USER DIRECTED VIEW SYNTHESIS ON OMAP PROCESSORS

2010-06-09
Yildiz, Mursel
Akar, Gözde
In this paper, we propose a system for user directed real time view synthesis for hand-held devices. Stored image frames with corresponding depth maps are used as input to the system. Users view point choice is captured using a GYRO based system. OMAP3530 microprocessor is used as the main processor which processes suggested view synthesis algorithm with occlusion handling and frame enhancement techniques. Proposed algorithms are implemented on DSP core and ARM core of OMAP3530 separately and their performances are evaluated through experiments. In addition, two daughter cards are designed for user view point determination. First daughter card handles communication process with EVM board and calculates view point according to the input from the second daughter card with single axis response GYRO sensor (ADIS16060).

Suggestions

User directed view synthesis on omap processors
Yıldız, Mürsel; Akar, Gözde; Department of Electrical and Electronics Engineering (2009)
In this thesis, real time image rendering for hand held devices is studied according to user’s view point choice and using image frames with corresponding depth maps obtained from 2 different cameras, of which positions on coordinate system is known. User’s view point choice is restricted to the area between right, and left cameras. Occlusion handling methods for image rendering systems is explored and discussed together with frame enhancement techniques. Median filtering is studied for multicolor image fra...
Functional Size of a Real-Time System
Desharnais, Jean-Marc; Abran, Alain; Dikici, Pinar Efe; Ilis, Mert Can; Karaca, Irfan Nuri;( Abstracts: This paper presents a case study on the implementation of IFPUG FPA and COSMIC software measurement methods for a small real-time system. The two methods were applied separately to measure the functional size of the same software. The main objective of this paper is to explore, through a case study, the issue of the measurement adequacy of each measurement method to capture the functional size of real-time software. For the practitioners, the real issue is that such a 'number' represent adequately the functional size. This number should take into consideration the particularities of specific real-time software and be sensitive to small variations of functionality.; 2009-11-06)
This paper presents a case study on the implementation of IFPUG FPA and COSMIC software measurement methods for a small real-time system. The two methods were applied separately to measure the functional size of the same software. The main objective of this paper is to explore, through a case study, the issue of the measurement adequacy of each measurement method to capture the functional size of real-time software. For the practitioners, the real issue is that such a 'number' represent adequately the funct...
Multiple Description Coding of 3D Dynamic Meshes Based on Temporal Subsampling
Bici, M. Oguz; Akar, Gözde (2010-01-21)
In this paper, we propose a Multiple Description Coding (MDC) method for reliable transmission of compressed time consistent 3D dynamic meshes. It trades off reconstruction quality for error resilience to provide the best expected reconstruction of 3D mesh sequence at the decoder side. The method is based on partitioning the mesh frames into two sets by temporal subsampling and encoding each set independently by a 3D dynamic mesh coder. The encoded independent bitstreams or so-called descriptions are transm...
Multi-modal video event recognition based on association rules and decision fusion
Guder, Mennan; Çiçekli, Fehime Nihan (2018-02-01)
In this paper, we propose a multi-modal event recognition framework based on the integration of feature fusion, deep learning, scene classification and decision fusion. Frames, shots, and scenes are identified through the video decomposition process. Events are modeled utilizing features of and relations between the physical video parts. Event modeling is achieved through visual concept learning, scene segmentation and association rule mining. Visual concept learning is employed to reveal the semantic gap b...
Deep Spectral Convolution Network for Hyperspectral Unmixing
Akar, Gözde (2018-10-10)
In this paper, we propose a novel hyperspectral unmixing technique based on deep spectral convolution networks (DSCN). Particularly, three important contributions are presented throughout this paper. First, fully-connected linear operation is replaced with spectral convolutions to extract local spectral characteristics from hyperspectral signatures with a deeper network architecture. Second, instead of batch normalization, we propose a spectral normalization layer which improves the selectivity of filters b...
Citation Formats
M. Yildiz and G. Akar, “USER DIRECTED VIEW SYNTHESIS ON OMAP PROCESSORS,” presented at the 4th 3DTV Conference on the True Vision - Capture, Transmission and Display of 3D Video, Tampere, FINLAND, 2010, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52982.