Dept. of Electr. Eng., National Taiwan Univ.Chang, Hao-ChiehHao-ChiehChangWang, Yi-ChuYi-ChuWangHsu, Mei-YunMei-YunHsuLIANG-GEE CHEN2018-09-102018-09-10200015206130https://www.scopus.com/inward/record.uri?eid=2-s2.0-0034500771&doi=10.1109%2fSIPS.2000.886699&partnerID=40&md5=c0c53692560e72423ad2481a72de896dhttp://scholars.lib.ntu.edu.tw/handle/123456789/288653This paper presents efficient algorithms and architectures for the MPEG-4 object-based video coding. The novel coding tools supporting for object-based coding will much increase the computational burden, in comparison with conventional frame-based video coding system. In order to process these extra computational tasks effectively, design techniques both on algorithms and architectures have to be addressed. By the careful examination of computational behavior of algorithms, the best-matched computation models can be derived, and the target architectures can be determined. Based on this design strategy, the computational behavior of the MPEG-4 video coding tools at simple/core profiles and level 2 is explored first. Then, by considering the analysis results, efficient algorithms and architectures are developed to meet the design specifications. The shape coding tool, which is the most computation-extensive task supporting for object-based functionality is selected as our study case. The real-time performance of shape coding can be easily achieved by the proposed architecture approximately running at 7.8 MHz while the optimized software running on a full-speed RISC (Ultra Sparc, 300 MHz) can only have about 1/10 performance.application/pdf629493 bytesapplication/pdfAlgorithms; Computational complexity; Computer architecture; Image compression; Mathematical models; Object recognition; Optimization; Real time systems; Motion picture experts group; Shape coding tool; Image codingjournal article10.1109/SIPS.2000.8866992-s2.0-0034500771