Game Development Reference
In-Depth Information
compress the video features in an efficient way. The correlations among interframe
feature descriptors are first utilized to generate compact representation for the purpose
of visual search in Makar et al. (
2014
). However, for video compression, the ultimate
goal is to achieve the best R-D performance rather than only improving the retrieving
accuracy. Therefore, the feature compression need to be redesigned according to
the requirements in video coding applications. Moreover, the correlations between
the image content and extracted features should be further studied. More compact
representation of video features will lead to more significant computation reduction
and storage/bandwidth savings.
12.5 Summary
This chapter provides an overview of the recent hot research topics in video coding
and video systems. Beyond the traditional prediction/transform coding, the percep-
tual coding becomes hopeful for further improving the coding efficiency by incor-
porating the human vision working mechanism. And with the arising or Internet
image/video applications, the Internet media-oriented compression technology has
aroused the wide attention of researchers. The cloud-based compression would be
more efficient for cloud storage. However, there are still many challenging problems
to be resolved in the future, and it is a long way for video coding to move forward.
References
Au O, Li S, Zou R, Dai W, Sun L (2012) Digital photo album compression based on global motion
compensation and intra/inter prediction. In: 2012 international conference on audio, language
and image processing (ICALIP). IEEE, pp 84-90
Bay H, Tuytelaars T, Van Gool L (2006) SURF: speeded up robust features. In: Computer vision—
ECCV 2006. Springer, Heidelberg, pp 404-417
Chai D, Ngan K (1997) Foreground/background video coding scheme. In: Proceedings of 1997
IEEE international symposium on circuits and systems, ISCAS'97, vol 2. IEEE, pp 1448-1451
Chandrasekhar V, Takacs G, Chen D, Tsai S, Grzeszczuk R, Girod B (2009) CHOG: compressed
histogram of gradients a low bit-rate feature descriptor. In: IEEE conference on computer vision
and pattern recognition, CVPR 2009. IEEE, pp 2504-2511
Chen Z, Guillemot C (2010) Perceptually-friendly H. 264/AVC video coding based on foveated
just-noticeable-distortion model. IEEE Trans Circuits Syst Video Technol 20(6):806-819
ChenCP, ChenCS, ChungKL, LuHI, TangGY (2004) Image set compression throughminimal-cost
prediction structures. In: ICIP, pp 1289-1292
Chen Z, Han J, Ngan KN (2006) Dynamic bit allocation for multiple video object coding. IEEE
Trans Multimed 8(6):1117-1124
Chen DM, Tsai SS, Chandrasekhar V, Takacs G, Singh J, Girod B (2009) Tree histogram coding
for mobile image matching. In: Data compression conference, DCC'09. IEEE, pp 143-152
Chen J, Zheng J, Xu F, Villasenor J (2012) Adaptive frequency weighting for high-performance
video coding. IEEE Trans Circuits Syst Video Technol 22(7):1027-1036
