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.
- Real-time Particle Measurement/Fluid Measurement
- Real-time Shape Measurement of a Moving/Deforming Object
- 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