{"slug": "low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu", "title": "Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System", "summary": "Researchers demonstrated the first low-power microcontroller-based edge device for automatic license plate recognition, using a 9-core RISC-V processor and ultra-low-power imager. The system achieved 38.9% mAP for detection and >99.13% recognition rate while consuming only 117 mW, making it 73x more energy-efficient than a Raspberry Pi3-based system.", "body_md": "arXiv:2607.09768v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu", "canonical_source": "https://arxiv.org/abs/2607.09768", "published_at": "2026-07-14 04:00:00+00:00", "updated_at": "2026-07-14 04:03:30.298912+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning"], "entities": ["GAP8", "RISC-V", "SSDlite-MobilenetV2", "LPRNet", "Raspberry Pi3"], "alternates": {"html": "https://wpnews.pro/news/low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu", "markdown": "https://wpnews.pro/news/low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu.md", "text": "https://wpnews.pro/news/low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu.txt", "jsonld": "https://wpnews.pro/news/low-power-license-plate-detection-and-recognition-on-a-risc-v-multi-core-mcu.jsonld"}}