A 1.9TOPS and 564GOPS/W Heterogeneous Multicore SoC with Color-Based Object Classification Accelerator for Image-Recognition Applications

📋 论文概要

本文提出了一款用于图像识别的异构多核SoC，集成了基于颜色的物体分类加速器，实现了1.9TOPS的性能和564GOPS/W的能效，旨在满足高级驾驶辅助系统（ADAS）对实时多任务识别和高检测率的需求。

💡 主要创新点

• 提出了一种基于颜色的物体分类加速器，通过颜色特征实现高效物体检测与分类。
• 采用异构多核架构，结合通用处理器与专用加速器，在1.9TOPS性能下实现564GOPS/W的高能效。
• 针对ADAS应用优化，支持多路实时识别处理，降低假阳性率。

🏷 关键词

📄 原文摘要

Mayu Okumura, Manabu Nishiyama, Tadakazu Nomura, Kazushige Oma, Nobuhiro Sato, Moriyasu Banno, Hiroo Hayashi, Takashi Miyamori Toshiba, Kawasaki, Japan Image recognition technologies have gained prominence in a variety of fields, such as automotive and surveillance, with dedicated image-recognition ICs being developed recently [1-2]. Image recognition ICs for an advanced driver assistance system (ADAS) have also been proposed [3]. However, future ADAS applications must support greater numbers of real-time recognition processes simultaneously, with higher detection rates and lower false-positive rates. For instance, adaptive cruise control (ACC), an application of ADAS, comprises many image recognition processes, such as pedestrian detection (PD), vehicle detection (VD), general obstacle detection (GOD), lane detection (LD), traffic light recognition (TLR), and traffic sign recognition (TSR). ACC also requires

👥 作者与机构

Jun Tanabe, Sano Toru, Yutaka Yamada, Tomoki Watanabe,