基于PP-PicoDet的半自动标注烟丝异物检测研究 |
| |
引用本文: | 陈永祺,顾茜,林郁. 基于PP-PicoDet的半自动标注烟丝异物检测研究[J]. 中国烟草学报, 2023, 29(2): 11-21. DOI: 10.16472/j.chinatobacco.2022.T0046 |
| |
作者姓名: | 陈永祺 顾茜 林郁 |
| |
作者单位: | 1.厦门烟草工业有限责任公司, 福建省厦门市海沧区新阳路1号 361022 |
| |
基金项目: | 福建中烟科技项目“机器视觉在制丝加工过程智能化的研究与应用”FJZYJH2021ZD032 |
| |
摘 要: | 【目的】应用半自动标注技术和轻量级目标检测模型,实现烟丝异物实时检测模型的快速开发和落地应用。【方法】在少量标注的样本上使用picodet-s-320训练基础模型,基于该模型生成对剩余数据样本的预测标注,人工矫正预测标注结果I后,.使用picodet-l-640训练基于全量数据的最终应用模型。【结果】数据标注效率提升223%,迭代周期缩短到1d,训练模型m APoU=o5达到1.000,测试集上漏检率为0%、误检率0.3%,部署模型推理速度提高291%,试运行期间无漏检,多检误报控制在0.23次/批。【结论】采用基于PP-PicoDet的半自动标注技术,大幅缩短算法的开发和迭代周期,模型的预测速度、精度、通用性好,可实现制丝工序烟丝异物的实时检测处置。
|
关 键 词: | 半自动标注 小样本学习 目标检测 轻量级模型 |
收稿时间: | 2021-03-04 |
Semi-automatic annotation technology for foreign materials detection in cut tobacco based on PP-PicoDet |
| |
Affiliation: | 1.China Tobacco Xiamen Industrial Co., Ltd, Xiamen 361022, Fujian, China2.China Tobacco Fujian Industiral Co., Ltd, Xiamen 361012, Fujian, China |
| |
Abstract: | Objective This study aims to achieve rapid development and application of real-time detection model of cut tobacco foreign materials by using semi-automatic annotation technology and lightweight object detection model. Methods The base model was trained using picodet-s-320 on a small labeled samples, predictive annotations on the remaining data samples were generated based on the model. After manually correcting the prediction annotation results, picodet-l-640 was used to train a final application model based on the full amount of data. Results The data annotation efficiency increased by 223%, the iteration cycle was shortened to 1 day, trained model $ {mathrm{m}mathrm{A}mathrm{P}}_{IoU=0.5} $ reached 1.000. The missed detection rate on the test dataset was 0%, false detection rate was 0.3%, the inference speed of the deployed model was increased by 291%, there was no miss detection during test run, and the multichecking and-false alarm rate was controlled at 0.23 per batch. Conclusion Based on the semi-automatic annotation technology of PP-PicoDet, the development and iteration cycle of the algorithm is greatly shortened. It also has solid prediction speed, accuracy and versatility, which can realize the real-time detection and disposal of cut tobacco foreign materials during cigarette processing |
| |
Keywords: | |
|
| 点击此处可从《中国烟草学报》浏览原始摘要信息 |
|
点击此处可从《中国烟草学报》下载免费的PDF全文 |
|