{"slug": "milsd-a-micro-line-segment-detector-for-resource-constrained-devices", "title": "MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices", "summary": "Researchers propose MiLSD, a micro line-segment detector designed for resource-constrained devices such as microcontrollers, achieving competitive accuracy within a one-megabyte memory budget. The detector uses a compact fully-convolutional backbone and 8-bit quantization to preserve performance, improving sAP10 on the ShanghaiTech Wireframe dataset from 10.6 to 24.1 within 1 MB.", "body_md": "arXiv:2607.06600v1 Announce Type: new\nAbstract: Line segment detection is a key building block in visual SLAM, 3D reconstruction, and industrial inspection. Recent deep learning methods have greatly improved accuracy, yet even the smallest models require several megabytes of memory, exceeding low-cost MCU capacity. This work investigates the maximum achievable accuracy under a sub-megabyte budget. We propose MiLSD, a detector tailored for MCU-level constraints, and systematically compare three output representations within a compact fully-convolutional backbone. Our study shows that the proposed F-Clip center-with-length-and-angle formulation learns most effectively at small model sizes. We find that 8-bit quantization preserves full-precision performance, while 4-bit quantization causes significant degradation, particularly in angle regression, with quantization-aware training recovering only part of the loss. With a one-megabyte activation budget and inference enhancements including sub-pixel decoding, test-time augmentation, and a lightweight verifier, MiLSD improves sAP10 on ShanghaiTech Wireframe from 10.6 (25k parameters, 0.25 MB) to 24.1 within 1 MB. Rather than competing with GPU-scale parsers, we map the accuracy memory trade-off across representations, bit-widths, capacities, and post-processing strategies for embedded vision systems.", "url": "https://wpnews.pro/news/milsd-a-micro-line-segment-detector-for-resource-constrained-devices", "canonical_source": "https://arxiv.org/abs/2607.06600", "published_at": "2026-07-09 04:00:00+00:00", "updated_at": "2026-07-09 04:28:20.988220+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "neural-networks", "ai-infrastructure"], "entities": ["MiLSD", "ShanghaiTech Wireframe"], "alternates": {"html": "https://wpnews.pro/news/milsd-a-micro-line-segment-detector-for-resource-constrained-devices", "markdown": "https://wpnews.pro/news/milsd-a-micro-line-segment-detector-for-resource-constrained-devices.md", "text": "https://wpnews.pro/news/milsd-a-micro-line-segment-detector-for-resource-constrained-devices.txt", "jsonld": "https://wpnews.pro/news/milsd-a-micro-line-segment-detector-for-resource-constrained-devices.jsonld"}}