objects from the sparse MV field. The spatial-temporal filter of MVs [6], the MV voting approach [7], the MV accumulation approach [17] and the MV confidence [8] approach are proposed to reduce the noisy MVs. In the real video surveillance structure, only unsupervised approaches are feasible in the divergent environments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An efficient approach to extract moving objects by the H.264 compressed-domain features

Wang

Chung

Kuo

2012

2012 12th International Conference on ITS Telecommunications

View full text Add to dashboard Cite

A new efficient algorithm on H.264 compresseddomain is proposed for extracting moving objects. The block entropy feature from the compressed-domain video is proposed to handle the bitstream with variable quantization QP values. Each video block builds two background entropy models to reflect the different coding efficiency between INTER and INTRA block types. Through background subtraction, the foreground energy frame is built after a normalization process. The hysteresis thresholding, where the thresholds can be easily obtained by an efficient unsupervised approach, is adopted with slightly modification to overcome the over-segmentation in extracting moving objects. At the final stage, morphological filters and connected components labeling(CCL) are applied to extract the list of moving objects. In our experiments, the proposed approach is able to operate faster than real time and the accurate object extraction can be achieved for huge H.264 surveillance videos.

show abstract

Section: E Extract Moving Objects and Information Feedbackmentioning

confidence: 82%

Section: E Extract Moving Objects and Information Feedbackmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An efficient approach to extract moving objects by the H.264 compressed-domain features

Wang

Chung

Kuo

2012

2012 12th International Conference on ITS Telecommunications

View full text Add to dashboard Cite

show abstract

“…Szczerba et al [74] used temporal and spatial relations of the MVs to generate a Bayesian probability based confidence measure for each motion vector. This measure represented the likeliness of the MV to represent real motion.…”

Section: H264/avc (Mpeg-4 Part 10)mentioning

confidence: 99%

A survey on compressed domain video analysis techniques

Babu

Tom

Wadekar

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

show abstract

“…Here, a fuzzy logic approach [34] applied to detect the active entities. Temporal and spatial relations used [35], to produce a probability based assurance level for each motion vector computed. To represent final segmentation, final binary motion mask extracted based on spatio-temporal confidence array.…”

Section: Background Studies On Moving Video Object (Group) Detection mentioning

confidence: 99%

Research Inferences In Video Compression Domain

Nihal*¹

2019

IJEAT

View full text Add to dashboard Cite

Video Compression (VC) is a painstaking investigation area in the modernization of digital existence because of more evolution being emerged in web relevance. In this direction, video compression is grown-up rapdily and confirmed by the large number of myriad applications in Video streaming, Computer Vision like Video Tampering Detection, Video Surveillance and Camera Moving etc., which collectively use of this compression technology. This paper attributes / opensup / endeavours the whole possible and recent research directions and its challenges by focusing the potential investigations on compression domain of MPEG, H.264, H.265 compression coding standard with latest computing techniques in learning videos via Machine Learning.

show abstract

Fast Compressed Domain Motion Detection in H.264 Video Streams for Video Surveillance Applications

Cited by 21 publications

References 9 publications

An efficient approach to extract moving objects by the H.264 compressed-domain features

An efficient approach to extract moving objects by the H.264 compressed-domain features

A survey on compressed domain video analysis techniques

Research Inferences In Video Compression Domain

Contact Info

Product

Resources

About