scholarly journals Improving Processing Speed of Real-Time Stereo Matching using Heterogenous CPU/GPU Model

2020 ◽  
Vol 9 (5) ◽  
pp. 1983-1987
Keyword(s):  
Real Time ◽  
Processing Speed ◽  
Computational Models ◽  
Stereo Matching ◽  
Graphics Processing Unit ◽  
Image Resolution ◽  
Cost Functions ◽  
Processing Unit ◽  
Disparity Map ◽  
Matching Problem

This paper presents an improvement of the processing speed of the stereo matching problem. The time required for stereo matching represents a problem for many real time applications such as robot navigation , self-driving vehicles and object tracking. In this work, a real-time stereo matching system is proposed that utilizes the parallelism of Graphics Processing Unit (GPU). An area based stereo matching system is used to generate the disparity map. Four different sequential and parallel computational models are used to analyze the time consumed by the stereo matching. The models are: 1) Sequential CPU, 2) Parallel multi-core CPU, 3) Parallel GPU and 4) Parallel heterogenous CPU/GPU. The dense disparity image is calculated, and the time is highly reduced using the heterogenous CPU/GPU model, while maintaining the same accuracy of other models. A static partitioning of CPU and GPU workload is properly designed based on time analysis. Different cost functions are used to measure the correspondence and to generate the disparity map. A sliding window is used to calculate the cost functions efficiently. A speed of more than 100 frames per second(f/s) is achieved using parallel heterogenous CPU/GPU for 640 x 480 image resolution and a disparity range equals 50.

Real-time, High-resolution Depth Upsampling on Embedded Accelerators

2021 ◽  
Vol 20 (3) ◽  
pp. 1-22
Author(s):  
David Langerman ◽  
Alan George
Keyword(s):  
High Resolution ◽  
Low Power ◽  
Real Time ◽  
Mixed Reality ◽  
Graphics Processing Unit ◽  
Processing Unit ◽  
Reconfigurable Logic ◽  
Depth Sensors ◽  
Time Requirements ◽  
Graphics Processing

High-resolution, low-latency apps in computer vision are ubiquitous in today’s world of mixed-reality devices. These innovations provide a platform that can leverage the improving technology of depth sensors and embedded accelerators to enable higher-resolution, lower-latency processing for 3D scenes using depth-upsampling algorithms. This research demonstrates that filter-based upsampling algorithms are feasible for mixed-reality apps using low-power hardware accelerators. The authors parallelized and evaluated a depth-upsampling algorithm on two different devices: a reconfigurable-logic FPGA embedded within a low-power SoC; and a fixed-logic embedded graphics processing unit. We demonstrate that both accelerators can meet the real-time requirements of 11 ms latency for mixed-reality apps. 1

scholarly journals Electronic Orientation Aid for Visually Impaired using Graphics Processing Unit (GPU)

2020 ◽  
Vol 32 ◽  
pp. 03054
Author(s):  
Akshata Parab ◽  
Rashmi Nagare ◽  
Omkar Kolambekar ◽  
Parag Patil
Keyword(s):  
Real Time ◽  
Visually Impaired ◽  
Graphics Processing Unit ◽  
Human Perception ◽  
Processing Unit ◽  
Surrounding Environment ◽  
Visually Impaired People ◽  
Impaired People ◽  
Definition Of ◽  
Graphics Processing

Vision is one of the very essential human senses and it plays a major role in human perception about surrounding environment. But for people with visual impairment their definition of vision is different. Visually impaired people are often unaware of dangers in front of them, even in familiar environment. This study proposes a real time guiding system for visually impaired people for solving their navigation problem and to travel without any difficulty. This system will help the visually impaired people by detecting the objects and giving necessary information about that object. This information may include what the object is, its location, its precision, distance from the visually impaired etc. All these information will be conveyed to the person through audio commands so that they can navigate freely anywhere anytime with no or minimal assistance. Object detection is done using You Only Look Once (YOLO) algorithm. As the process of capturing the video/images and sending it to the main module has to be carried at greater speed, Graphics Processing Unit (GPU) is used. This will help in enhancing the overall speed of the system and will help the visually Impaired to get the maximum necessary instructions as quickly as possible. The process starts from capturing the real time video, sending it for analysis and processing and get the calculated results. The results obtained from analysis are conveyed to user by means of hearing aid. As a result by this system the blind or the visually impaired people can visualize the surrounding environment and travel freely from source to destination on their own.

scholarly journals Real-time speckle variance swept-source optical coherence tomography using a graphics processing unit

2012 ◽  
Vol 3 (7) ◽  
pp. 1557 ◽  
Author(s):  
Kenneth K. C. Lee ◽  
Adrian Mariampillai ◽  
Joe X. Z. Yu ◽  
David W. Cadotte ◽  
Brian C. Wilson ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Real Time ◽  
Graphics Processing Unit ◽  
Processing Unit ◽  
Optical Coherence ◽  
Swept Source ◽  
Graphics Processing

A Real-Time Photogrammetric System for Acquisition and Monitoring of Three-Dimensional Human Body Kinematics

2021 ◽  
Vol 87 (5) ◽  
pp. 363-373
Author(s):  
Long Chen ◽  
Bo Wu ◽  
Yao Zhao ◽  
Yuan Li
Keyword(s):  
Real Time ◽  
Human Body ◽  
Graphics Processing Unit ◽  
Three Dimensional ◽  
Stereo Pair ◽  
Processing Unit ◽  
Detection Distance ◽  
Human Kinematics ◽  
Graphics Processing ◽  
Time Acquisition

Real-time acquisition and analysis of three-dimensional (3D) human body kinematics are essential in many applications. In this paper, we present a real-time photogrammetric system consisting of a stereo pair of red-green-blue (RGB) cameras. The system incorporates a multi-threaded and graphics processing unit (GPU)-accelerated solution for real-time extraction of 3D human kinematics. A deep learning approach is adopted to automatically extract two-dimensional (2D) human body features, which are then converted to 3D features based on photogrammetric processing, including dense image matching and triangulation. The multi-threading scheme and GPU-acceleration enable real-time acquisition and monitoring of 3D human body kinematics. Experimental analysis verified that the system processing rate reached ∼18 frames per second. The effective detection distance reached 15 m, with a geometric accuracy of better than 1% of the distance within a range of 12 m. The real-time measurement accuracy for human body kinematics ranged from 0.8% to 7.5%. The results suggest that the proposed system is capable of real-time acquisition and monitoring of 3D human kinematics with favorable performance, showing great potential for various applications.

scholarly journals Real-Time Computer Simulation of Three Dimensional Elastostatics Using the Finite Point Method

2011 ◽  
Vol 110-116 ◽  
pp. 2740-2745
Author(s):  
Kirana Kumara P. ◽  
Ashitava Ghosal
Keyword(s):  
Real Time ◽  
Graphics Processing Unit ◽  
Numerical Technique ◽  
Three Dimensional ◽  
Point Method ◽  
Processing Unit ◽  
Finite Point ◽  
Deformable Solids ◽  
Finite Point Method ◽  
Linear Elastostatics

Real-time simulation of deformable solids is essential for some applications such as biological organ simulations for surgical simulators. In this work, deformable solids are approximated to be linear elastic, and an easy and straight forward numerical technique, the Finite Point Method (FPM), is used to model three dimensional linear elastostatics. Graphics Processing Unit (GPU) is used to accelerate computations. Results show that the Finite Point Method, together with GPU, can compute three dimensional linear elastostatic responses of solids at rates suitable for real-time graphics, for solids represented by reasonable number of points.

scholarly journals Using Unreal Engine to Visualize a Cosmological Volume

Universe ◽  
2020 ◽  
Vol 6 (10) ◽  
pp. 168
Author(s):  
Christopher Marsden ◽  
Francesco Shankar
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Graphics Processing Unit ◽  
Large Scale Structure ◽  
Two Dimensions ◽  
Scale Structure ◽  
Sloan Digital Sky Survey ◽  
Processing Unit ◽  
Large Scale Universe ◽  
Time Projection

In this work we present “Astera’’, a cosmological visualization tool that renders a mock universe in real time using Unreal Engine 4. The large scale structure of the cosmic web is hard to visualize in two dimensions, and a 3D real time projection of this distribution allows for an unprecedented view of the large scale universe, with visually accurate galaxies placed in a dynamic 3D world. The underlying data are based on empirical relations assigned using results from N-Body dark matter simulations, and are matched to galaxies with similar morphologies and sizes, images of which are extracted from the Sloan Digital Sky Survey. Within Unreal Engine 4, galaxy images are transformed into textures and dynamic materials (with appropriate transparency) that are applied to static mesh objects with appropriate sizes and locations. To ensure excellent performance, these static meshes are “instanced’’ to utilize the full capabilities of a graphics processing unit. Additional components include a dynamic system for representing accelerated-time active galactic nuclei. The end result is a visually realistic large scale universe that can be explored by a user in real time, with accurate large scale structure. Astera is not yet ready for public release, but we are exploring options to make different versions of the code available for both research and outreach applications.

scholarly journals Lightweight Architecture for Real-Time Hand Pose Estimation with Deep Supervision

Symmetry ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 585
Author(s):  
Yufei Wu ◽  
Xiaofei Ruan ◽  
Yu Zhang ◽  
Huang Zhou ◽  
Shengyu Du ◽  
...  
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Graphics Processing Unit ◽  
Parallel Execution ◽  
Processing Unit ◽  
Network Efficiency ◽  
Hand Pose Estimation ◽  
Central Processing ◽  
Deployment Optimization ◽  
Hand Pose

The high demand for computational resources severely hinders the deployment of deep learning applications in resource-limited devices. In this work, we investigate the under-studied but practically important network efficiency problem and present a new, lightweight architecture for hand pose estimation. Our architecture is essentially a deeply-supervised pruned network in which less important layers and branches are removed to achieve a higher real-time inference target on resource-constrained devices without much accuracy compromise. We further make deployment optimization to facilitate the parallel execution capability of central processing units (CPUs). We conduct experiments on NYU and ICVL datasets and develop a demo1 using the RealSense camera. Experimental results show our lightweight network achieves an average running time of 32 ms (31.3 FPS, the original is 22.7 FPS) before deployment optimization. Meanwhile, the model is only about half parameters size of the original one with 11.9 mm mean joint error. After the further optimization with OpenVINO, the optimized model can run at 56 FPS on CPUs in contrast to 44 FPS running on a graphics processing unit (GPU) (Tensorflow) and it can achieve the real-time goal.

Sign in / Sign up

Export Citation Format

Share Document