Configurable Hardware Core for IoT Object Detection

Future Internet

João D. Lopes¹  José T. de Sousa¹  Pedro R. Miranda¹  Daniel Pestana¹  Rui Policarpo Duarte¹  Horácio C. Neto¹  Mário P. Véstias² 

[1] INESC-ID, Instituto Superior Técnico, Universidade de Lisboa, 1000-029 Lisboa, Portugal;INESC-ID, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, 1500-310 Lisboa, Portugal;

关键词: Internet of Things;    object detection;    YOLO;    FPGA;   

DOI  :  10.3390/fi13110280

来源: DOAJ

【 摘 要 】

Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of $\mathrm{m}\mathrm{A}{\mathrm{P}}_{50}$.

【 授权许可】

Unknown