scholarly journals Hardware-Abbildung eines videobasierten Verfahrens zur echtzeitfähigen Auswertung von Winkelhistogrammen auf eine modulare Coprozessor-Architektur

2010 ◽  
Vol 8 ◽  
pp. 135-142 ◽  
Author(s):  
H. Flatt ◽  
A. Tarnowsky ◽  
H. Blume ◽  
P. Pirsch

Abstract. Dieser Beitrag behandelt die Abbildung eines videobasierten Verfahrens zur echtzeitfähigen Auswertung von Winkelhistogrammen auf eine modulare Coprozessor-Architektur. Die Architektur besteht aus mehreren dedizierten Recheneinheiten zur parallelen Verarbeitung rechenintensiver Bildverarbeitungsverfahren und ist mit einem RISC-Prozessor verbunden. Eine konfigurierbare Architekturerweiterung um eine Recheneinheit zur Auswertung von Winkelhistogrammen von Objekten ermöglicht in Verbindung mit dem RISC eine echtzeitfähige Klassifikation. Je nach Konfiguration sind für die Architekturerweiterung auf einem Xilinx Virtex-5-FPGA zwischen 3300 und 12 000 Lookup-Tables erforderlich. Bei einer Taktfrequenz von 100 MHz können unabhängig von der Bildauflösung pro Einzelbild in einem 25-Hz-Videodatenstrom bis zu 100 Objekte der Größe 256×256 Pixel analysiert werden. This paper presents the mapping of a video-based approach for real-time evaluation of angular histograms on a modular coprocessor architecture. The architecture comprises several dedicated processing elements for parallel processing of computation-intensive image processing tasks and is coupled with a RISC processor. A configurable architecture extension, especially a processing element for evaluating angular histograms of objects in conjunction with a RISC processor, provides a real-time classification. Depending on the configuration of the architecture extension, 3 300 to 12 000 look-up tables are required for a Xilinx Virtex-5 FPGA implementation. Running at a clock frequency of 100 MHz and independently of the image resolution per frame, 100 objects of size 256×256 pixels are analyzed in a 25 Hz video stream by the architecture.

2013 ◽  
Vol 569-570 ◽  
pp. 932-939 ◽  
Author(s):  
David M.J. McCarthy ◽  
Jim H. Chandler ◽  
Alessandro Palmeri

Photogrammetric techniques have demonstrated their suitability for monitoring static structural tests. Advantages include scalability, reduced cost, and three dimensional monitoring of very high numbers of points without direct contact with the test element. Commercial measuring instruments now exist which use this approach. Dynamic testing is becoming a convenient approach for long-term structural health monitoring. If image based methods could be applied to the dynamic case, then the above advantages could prove beneficial. Past work has been successful where the vibration has either large amplitude or low frequency, as even specialist imaging sensors are limited by an inherent compromise between image resolution and imaging frequency. Judgement in sensor selection is therefore critical. Monitoring of structures in real-time is possible only at a reduced resolution, and although imaging and computer processing hardware continuously improves, so the accuracy demands of researchers and engineers increase. A new approach to measuring vibration is introduced here, whereby a long-exposure photograph is used to capture a blurred image of the vibrating structure. The high resolution blurred image showing the whole vibration interval is measured with no need for high-speed imaging. Results are presented for a series of small-scale laboratory models, as well as a larger scale test, which demonstrate the flexibility of the proposed technique. Different image processing strategies are presented and compared, as well as the effects of exposure, aperture and sensitivity selection. Image processing time appears much faster, increasing suitability for real-time monitoring.


2005 ◽  
Vol 17 (4) ◽  
pp. 410-419 ◽  
Author(s):  
Takashi Komuro ◽  
◽  
Yoshiki Senjo ◽  
Kiyohiro Sogen ◽  
Shingo Kagami ◽  
...  

We propose a method to realize robust real-time shape recognition against noise and occlusion by using information of an entire image, and by performing image processing in a pixel parallel manner. The evaluation by simulation showed that the proposed method was effective for images with noise or partially occluded images. We implemented the algorithm to a vision chip which performs pixel-parallel processing and confirmed real-time operation. We also estimated the performance of the method on an ideal processor.


Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1664
Author(s):  
Yoon-Ki Kim ◽  
Yongsung Kim

Recently, as the amount of real-time video streaming data has increased, distributed parallel processing systems have rapidly evolved to process large-scale data. In addition, with an increase in the scale of computing resources constituting the distributed parallel processing system, the orchestration of technology has become crucial for proper management of computing resources, in terms of allocating computing resources, setting up a programming environment, and deploying user applications. In this paper, we present a new distributed parallel processing platform for real-time large-scale image processing based on deep learning model inference, called DiPLIP. It provides a scheme for large-scale real-time image inference using buffer layer and a scalable parallel processing environment according to the size of the stream image. It allows users to easily process trained deep learning models for processing real-time images in a distributed parallel processing environment at high speeds, through the distribution of the virtual machine container.


2012 ◽  
Vol 6-7 ◽  
pp. 659-664
Author(s):  
En Shun Kang ◽  
Yu Xi Zhao

Traditional median filter algorithm has the long processing time, which goes against the real-time image processing. According to its shortcomings, this paper puts forward the rapid median filter algorithm, and uses DE2 board of the company called Altera to do the realization on FPGA (CycloneII 2C35). The experimental results show that the image pre-processing system is able to complete a variety of high-level image algorithms in milliseconds, and FPGA's parallel processing capability and pipeline operations can dramatically improve the speed of image processing, so the FPGA-based image processing system has broad prospects for development.


Sign in / Sign up

Export Citation Format

Share Document