An FPGA based high performance optical flow hardware design for computer vision applications

2013-05-01
Gultekin, Gokhan Koray
Saranlı, Afşar
Optical Flow (OF) information is used in higher level vision tasks in a variety of computer vision applications. However, its use in resource constrained applications such as small-scale mobile robotic platforms is limited because of the high computational complexity involved. The inability to compute the OF vector field in real-time is the main drawback which prevents these applications to efficiently utilize some successful techniques from the computer vision literature. In this work, we present the design and implementation of a high performance FPGA hardware with a small footprint and low power consumption that computes OF at a speed exceeding real-time performance. A well known OF algorithm by Horn and Schunck is selected for this baseline implementation. A detailed multiple-criteria performance analysis of the proposed hardware is presented with respect to computation speed, resource usage, power consumption and accuracy compared to a PC based floating-point implementation. The implemented hardware computes OF vector field on 256 x 256 pixels images in 3.89 ms i.e. 257 fps. Overall, the proposed implementation achieves a superior performance in terms of speed, power consumption and compactness while there is minimal loss of accuracy. We also make the FPGA design source available in full for research and academic use.
MICROPROCESSORS AND MICROSYSTEMS

Suggestions

An FPGA based high performance optical flow hardware design for autonomous mobile robotic platforms
Gültekin, Gökhan Koray; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2010)
Optical flow is used in a number of computer vision applications. However, its use in mobile robotic applications is limited because of the high computational complexity involved and the limited availability of computational resources on such platforms. The lack of a hardware that is capable of computing optical flow vector field in real time is a factor that prevents the mobile robotics community to efficiently utilize some successful techniques presented in computer vision literature. In this thesis work,...
A new approach to shutterless operation of microbolometer based infrared cameras
Çavdar, Semih; Akın, Tayfun; Department of Electrical and Electronics Engineering (2021-2-03)
This thesis presents an algorithm for the shutterless operation of microbolometer based infrared imaging systems. The active material of the microbolometer used in the thesis is vanadium oxide and it is produced in METU MEMS Center. The array size of the microbolometer is 480x640 and pixel pitch is 17 μm. The microbolometer has a CTIA type readout circuit which consists of detector and reference resistance. Voltage values are optimized at steady-state considering interactions between pixels in the focal pla...
Design and Optimization of Nanoantennas for Nano-Optical Applications
Işıklar, Göktuğ; Ergül, Özgür Salih; Department of Electrical and Electronics Engineering (2020-9)
In this study, design and simulation of plasmonic nanoantenna structures to obtain high power enhancement capabilities at optical frequencies, as well as utilization of nanoantennas for imaging and sensing applications are presented. Plasmonic characteristics of nanoantennas, which depend on many parameters, such as material, frequency, geometry, and size, are investigated in detail via computational analyses of various nanoantenna structures. Numerical solutions of electromagnetic problems are performe...
A Fusion-Based Framework for Wireless Multimedia Sensor Networks in Surveillance Applications
Yazici, Adnan; Koyuncu, Murat; Sert, Seyyit Alper; Yilmaz, Turgay (2019-01-01)
Multimedia sensors enable monitoring applications to obtain more accurate and detailed information. However, the development of efficient and lightweight solutions for managing data traffic over wireless multimedia sensor networks (WMSNs) has become vital because of the excessive volume of data produced by multimedia sensors. As part of this motivation, this paper proposes a fusion-based WMSN framework that reduces the amount of data to be transmitted over the network by intra-node processing. This framewor...
A Fast shape detection approach by directional integrations
Okman, Osman Erman; Akar, Gözde; Department of Electrical and Electronics Engineering (2013)
Detection and identification of objects from aerial images are important problems for various types of application areas. For many of the man-made structures shape is a fundamental feature by which these objects are separated from the background and other structures. In this thesis, a novel geometric shape detection algorithm based on the spatial properties of structures is proposed. Since the objects are transformed into 1-D vectors by evaluating directional integrals and detections occur by the analysis o...
Citation Formats
G. K. Gultekin and A. Saranlı, “An FPGA based high performance optical flow hardware design for computer vision applications,” MICROPROCESSORS AND MICROSYSTEMS, pp. 270–286, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/36337.