Current Issue : April - June Volume : 2018 Issue Number : 2 Articles : 5 Articles
This paper proposes a novel method for 2D-to-3D video conversion, based on boundary information to automatically\ngenerate the depth map. First, we use the Gaussian model to detect foreground objects and then separate the\nforeground and background. Second, we employ the superpixel algorithm to find the edge information. According to\nthe superpixels, we will assign corresponding hierarchical depth value to initial depth map. From the result of depth\nvalue assignment, we detect the edges by Sobel edge detection with two thresholds to strengthen edge information.\nTo identify the boundary pixels, we use a thinning algorithm to modify edge detection. Following these results, we\nassign the depth value of foreground to refine it. We use four kinds of scanning path for the entire image to create a\nmore accurate depth map. After that, we have the final depth map. Finally, we utilize depth image-based rendering\n(DIBR) to synthesize left and right view images. After combining the depth map and the original 2D video, a vivid 3D\nvideo is produced....
High Efficiency Video Coding (HEVC or H.265), the latest international video coding standard, displays a 50% bit rate\nreduction with nearly equal quality and dramatically higher coding complexity compared with H.264. Unlike other\nfast algorithms, we first propose an algorithm that combines the CU coding bits with the reduction of unnecessary\nintra-prediction modes to decrease computational complexity. In this study, we first analyzed the statistical relationship\nbetween the best mode and the costs calculated through Rough Mode Decision (RMD) process and proposed an\neffective mode decision algorithm in intra-mode prediction process. We alleviated the computation difficulty by\ncarrying out the RMD process in two stages, reducing 35 modes down to 11 modes in the first RMD process stage,\nand adding modes adjacent to the most promising modes selected during the first stage into the second RMD stage.\nAfter these two stages, we had two or three modes ready to be used in the rate distortion operation (RDO) process\ninstead of the three or eight in the original HEVC process, which significantly reduced the number of unnecessary\ncandidate modes in the RDO process. We then used the coding bits of the current coding unit (CU) as the main basis\nfor judging its complexity and proposed an early termination method for CU partition based on the number of coding\nbits of the current CU. Experimental results show that the proposed fast algorithm provides an average time reduction\nrate of 53% compared to the reference HM-16.12, with only 1.7% Bjontegaard delta rate increase, which is acceptable\nfor Rate-Distortion performance....
There are many techniques of image enhancement. Their parameters are traditionally tuned by maximization of SNR\ncriterion, which is unfortunately based on the knowledge of an ideal image. Our approach is based on Hartley\nentropy, its estimation, and differentiation. Resulting gradient of entropy is estimated without knowledge of ideal\nimages, and it is a subject of minimization. Both SNR maximization and gradient magnitude minimization cause\nvarious settings of the given filter. The optimum settings are compared, and their differences are discussed...
Marine monitoring systems have the requirements of a large field of view, low power consumption, real-time\nviewing, and economical and automatic functionality. This paper establishes an omnidirectional vision system used\nin marine buoys that meets these requirements. We present a framework for image stabilization, which is achieved\nby omnidirectional sea-skyline detection in a marine environment. We propose an optimal edge estimation method\nto calculate the sea-skyline ellipsis according to the sea-skyline characteristics in panoramic images. We construct a\ncompact panoramic image stabilization model based on the sea-skyline and propose a reconstruction method for\nthe invalid regions using the key frame. The experimental results and analysis show that the proposed approach is\ncapable of acquiring stable video in real-time marine monitoring tasks and that the target detection is sufficiently\neffective, efficient, and accurate for a real-time ship target detection application....
This paper presents a textline detection method for degraded historical documents. Our method follows a\nconventional two-step procedure that the binarization is first performed and then the textlines are extracted from the\nbinary image. In order to address the challenges in historical documents such as document degradation, structure\nnoise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the\nperformance of binarization by detecting the non-text regions and processing only text regions. We also improve the\ntextline detection method by extracting main textblock and compensating the skew angle and writing style.\nExperimental results show that the proposed method yields the state-of-the-art performance for several datasets....
Loading....