scholarly journals BMP-RAP: Branching Multithreaded Pipeline for Real-time Applications with Pooled Resources

2019 ◽  
Author(s):  
Michael Sherer ◽  
Ebin Scaria
Keyword(s):  
Computer Vision ◽  
Real Time ◽  
Directed Graph ◽  
Graph Structure ◽  
Performance Gain ◽  
Filter Structure ◽  
Computer Vision Systems ◽  
Real Time Applications ◽  
Time Critical ◽  
Better Than

Many programs have a fixed directed graph structure in the way they are processed. In particular, computer vision systems often employ this kind of pipe-and-filter structure. It is desirable to take advantage of the inherent parallelism in such a system. Additionally, such systems need to run in real-time for robotics applications. In such applications, robotic platforms must make time-critical decisions, and so any additional performance gain would be beneficial. To further improve on this, the platform may need to make the best decision it can by a given time, so that newer data can be processed. Thus, having a timeout that would return a good result may be better than operating on outdated information.

Image Completion Using Randomized Correspondence

2011 ◽  
Vol 271-273 ◽  
pp. 229-234
Author(s):  
Yun Ling ◽  
Hai Tao Sun ◽  
Jian Wei Han ◽  
Xun Wang
Keyword(s):  
Real Time ◽  
Random Sampling ◽  
Nearest Neighbor ◽  
Structural Constraint ◽  
Image Completion ◽  
Image Patches ◽  
Real Time Applications ◽  
Surrounding Areas ◽  
Straight Lines ◽  
Better Than

Image completion techniques can be used to repair unknown image regions. However, existing techniques are too slow for real-time applications. In this paper, an image completion technique based on randomized correspondence is presented to accelerate the completing process. Some good patch matches are found via random sampling and propagated to surrounding areas. Approximate nearest neighbor matches between image patches can be found in real-time. For images with strong structure, straight lines or curves across unknown regions can be manually specified to preserve the important structures. In such case, search is only performed on specified lines or curves. Finally, the remaining unknown regions can be filled using randomized correspondence with structural constraint. The experiments show that the quality and speed of presented technique are much better than that of existing methods.

scholarly journals Image processing in real-time computer vision systems using FPGA

2016 ◽  
pp. 1-16
Author(s):  
Alexander Sergeevich Derzhanovsky ◽  
Sergey Mikhailovich Sokolov
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Real Time ◽  
Vision Systems ◽  
Computer Vision Systems

Improved SURF Detection Combined with Dual FLANN Matching and Clustering Analysis

2014 ◽  
Vol 556-562 ◽  
pp. 2792-2796 ◽  
Author(s):  
Jun Fei Li ◽  
Geng Wang ◽  
Qiang Li
Keyword(s):  
Computer Vision ◽  
Object Tracking ◽  
Real Time ◽  
Clustering Analysis ◽  
Detection Method ◽  
Haar Wavelet ◽  
Time Cost ◽  
Speed Up ◽  
Real Time Applications ◽  
Speed Up Robust Feature

In this paper, an improved object detection method based on SURF (Speed-Up Robust Feature) is presented. SURF is a widely used method in computer vision. But it’s still not efficient enough to apply in real-time applications, such as real time object tracking. To reduce the time cost, the traditional descriptor of SURF is altered. Triangle and diagonal descriptor is adopted to replace the Haar wavelet calculation. Then dual matching approach based on FLANN is employed. Thus matching errors can be cut down. Besides, the traditional SURF does not give the accurate region of the target. To restrict the area, clustering analysis is used which is promoted from K-WMeans. Experimental work demonstrates the proposed approach achieve better effect than traditional SURF in real scenarios.

scholarly journals Real-Time Detection of Planar Regions in Unorganized Point Clouds

2020 ◽  
Author(s):  
Frederico Limberger ◽  
Manuel Oliveira
Keyword(s):  
Real Time ◽  
Point Clouds ◽  
Gaussian Kernel ◽  
Region Detection ◽  
Laser Scanners ◽  
Computer Vision Applications ◽  
Voting Scheme ◽  
Real Time Applications ◽  
Planar Regions ◽  
Better Than

Automatic detection of planar regions in point clouds is an important step for many graphics, image processing, and computer vision applications. While laser scanners and digital photography have allowed us to capture increasingly larger datasets, previous approaches for planar region detection are computationally expensive, precluding their use in real-time applications. We present an O(n log n) technique for plane detection in unorganized point clouds based on an efficient Hough-transform voting scheme. It works by clustering sets of approximately co-planar points and by casting votes for these clusters on a spherical accumulator using a trivariate Gaussian kernel. A comparison with competing techniques shows that our approach is considerably faster and scales significantly better than previous ones, being the first practical solution for deterministic plane detection in large unorganized point clouds.

Sign in / Sign up

Export Citation Format

Share Document