A 58.6mW 30fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920×1080 Videos
A 58.6mW 30fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920×1080 Videos
复制标题
58.6mW 30fps 实时可编程多目标检测加速器，在全高清 1920×1080 视频上具有可变形零件模型
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Zhengdong Zhang
中科院分区：
文献类型：
--
作者：
V. Sze;Amr Suleiman;Zhengdong Zhang
本文提出了一种可编程的，节能的和实时的目标检测硬件加速器，用于低功耗和高吞吐量的应用，使用可变形的零件模型，检测精度比传统的刚体模型高2倍。采用三种方法来解决8个可变形零件检测的高计算复杂度：分类修剪减少33倍零件分类，矢量量化减少15倍内存大小，特征基投影减少2倍每个分类的成本。该芯片采用65 nm CMOS工艺制造，可以以60 fps的速度处理全高清1920×1080视频，无需任何片外存储。该芯片具有两个可编程分类引擎，用于多目标检测。在30 fps时，芯片功耗仅为58.6mW（0.94 nJ/pixel，1168 GOPS/W）。在60 fps的更高吞吐量下，分类引擎可以进行时间复用，以检测甚至超过两个对象类别。这种加速器使目标检测能够像视频压缩一样节能，这在今天的大多数相机中都可以找到。关键词-可变形零件，目标检测，基本投影，修剪。
This paper presents a programmable, energyefficient and real-time object detection hardware accelerator for low power and high throughput applications using deformable parts models, with 2× higher detection accuracy than traditional rigid body models. Three methods are used to address the high computational complexity of 8 deformable parts detection: classification pruning for 33× fewer part classification, vector quantization for 15× memory size reduction, and feature basis projection for 2× reduction in the cost of each classification. The chip was fabricated in a 65nm CMOS technology, and can process full high definition 1920×1080 videos at 60fps without any off-chip storage. The chip has two programmable classification engines for multi-object detection. At 30fps, the chip consumes only 58.6mW (0.94 nJ/pixel, 1168 GOPS/W). At a higher throughput of 60fps, the classification engines can be time multiplexed to detect even more than two object classes. This proposed accelerator enables object detection to be as energyefficient as video compression, which is found in most cameras today. Keywords—Deformable parts, object detection, basis projection, pruning.