Search

Problem statement: Recently, 3D objects have been used in several applications like internet games, virtual reality and scientific visualization. These applications require real time rendering and fast transmission of large objects through internet. However, due to limitation of bandwidth, the compression and streaming of 3D object is still an open research problem. Approach: Novel procedure for compression and coding of 3-Dimensional (3-D) semi-regular meshes using wavelet transform had been introduced. This procedure was based on Space Frequency Quantization (SFQ) which was used to minimize distortion error of reconstructed mesh for a different bit-rate constraint. Results: Experimental results had been carried out over five datasets with different mesh intense and irregularity. Results were evaluated by using the peak signal to noise ratio as an error measurement. Experiments showed that 3D SFQ code over performs Progressive Geometry Coder (PGC) in terms of quality of compressed meshes. Conclusion: A pure 3D geometry coding algorithm based on wavelet had been introduced. Proposed procedure showed its superiority over the state of art coding techniques. Moreover, bit-stream can be truncated at any point and still decode reasonable visual quality meshes. Key words: Compression, 3D geometry coding, wavelet, 3D space frequency quantization, rate-distortion sense, INTRODUCTION An extensive range of applications from different research areas require highly detailed complex 3D models that support these applications to achieve a convincing level of realism. The most efficient [...]

Real-time three-dimensional (3D) reconstruction has been widely explored in several domains in motion capture, robot navigation, augmented reality, and autonomous driving. It is considered one of the most efficient solutions to overcome several problems, such as occlusion and collision in computer vision and computer graphics. This process is computationally intensive and it considers a bottleneck for real-time realistic interaction applications which need a quick response to achieve action in real-time. The Monocular 3D model reconstruction (M3DMR) is considered one of the possible solutions to build an accurate 3D reconstruction in a dynamic environment. However, the proposed framework needs a high computational power to create a single frame. Graphics processors unit (GPU) architecture is used to improve the computational time of M3DMR. This study discussed how to maximize the benefits of using GPU resources by using several optimization techniques that enable GPU architecture to achieve the best possible performance for the M3DMR. Different multicore heterogeneous systems are used to evaluate the performance of the proposed framework. Experimental results confirm that our parallel implementation of 3D Model Reconstruction of Monocular Video Frames is valid for different GPU architectures. The proposed parallel implementation can execute 28 FBS compared with the serial version that executes one frame in 30 min. [ABSTRACT FROM AUTHOR]

Spectral unmixing algorithms are commonly used in processing of hyperspectral images to identify the elemental components, called end-members, and their corresponding information in each pixel of the image. However, these algorithms are computationally intensive and can become a bottleneck for remote sensing hyperspectral image processing, especially in large aerial imagery processing centers. This paper, explores the use of massive parallel processing graphical processing unit to speed up the multi kernel self-organizing map (MKSOM) unmixing algorithm. MKSOM is based on artificial neural networks, which makes it suitable to be efficiently parallelized. Two real benchmark hyperspectral images; AVIRIS Cuprite and Brullus are used to evaluate the performance of the parallel algorithm. The experimental results show that the proposed implementation is appropriated for real-time hyperspectral remote sensing applications due to a very small worst case parallel execution time (0.83 s when the number of classes is less than 9) which makes it feasible to be integrated as on-board processing on any Hyperspectral remote sensors. Our parallel technique achieved a significant speedup compared with a multi-threaded CPU implementation applied on the same hyperspectral image. The results showed a speedup of 93.46 × for SOM size of 256 and trained for 100 epochs on medium-sized HSI such as AVIRIS Cuprite. [ABSTRACT FROM AUTHOR]