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 (687MMAC) achieves a throughput of 1.09 FPS at a power cost of 117mW 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.
Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System / Lamberti, Lorenzo; Rusci, Manuele; Fariselli, Marco; Paci, Francesco; Benini, Luca. - In: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS PROCEEDINGS. - ISSN 0271-4302. - ELETTRONICO. - (2021), pp. 1-5. (Intervento presentato al convegno IEEE International Symposium on Circuits and Systems, ISCAS 2021 tenutosi a Daegu, Korea nel 22-28 May 2021) [10.1109/ISCAS51556.2021.9401730].
Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System
Lamberti, Lorenzo;Rusci, Manuele;Benini, Luca
2021
Abstract
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 (687MMAC) achieves a throughput of 1.09 FPS at a power cost of 117mW 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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.