Heterogeneous vision chip and LBP-based algorithm for high-speed tracking

• Published in: Electronics letters Vol. 50; no. 6; pp. 438 - 439
• Main Authors: Yang, Jie, Shi, Cong, Liu, Liyuan, Wu, Nanjian
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 13.03.2014; Institution of Engineering and Technology
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; computer vision; Electronics; Exact sciences and technology; high‐speed tracking; Image and vision processing and display technology; image resolution; Integrated circuits; Integrated circuits by function (including memories and processors); LBP‐based algorithm; local binary pattern‐based tracking algorithm; microprocessor chips; novel heterogeneous vision chip architecture; object tracking; parallel processing; parallel processors; patch‐parallel way; Pattern recognition. Digital image processing. Computational geometry; pixel‐parallel way; Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices; local binary pattern-based tracking algorithm; novel heterogeneous vision chip architecture; LBP-based algorithm; computer vision; object tracking; microprocessor chips; patch-parallel way; pixel-parallel way; parallel processors; parallel processing; high-speed tracking; image resolution; Computer vision; Local binary pattern; Experimental result; Tracking; Processor; Circuit design; Classification; High speed; Texture; Pixel
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2014.0033

A local binary pattern (LBP)-based tracking algorithm and a novel heterogeneous vision chip architecture that implements the algorithm in high speed are proposed. The algorithm is more robust than previously reported high-speed tracking algorithms. The proposed vision chip architecture adopts multiple levels of parallel processors to execute the algorithm in pixel-parallel and patch-parallel ways. Experimental results show that the proposed implementation can achieve 1000 fps robust tracking.