masterhead masterhead  masterhead

Processor for High-speed Moment-based Analysis of Numerous Objects


We developed a processor for moment-based analysis of numerous objects. Moments are useful values providing information about geometric features and invariant features with respect to image-plane transformations. In addition, the simultaneous observation of numerous objects allows recognition of various complex phenomena. Our processor has a high-performance core based on a pixel-parallel and object-parallel calculation method [link].

This module was mounted to the high-speed vision system [link] as a co-processor. As a result, the moments from 0th to 2nd order of 1,024 objects were extracted at 1kfps. We believe that the achieved performance is highly promising for wide range of applications such as flow control [link], particle manipulation, image classification in industrial inspection, real-time shape measurement for robotics [link], and so on.

For example, the features including size, centroid, orientation, and horizontal to vertical ratio can be obtained at high throughput rates and low latency as shown below.


Related Works


  1. Yoshihiro Watanabe, Takashi Komuro, and Masatoshi Ishikawa: A High-speed Vision System for Moment-based Analysis of Numerous Objects, 2007 IEEE International Conference on Image Processing(ICIP'07) (San Antonio, 2007.9.19) /Proceedings, pp. V177-V180. [PDF] *IEEE
*IEEE © 2001-2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Ishikawa Watanabe Laboratory, Department of Information Physics and Computing, Department of Creative Informatics,
Graduate School of Information Science and Technology, University of Tokyo
Ishikawa Watanabe Laboratory WWW admin:
Copyright © 2008 Ishikawa Watanabe Laboratory. All rights reserved.