An attention controlled multi-core architecture for energy efficient object recognition

作者：Kim Joo Young^*; Oh Sejong; Lee Seungjin; Kim Minsu; Oh Jinwook; Yoo Hoi Jun

来源：Signal Processing: Image Communication , 2010, 25(5): 363-376.

DOI：10.1016/j.image.2010.03.003

• Attention controlled
• Multi-core architecture
• Object recognition
• Visual attention
• Energy efficient

In this paper, an attention controlled multi-core architecture is proposed for energy efficient object recognition. The proposed architecture employs two IP layers having different roles for energy efficient recognition processing: the attention/control IPs compute regions-of-interest (ROIs) of the entire image and control the multiple processing cores to perform local object recognition processing on selected area. To this end, a task manager is proposed to perform dynamic scheduling of various ROI tasks from the attention IP to multiple cores in a unit of small-sized grid-tile. Thanks to a number of grid-tile threads generated by the task manager, the utilization of the multiple cores amounts to 92% on average. As a result, the proposed architecture achieves 2.1 x energy reduction in multi-core recognition system by indicating processing cores to focus on critical area of the image with a 0.87 mJ attention processing. Finally, the proposed architecture is implemented in 0.13 mu m CMOS technology and the fabricated chip verifies 3.2 x lower energy dissipation per frame than the state-of-the-art object recognition processor.

• 出版日期2010-6