In this paper, we present a probabilistic neural model, which extends Kohonen's self-organizing map (SOM) by performing a probabilistic principal component analysis (PPCA) at each neuron. Several SOMs have been proposed in the literature to capture the local principal subspaces, but our approach offers a probabilistic model while it has a low complexity on the dimensionality of the input space. This allows to process very high-dimensional data to obtain reliable estimations of the probability densities which are based on the PPCA framework. Experimental results are presented, which show the map formation capabilities of the proposal with high-dimensional data, and its potential in image and video compression applications.

Probabilistic PCA Self-Organizing Maps

This article presents a novel real-time algorithm for reducing and dynamically controlling the computational complexity of an H.264 video encoder implemented in software. A fast mode decision algorithm, based on a Pareto-optimal macroblock classification scheme, is combined with a dynamic complexity control algorithm that adjusts the MB class decisions such that a constant frame rate is achieved. The average coding efficiency of the proposed algorithm was found to be similar to that of conventional encoding operating at half the frame rate. The proposed algorithm was found to provide lower average bitrate and distortion than static complexity scaling.

/pdf/real-time-h-264-video-encoding-in-software-with-fast-mode-422rqg65eu.pdf

Real-time H.264 video encoding in software with fast mode decision and dynamic complexity control

We propose a Stereoscopic Visual Attention- (SVA-) based regional bit allocation optimization for Multiview Video Coding (MVC) by the exploiting visual redundancies from human perceptions. We propose a novel SVA model, where multiple perceptual stimuli including depth, motion, intensity, color, and orientation contrast are utilized, to simulate the visual attention mechanisms of human visual system with stereoscopic perception. Then, a semantic region-of-interest (ROI) is extracted based on the saliency maps of SVA. Both objective and subjective evaluations of extracted ROIs indicated that the proposed SVA model based on ROI extraction scheme outperforms the schemes only using spatial or/and temporal visual attention clues. Finally, by using the extracted SVA-based ROIs, a regional bit allocation optimization scheme is presented to allocate more bits on SVA-based ROIs for high image quality and fewer bits on background regions for efficient compression purpose. Experimental results on MVC show that the proposed regional bit allocation algorithm can achieve over 20 ∼ 30% bit-rate saving while maintaining the subjective image quality. Meanwhile, the image quality of ROIs is improved by 0.46 ∼ 0.61 dB at the cost of insensitive image quality degradation of the background image.

/pdf/stereoscopic-visual-attention-based-regional-bit-allocation-2flsp5pvsb.pdf

Stereoscopic visual attention-based regional bit allocation optimization for multiview video coding

Recently, the content distribution network industry has become exposed to significant changes. The advent of cheaper and more powerful mobile devices having the ability to play, create, and transmit video content and which maximize a number of multimedia content distributions on various mobile networks will place unprecedented demands on networks for high capacity, low-latency, and low-loss communications paths. The reduction of cost of digital video cameras along with development of user-generated video sites (e.g., iTunesTM, GoogleTM Video and YouTubeTM) have stimulated the new user-generated content sector. Growing premium content coupled with advanced video technologies, such as the Internet TV, will replace in the near future conventional technologies (e.g., cable or satellite TV). The relatively recent ITU-T H.264/AVC (ISO/IEC MPEG-4 Part 10) video coding standard (Wiegand & Sullivan, 2003), which was officially issued in 2003, has become a challenge for real-time video applications. Compared to others standards, it gains about 50% in bit rate, while providing the same visual quality. In addition to having all the advantages of MPEG2, H.263 and MPEG-4, the H.264 video coding standard possesses a number of improvements, such as the content-adaptive-based arithmetic codec (CABAC), enhanced transform and quantization, prediction of "Intra" macroblocks (spatial prediction), and others. H.264 is designed for both constant bit rate (CBR) and variable bit rate (VBR) video coding, useful for transmitting video sequences over statistically multiplexed networks (e.g. asynchronous transfer mode (ATM), the Ethernet, or other Internet networks). This video coding standard can also be used at any bit rate range for various applications, varying from wireless video phones to high definition television (HDTV) and digital video broadcasting (DVB). In addition, H.264 provides significantly improved coding efficiency and greater functionality, such as rate scalability, “Intra” prediction and error resilience in comparison with its predecessors, MPEG-2 and H.263. However, H.264/AVC is much more complex in comparison to other coding standards and to achieve maximum quality encoding, high computational resources are required. Due to the recent technological achievements and trends, the high-definition, highly interactive networked media applications pose challenges to network operators. The variety of end-user devices with different capabilities, ranging from cell phones with small screens and restricted processing power to high-end PCs with high-definition displays, have stimulated significant interest in effective technologies for video adaptation for spatial formats, consuming power and bit rate.

/pdf/recent-advances-in-region-of-interest-video-coding-elky9wsxq3.pdf

Recent Advances in Region-of-interest Video Coding

We present a complexity-aware adaptive spatial preprocessing (pre-filtering) scheme for the efficient Region-of-Interest (ROI) Scalable Video Coding (SVC). According to the proposed approach, we adaptively vary various parameters of the SVC pre-filters, such as standard deviations, a number of filters for the dynamic pre-processing of a transition region between the ROI and background, etc., thereby enabling to dynamically adjust the desired SVC settings. In addition, our adaptive spatial pre-filtering system is based on an SVC computational complexity-rate-distortion (C-R-D) analysis, thereby adding a complexity dimension to the conventional Region-of-Interest SVC R-D analysis. As a result, the ROI SVC visual presentation quality is significantly improved, which can be especially useful for various resource-limited devices, such as mobile devices. The performance of the presented adaptive spatial ROI SVC pre-processing scheme is evaluated and tested in detail, further comparing it to the Joint Scalable Video Model reference software (JSVM 9.19) and demonstrating significant improvements.

HadarO.

Papers

Dynamic computational complexity and bit allocation for optimizing H.264/AVC video compression