Prioritized Region of Interest Coding in JPEG2000

Sánchez, Vı́ctor; Basu, Anup; Mandal, Mrinal

doi:10.1109/tcsvt.2004.833168

Cited by 42 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique transmits only important regions in video frames at high quality [18,17]. For instance, video sources can stream those regions with faces in higher quality to proxies.…”

Section: Related Workmentioning

confidence: 99%

Critical video quality for distributed automated video surveillance

Korshunov

Ooi

2005

Proceedings of the 13th Annual ACM International Conference on Multimedia

View full text Add to dashboard Cite

Large-scale distributed video surveillance systems pose new scalability challenges. Due to the large number of video sources in such systems, the amount of bandwidth required to transmit video streams for monitoring often strains the capability of the network. On the other hand, large-scale surveillance systems often rely on computer vision algorithms to automate surveillance tasks. We observe that these surveillance tasks present an opportunity for trade-off between the accuracy of the tasks and the bit rate of the video being sent. This paper shows that there exists a sweet spot, which we term critical video quality that can be used to reduce video bit rate without significantly affecting the accuracy of the surveillance tasks. We demonstrate this point by running extensive experiments on standard face detection and face tracking algorithms. Our experiments show that face detection works equally well even if the quality of compression is significantly reduced, and face tracking still works even if the frame rate is reduced to 6 frames per second. We further develop a prototype video surveillance system to demonstrate this idea. Our evaluation shows that we can achieve up to 29 times reduction in video bit rate when detecting faces and 16 times reduction when tracking faces. This paper also proposes a formal rate-accuracy optimization framework which can be used to determine appropriate encoding parameters in distributed video surveillance systems that are subjected to either bandwidth constraints or accuracy constraints.

show abstract

“…This technique transmits only important regions in video frames at high quality [18,17]. For instance, video sources can stream those regions with faces in higher quality to proxies.…”

Section: Related Workmentioning

confidence: 99%

Critical video quality for distributed automated video surveillance

Korshunov

Ooi

2005

Proceedings of the 13th Annual ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Note that through Equation (3), rate-distortion estimates for coding passes are modified at codeblock level. The main difference with previous methods [7, Ch.16.2] [37,39], is that in ROITCOP codeblocks contain only ROI or BG coefficients, whereas in previous approaches codeblocks may contain both types of coefficients. With the use of ROITCOP method, perfect fine-grain accuracy is achieved.…”

Section: Features Of Jpeg2000 Roi Coding Mechanismsmentioning

confidence: 98%

“…Thus, the performance of such mechanism may be severely degraded in some cases. Sanchez, Basu, and Mandal [37] proposed a rearrangement of the codestream to allocate the ROI before the background, and ROI coding with separated codeblock was presented in [38]. [39] introduced the Subblock and Weighted ROI coding methods, which are able to better estimate the rate-distortion contributions of ROI codeblocks.…”

Section: Roi Coding Mechanismsmentioning

confidence: 99%

JPEG2000 ROI coding through component priority for digital mammography

Bartrina-Rapesta

Serra-Sagristí

Aulí-Llinís

2011

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Region Of Interest (ROI) coding is a prominent feature of some image coding systems aimed to prioritize specific areas of the image through the construction of a codestream that, decoded at increasing bit-rates, recovers the ROI first and with higher quality than the rest of the image. JPEG2000 is a wavelet-based coding system that is supported in the Digital Imaging and Communications in Medicine (DICOM) standard. Among other features, JPEG2000 provides lossy-to-lossless compression and ROI coding, which are especially relevant to the medical community. But, due to JPEG2000 supported ROI coding methods that guarantee lossless coding are not designed to achieve a high degree of accuracy to prioritize ROIs, they have not been incorporated in the medical community. This paper introduces a ROI coding method that is able to prioritize multiple ROIs at different priorities, guaranteeing lossy-to-lossless coding.The proposed ROI Coding Through Component Prioritization (ROITCOP) method uses techniques of rate-distortion optimization combined with a simple yet effective strategy of ROI allocation that employs the multi-component Preprint submitted to Computer Vision and Image Understanding September 15, 2010Pre-print of: Bartrina, J., Serra, J. and Aulí, F. "JPEG2000 ROI coding through component priority for digital mammography" in Computer vision and image understanding (Elsevier), vol.

show abstract

“…Many latest video and image coders support region of interest (ROI) coding, which allows encoding different regions with different quality [Schumeyer et al 1997;Sanchez et al 2004]. For instance, a static background can be encoded with lower quality than a moving foreground object, drastically reducing overall video transmission.…”

Section: Related Workmentioning

confidence: 99%

Video quality for face detection, recognition, and tracking

Korshunov

Ooi

2011

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Many distributed multimedia applications rely on video analysis algorithms for automated video and image processing. Little is known, however, about the minimum video quality required to ensure an accurate performance of these algorithms. In an attempt to understand these requirements, we focus on a set of commonly used face analysis algorithms. Using standard datasets and live videos, we conducted experiments demonstrating that the algorithms show almost no decrease in accuracy until the input video is reduced to a certain critical quality, which amounts to significantly lower bitrate compared to the quality commonly acceptable for human vision. Since computer vision percepts video differently than human vision, existing video quality metrics, designed for human perception, cannot be used to reason about the effects of video quality reduction on accuracy of video analysis algorithms. We therefore investigate two alternate video quality metrics, blockiness and mutual information, and show how they can be used to estimate the critical video qualities for face analysis algorithms.

show abstract

Prioritized Region of Interest Coding in JPEG2000

Cited by 42 publications

References 14 publications

Critical video quality for distributed automated video surveillance

Critical video quality for distributed automated video surveillance

JPEG2000 ROI coding through component priority for digital mammography

Video quality for face detection, recognition, and tracking

Contact Info

Product

Resources

About