{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:00:14Z","timestamp":1774540814907,"version":"3.50.1"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T00:00:00Z","timestamp":1717718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>In the tobacco industry, impurity detection is an important prerequisite for ensuring the quality of tobacco. However, in the actual production process, the complex background environment and the variability of impurity shapes can affect the accuracy of impurity detection by tobacco robots, which leads to a decrease in product quality and an increase in health risks. To address this problem, we propose a new online detection method of tobacco impurities for tobacco robot. Firstly, a BCFormer attention mechanism module is designed to effectively mitigate the interference of irrelevant information in the image and improve the network's ability to identify regions of interest. Secondly, a Dual Feature Aggregation (DFA) module is designed and added to Neck to improve the accuracy of tobacco impurities detection by augmenting the fused feature maps with deep semantic and surface location data. Finally, to address the problem that the traditional loss function cannot accurately reflect the distance between two bounding boxes, this paper proposes an optimized loss function to more accurately assess the quality of the bounding boxes. To evaluate the effectiveness of the algorithm, this paper creates a dataset specifically designed to detect tobacco impurities. Experimental results show that the algorithm performs well in identifying tobacco impurities. Our algorithm improved the mAP value by about 3.01% compared to the traditional YOLOX method. The real-time processing efficiency of the model is as high as 41 frames per second, which makes it ideal for automated inspection of tobacco production lines and effectively solves the problem of tobacco impurity detection.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1422960","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T19:14:59Z","timestamp":1718133299000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A new online detection method of tobacco impurities for tobacco robot"],"prefix":"10.3389","volume":"18","author":[{"given":"Lei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Dailin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Dayong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Erqiang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhenyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jiakang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Du","sequence":"additional","affiliation":[]},{"given":"Shanlian","family":"Li","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"B1","first-page":"6154","article-title":"\u201cCascade R-CNN: delving into high quality object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Cai","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2857","DOI":"10.1177\/0142331220929816","article-title":"Research on tobacco foreign body detection device based on machine vision","volume":"42","author":"Chao","year":"2020","journal-title":"Trans. Inst. Meas. Control"},{"key":"B3","first-page":"102","article-title":"Dawnbench: an end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman","year":"2017","journal-title":"Training"},{"key":"B4","first-page":"27","article-title":"Research on online recognition algorithm of tobacco foreign body based on adaptive clustering and color difference analysis","volume":"25","author":"Fuguang","year":"2012","journal-title":"J. Chongqing Educ. Inst"},{"key":"B5","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1186\/s40064-016-1770-z","article-title":"Levels of heavy metals in the raw and processed Ethiopian tobacco leaves","volume":"5","author":"Girma Regassa","year":"2016","journal-title":"Springerplus"},{"key":"B6","first-page":"1440","article-title":"\u201cFast R-CNN,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Girshick","year":"2015"},{"key":"B7","first-page":"580","article-title":"\u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Girshick","year":"2014"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.09742","article-title":"Image translation as diffusion visual programmers","author":"Han","year":"","journal-title":"arXiv"},{"key":"B9","doi-asserted-by":"publisher","author":"Han","year":"","DOI":"10.48550\/arXiv.2401.12902"},{"key":"B10","first-page":"2961","article-title":"\u201cMask R-CNN,\u201d","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"He","year":"2017"},{"key":"B11","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/ICSCDS53736.2022.9760746","article-title":"\u201cTobacco plant disease detection and classification using deep convolutional neural networks,\u201d","volume-title":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","author":"Kumar","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1326050","DOI":"10.3389\/frai.2024.1326050","article-title":"A multimodal deep learning architecture for smoking detection with a small data approach","volume":"7","author":"Lakatos","year":"2024","journal-title":"Front. Artif. Intell"},{"key":"B13","first-page":"734","article-title":"\u201cCornernet: detecting objects as paired keypoints,\u201d","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Law","year":"2018"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPECA51329.2021.9362689","article-title":"Research on moldy tobacco leaf image recognition method based on convolutional neural network","author":"Li","year":"2021","journal-title":"Comput. Eng. Sci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"107390","DOI":"10.1016\/j.compag.2022.107390","article-title":"Camffnet: a novel convolutional neural network model for tobacco disease image recognition","volume":"202","author":"Lin","year":"2022","journal-title":"Comput. Electron. Agric"},{"key":"B16","first-page":"2980","article-title":"\u201cFocal loss for dense object detection,\u201d","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Lin","year":"2017"},{"key":"B17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"\u201cSSD: single shot multibox detector,\u201d","volume-title":"Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14","author":"Liu","year":"2016"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.05561","article-title":"Global attention mechanism: retain information to enhance channel-spatial interactions","author":"Liu","year":"2021","journal-title":"arXiv"},{"key":"B19","first-page":"10012","article-title":"\u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Liu","year":"2021"},{"key":"B20","doi-asserted-by":"publisher","first-page":"11","DOI":"10.13031\/ja.14537","article-title":"Tobacco leaf grading based on deep convolutional neural networks and machine vision","volume":"65","author":"Lu","year":"2022","journal-title":"J. ASABE"},{"key":"B21","doi-asserted-by":"publisher","first-page":"58","DOI":"10.16652\/j.issn.1004-373x.2022.03.012","article-title":"Remote sensing object detection algorithm based on improved faster R CNN","volume":"45","author":"Ma","year":"2022","journal-title":"Mod. Electron. Technol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1406","article-title":"\u201cOn the role of nonlinear transformations in deep neural network acoustic models,\u201d","author":"Nagamine","year":"2016","journal-title":"Interspeech"},{"key":"B23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1145\/3426826.3426832","article-title":"\u201cA review on industrial surface defect detection based on deep learning technology,\u201d","volume-title":"Proceedings of the 2020 3rd International Conference on Machine Learning and Machine Intelligence","author":"Qi","year":"2020"},{"key":"B24","first-page":"779","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Redmon","year":"2016"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.3390\/s21062170","article-title":"A novel upsampling and context convolution for image semantic segmentation","volume":"21","author":"Sediqi","year":"2021","journal-title":"Sensors"},{"key":"B27","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.11834\/jrs.20219365","article-title":"Improved faster R-CNN for aircraft object detection in remote sensing images","volume":"26","author":"Sha","year":"2022","journal-title":"Nat. Remote Sens. Bull"},{"key":"B28","first-page":"22","article-title":"Typical foreign body disposal methods in tobacco foreign body removal system","author":"Shaotang","year":"2009","journal-title":"Tobacco Technol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3312405","article-title":"A memristive fully connect neural network and application of medical image encryption based on central diffusion algorithm","author":"Sun","year":"2023","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3393975","article-title":"Memristor-based operant conditioning neural network with blocking and competition effects","author":"Sun","year":"","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3348553","article-title":"Memristor-based neural network circuit of associative memory with overshadowing and emotion congruent effect","author":"Sun","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B32","first-page":"10781","article-title":"\u201cEfficientdet: scalable and efficient object detection,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tan","year":"2020"},{"key":"B33","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1117\/12.2631167","article-title":"\u201cDACFA-det: a domain adaptive calibrated free anchor detection network for agricultural similar pests,\u201d","author":"Wang","year":"2022","journal-title":"International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021), Vol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"245","DOI":"10.3778\/j.issn.1002-8331.2208-0240","article-title":"Acfem-retinanet algorithm for object detection in remote sensing images","volume":"60","author":"Wenlong","year":"2024","journal-title":"Comput. Eng. Appl"},{"key":"B35","first-page":"3","article-title":"\u201cCBAM: convolutional block attention module,\u201d","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Woo","year":"2018"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.13336\/j.1003-6520.hve.20230816","article-title":"An improved algorithm for infrared image target detection based on YOLOV5s","volume":"53","author":"Xiao-pei","year":"2023","journal-title":"Laser Infrared"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1228007","DOI":"10.3788\/LOP221679","article-title":"Improved aircraft detection for optical remote sensing images based on faster r-cnn","volume":"60","author":"Xin","year":"2023","journal-title":"Laser Optoelectron. Prog"},{"key":"B38","doi-asserted-by":"publisher","first-page":"67","DOI":"10.19358\/j.issn.2097-1788.2022.03.011","article-title":"Attention feature fusion ssd algorithm for object detection in remote sensing images","volume":"41","author":"Yin","year":"2022","journal-title":"Netw. Secur. Data Gov"},{"key":"B39","doi-asserted-by":"publisher","first-page":"109334","DOI":"10.1016\/j.optlastec.2023.109334","article-title":"A novel CS 2G-starlet denoising method for high noise astronomical image","volume":"163","author":"Zhang","year":"2023","journal-title":"Optics Laser Technol"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1422960\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T19:15:20Z","timestamp":1718133320000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1422960\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,7]]},"references-count":39,"alternative-id":["10.3389\/fnbot.2024.1422960"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1422960","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,7]]},"article-number":"1422960"}}