AI 中文总结
研究基于RISC-V多核MCU的视觉系统的低功耗车牌检测与识别，采用多模型推理方法，在公共数据集上车牌检测mAP达38.9%，字符识别率>99.13%，实际数据中低尺寸车牌也能识别，节能且无需硬连线加速引擎，便于算法改进。
AI 中文摘要
本文展示了首个基于低功耗微控制器单元（MCU）的边缘设备用于自动车牌识别（ALPR）。该设计采用9核RISC-V处理器GAP8与QVGA超低功耗灰度成像器。视觉处理管道使用基于SSDLite-MobilenetV2的多模型推理方法进行车牌检测，用LPRNet进行光学字符识别，在公共数据集上车牌检测平均精度均值（mAP）达38.9%，字符识别率>99.13%。在实际数据中，当车牌裁剪尺寸小至30x5像素时也能识别。通过压缩和优化策略，多模型推理（687 MMAC）在GAP8上运行时以117 mW功耗实现1.09 FPS吞吐量。该解决方案是首个嵌入此网络复杂度的MCU级设备，比树莓派3的前代移动级ALPR系统节能73倍，且无需硬连线加速引擎，便于未来算法改进。
英文摘要
In this paper, we present the first (to the best of our knowledge) demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). The design leverages on a 9-core RISC-V processor, GAP8, coupled with a QVGA ultra-low-power greyscale imager. The proposed visual processing pipeline uses a multi-model inference approach based on SSDlite-MobilenetV2 for license plate detection and LPRNet for optical character recognition, reaching a 38.9% mAP score for the first task and a recognition rate of >99.13% for the latter on public datasets. On real-world data, the pipeline recognizes registration numbers when the size of LP crops is as small as 30x5 pixels. Thanks to the applied compression and optimization strategies, the multi-model inference (687 MMAC) achieves a throughput of 1.09 FPS at a power cost of 117 mW when running on GAP8. Our solution is the first MCU-class device embedding such a level of network complexity, resulting to be 73x more energy-efficient w.r.t. precedent mobile-class ALPR system featuring a Raspberry Pi3. The proposed design does not resort to any hardwired acceleration engines, thus retaining full flexibility for future algorithmic improvements.
Comments5 pages, 2 figures, 5 tables. This paper has been accepted for publication in the IEEE International Symposium on Circuits and Systems (ISCAS). Copyright 2021 IEEE
