Fast FPGA-Based Multiobject Feature Extraction

• Published in: IEEE transactions on circuits and systems for video technology Vol. 23; no. 1; pp. 30 - 45
• Main Authors: Qingyi Gu, Takaki, T., Ishii, I.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.01.2013; Institute of Electrical and Electronics Engineers
• Subjects: Acceleration; Algorithm design and analysis; Applied sciences; Artificial intelligence; Circuit properties; Computer science; control theory; systems; Digital circuits; Display; Electric, optical and optoelectronic circuits; Electronic circuits; Electronics; Exact sciences and technology; Feature extraction; Field programmable gate arrays; Hardware; Hardware implementation; high-frame-rate vision; image recognition; Information, signal and communications theory; Labeling; Memory management; multiobject tracking; Pattern recognition; Pattern recognition. Digital image processing. Computational geometry; Signal processing; Telecommunications and information theory; Zero order; Computer vision; Target tracking; Image recognition; Hardware implementation; Field programmable gate array; Vision system; Frame rate; Pattern recognition; Algorithm; high-frame-rate vision; Implementation; First order; Gesture; Signal processing; Feature extraction; Autocorrelation; Localization; multiobject tracking
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2012.2202195

This paper describes a high-frame-rate (HFR) vision system that can extract locations and features of multiple objects in an image at 2000 f/s for 512 × 512 images by implementing a cell-based multiobject feature extraction algorithm as hardware logic on a field-programmable gate array-based high-speed vision platform. In the hardware implementation of the algorithm, 25 higher-order local autocorrelation features of 1024 objects in an image can be simultaneously extracted for multiobject recognition by dividing the image into 8 × 8 cells concurrently with calculation of the zeroth and first-order moments to obtain the sizes and locations of multiple objects. Our developed HFR multiobject extraction system was verified by performing several experiments: tracking for multiple objects rotating at 16 r/s, recognition for multiple patterns projected at 1000 f/s, and recognition for human gestures with quick finger motion.