| 刘乐,顾玲珑,李子洋,方一鸣.基于StarNet改进的轻量化连铸板坯检测算法SGI-YOLOv7[J].电子测量与仪器学报,2026,40(6):12-23 |
| 基于StarNet改进的轻量化连铸板坯检测算法SGI-YOLOv7 |
| Improved lightweight continuous casting slab detection algorithmSGI-YOLOv7 based on StarNet |
| |
| DOI： |
| 中文关键词: 连铸板坯检测 YOLOv7 轻量化 StarNet 损失函数 |
| 英文关键词:continuous casting slab detection YOLOv7 lightweight StarNet loss function |
| 基金项目:国家自然科学基金(62573375)、河北省自然科学基金(F2024203038)、秦皇岛市科学技术研究与发展计划项目(202302B048)、省级重点实验室绩效补助经费项目(22567619H)资助 |
|
|
| Author | Institution |
| Liu Le | Key Laboratory of Intelligent Rehabilitation and Neuroregulation of Hebei Province,
Yanshan University, Qinhuangdao 066004,China |
| Gu Linglong | Key Laboratory of Intelligent Rehabilitation and Neuroregulation of Hebei Province,
Yanshan University, Qinhuangdao 066004,China |
| Li Ziyang | Key Laboratory of Intelligent Rehabilitation and Neuroregulation of Hebei Province,
Yanshan University, Qinhuangdao 066004,China |
| Fang Yiming | Key Laboratory of Intelligent Rehabilitation and Neuroregulation of Hebei Province,
Yanshan University, Qinhuangdao 066004,China |
|
| 摘要点击次数: 62 |
| 全文下载次数: 19 |
| 中文摘要: |
| 针对当前通用检测算法存在的网络复杂度高、参数量大、难以适应连铸产线复杂环境与严苛实时要求等问题，提出一种基于StarNet改进的轻量化连铸板坯检测算法SGI YOLOv7（YOLOv7 with StarNet, GSConv-based Slim-neck, and Inner-SIoU loss function）。首先，基于采集的连铸产线板坯图像构建用于板坯检测的专用数据集；其次，采用StarNet替换YOLOv7（you only look once version 7）主干网络，利用星型操作实现高效特征映射，有效降低了模型参数规模和计算复杂度；再次，引入基于分组混洗卷积（group shuffle convolution，GSConv）的轻量化Slim-neck结构，实现跨层级特征的高效融合与压缩；同时，设计基于辅助边框的内部尺度感知交并比（inner scale-aware intersection over union，Inner-SIoU）损失函数，通过方向感知梯度优化与多尺度回归机制，提升模型在宽高比差异显著场景下的适应性与收敛速度。最后，在自制板坯数据集上的对比实验结果表明，所提SGI-YOLOv7算法在维持较高检测精度（mAP@0.5为96.0%）的同时，参数量较基准YOLOv7模型减少35.6%、计算量降低65.6%，推理速度达到82 fps，显著减轻硬件部署负担，实现了工业场景下连铸板坯的高效、轻量化实时检测。 |
| 英文摘要: |
| Aiming at the problems of high network complexity, large parameter size, and difficulty in adapting to the complex environment and stringent real-time requirements of continuous casting production lines in current general detection algorithms, this paper proposes a lightweight continuous casting slab detection algorithm named SGI-YOLOv7 (YOLOv7 with StarNet, GSConv-based Slim-neck, and Inner-SIoU loss function). Firstly, a dedicated dataset for slab detection is constructed based on images collected from the continuous casting production line. Secondly, StarNet is adopted to replace the backbone network of YOLOv7 (you only look once version 7), utilizing star operations to achieve efficient feature mapping, which effectively reduces the model’s parameter scale and computational complexity. Thirdly, a lightweight Slim-neck structure based on group shuffle convolution (GSConv) is introduced to achieve efficient fusion and compression of cross-level features. Simultaneously, an inner scale-aware intersection over union (Inner-SIoU) loss function is designed based on auxiliary bounding boxes, which enhances the model’s adaptability and convergence speed in scenarios with significant aspect ratio variations through direction-aware gradient optimization and a multi-scale regression mechanism. Finally, comparative experimental results on the self-built slab dataset show that the proposed SGI-YOLOv7 algorithm maintains high detection accuracy (mAP@0.5 is 96.0%) while reducing parameters by 35.6% and computational cost by 65.6% compared to the baseline YOLOv7 model, with an inference speed reaching 82 frames per second. This significantly alleviates the hardware deployment burden and achieves efficient, lightweight, real-time detection of continuous casting slabs in industrial scenarios. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
