{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:53:40Z","timestamp":1769842420665,"version":"3.49.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"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:sec><jats:title>Introduction<\/jats:title><jats:p>Simultaneous Localization and Mapping (SLAM) is a technology used in intelligent systems such as robots and autonomous vehicles. Visual SLAM has become a more popular type of SLAM due to its acceptable cost and good scalability when applied in robot positioning, navigation and other functions. However, most of the visual SLAM algorithms assume a static environment, so when they are implemented in highly dynamic scenes, problems such as tracking failure and overlapped mapping are prone to occur.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To deal with this issue, we propose ISFM-SLAM, a dynamic visual SLAM built upon the classic ORB-SLAM2, incorporating an improved instance segmentation network and enhanced feature matching. Based on YOLACT, the improved instance segmentation network applies the multi-scale residual network Res2Net as its backbone, and utilizes CIoU_Loss in the bounding box loss function, to enhance the detection accuracy of the segmentation network. To improve the matching rate and calculation efficiency of the internal feature points, we fuse ORB key points with an efficient image descriptor to replace traditional ORB feature matching of ORB-SLAM2. Moreover, the motion consistency detection algorithm based on external variance values is proposed and integrated into ISFM-SLAM, to assist the proposed SLAM systems in culling dynamic feature points more effectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results and discussion<\/jats:title><jats:p>Simulation results on the TUM dataset show that the overall pose estimation accuracy of the ISFM-SLAM is 97% better than the ORB-SLAM2, and is superior to other mainstream and state-of-the-art dynamic SLAM systems. Further real-world experiments validate the feasibility of the proposed SLAM system in practical applications.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1473937","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:10:01Z","timestamp":1732097401000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["ISFM-SLAM: dynamic visual SLAM with instance segmentation and feature matching"],"prefix":"10.3389","volume":"18","author":[{"given":"Chao","family":"Li","sequence":"first","affiliation":[]},{"given":"Yang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Jianqiang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jianhai","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Sun","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"A deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan","year":"2015","journal-title":"Arxiv"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","article-title":"DynaSLAM: tracking, mapping, and inpainting in dynamic scenes","volume":"3","author":"Bescos","year":"2018","journal-title":"IEEE Robot. Automat. Lett."},{"key":"ref3","first-page":"9157","article-title":"Yolact: real-time instance segmentation","author":"Bolya","year":"2019"},{"key":"ref4","first-page":"780","article-title":"A robust SLAM for highly dynamic environments","author":"Cai","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"166528","DOI":"10.1109\/ACCESS.2019.2952161","article-title":"SOF-SLAM: a semantic visual SLAM for dynamic environments","volume":"7","author":"Cui","year":"2019","journal-title":"IEEE Access"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1109\/TPAMI.2007.1049","article-title":"MonoSLAM: Real-time single camera SLAM","volume":"29","author":"Davison","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref7","first-page":"834","article-title":"LSD-SLAM: Large-scale direct monocular SLAM","volume-title":"Computer Vision \u2013 ECCV 2014. ECCV 2014. Lecture Notes in Computer Science","author":"Engel","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2net: a new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref9","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"13210","DOI":"10.1109\/JSEN.2023.3270534","article-title":"OVD-SLAM: an online visual SLAM for dynamic environments","volume":"23","author":"He","year":"2023","journal-title":"IEEE Sensors J."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","article-title":"EP n P: an accurate O (n) solution to the P n P problem","volume":"81","author":"Lepetit","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1911.02855","DOI":"10.48550\/arXiv.1911.02855","article-title":"Dice loss for data-imbalanced NLP tasks","author":"Li","year":"2019","journal-title":"Arxiv"},{"key":"ref13","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras","volume":"33","author":"Mur-Artal","year":"2017","journal-title":"IEEE Trans. Robot."},{"key":"ref15","first-page":"863","article-title":"Boosting for regression transfer","author":"Pardoe","year":"2010"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1080\/2150704X.2017.1415473","article-title":"Accurate non-maximum suppression for object detection in high-resolution remote sensing images","volume":"9","author":"Qiu","year":"2018","journal-title":"Remote Sens. Lett."},{"key":"ref17","first-page":"7833","article-title":"Fouriernet: compact mask representation for instance segmentation using differentiable shape decoders","author":"Riaz","year":"2021"},{"key":"ref18","first-page":"406","article-title":"Houghnet: integrating near and long-range evidence for bottom-up object detection","author":"Samet","year":"2020"},{"key":"ref19","first-page":"573","article-title":"A benchmark for the evaluation of RGB-D SLAM systems","author":"Sturm","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"87754","DOI":"10.1109\/ACCESS.2022.3199350","article-title":"Real-time dynamic SLAM algorithm based on deep learning","volume":"10","author":"Su","year":"2022","journal-title":"IEEE Access"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.patrec.2020.04.005","article-title":"BEBLID: boosted efficient binary local image descriptor","volume":"133","author":"Su\u00e1rez","year":"2020","journal-title":"Pattern Recogn. Lett."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.robot.2016.11.012","article-title":"Improving RGB-D SLAM in dynamic environments: a motion removal approach","volume":"89","author":"Sun","year":"2017","journal-title":"Robot. Auton. Syst."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41074-017-0027-2","article-title":"Visual SLAM algorithms: a survey from 2010 to 2016","volume":"9","author":"Taketomi","year":"2017","journal-title":"IPSJ Trans. Comput. Vis. Appl."},{"key":"ref24","first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"ref25","first-page":"12193","article-title":"Polarmask: single shot instance segmentation with polar representation","author":"Xie","year":"2020"},{"key":"ref26","first-page":"1052","article-title":"Drso-slam: a dynamic rgb-d slam algorithm for indoor dynamic scenes","author":"Yu","year":"2021"},{"key":"ref27","first-page":"1168","article-title":"DS-SLAM: a semantic visual SLAM towards dynamic environments","author":"Yu","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref29","first-page":"2736","article-title":"ResNeSt: Split-attention networks","author":"Zhang","year":"2022"},{"key":"ref30","first-page":"12993","article-title":"Distance-IoU loss: faster and better learning for bounding box regression","author":"Zheng","year":"2020"},{"key":"ref31","first-page":"1001","article-title":"Detect-SLAM: making object detection and SLAM mutually beneficial","author":"Zhong","year":"2018"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1473937\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:10:03Z","timestamp":1732097403000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1473937\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":31,"alternative-id":["10.3389\/fnbot.2024.1473937"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1473937","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"article-number":"1473937"}}