{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T23:14:01Z","timestamp":1772838841576,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T00:00:00Z","timestamp":1684800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>When using deep learning networks for dynamic feature rejection in SLAM systems, problems such as a priori static object motion leading to disturbed build quality and accuracy and slow system runtime are prone to occur. In this paper, based on the ORB-SLAM2 system, we propose a method based on improved YOLOv5 networks combined with geometric constraint methods for SLAM map building in dynamic environments. First, this paper uses ShuffleNetV2 to lighten the YOLOv5 network, which increases the improved network\u2019s operation speed without reducing the accuracy. At the same time, a pyramidal scene parsing network segmentation head is added to the head part of the YOLOv5 network to achieve semantic extraction in the environment, so that the improved YOLOv5 network has both target detection and semantic segmentation functions. In order to eliminate the objects with low dynamic features in the environment, this paper adopts the method of geometric constraints to extract and eliminate the dynamic features of the low dynamic objects. By combining the improved YOLOv5 network with the geometric constraint method, the robustness of the system is improved and the interference of dynamic targets in the construction of the SLAM system map is eliminated. The test results on the TUM dataset show that, when constructing a map in a dynamic environment, compared with the traditional ORB-SLAM2 algorithm, the accuracy of map construction in a dynamic environment is significantly improved. The absolute trajectory error is reduced by 97.7% compared with ORB-SLAM2, and the relative position error is reduced by 59.7% compared with ORB-SLAM2. Compared with DynaSLAM for dynamic scenes of the same type, the accuracy of map construction is slightly improved, but the maximum increase in keyframe processing time is 94.7%.<\/jats:p>","DOI":"10.3390\/ijgi12060211","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T03:20:06Z","timestamp":1684812006000},"page":"211","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Geometric Constraint-Based and Improved YOLOv5 Semantic SLAM for Dynamic Scenes"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1606-7686","authenticated-orcid":false,"given":"Ruidong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"117734","DOI":"10.1016\/j.eswa.2022.117734","article-title":"A survey of state-of-the-art on visual SLAM","volume":"205","author":"Kazerouni","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1007\/s12239-022-0063-5","article-title":"Moncular Vision SLAM Research for Parking Environment With low Light","volume":"23","author":"Zhang","year":"2022","journal-title":"Int. J. Automot. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s11370-021-00400-8","article-title":"An improved multi-object classification algorithm for visual SLAM under dynamic environment","volume":"15","author":"Wen","year":"2022","journal-title":"Intell. Serv. Robot."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: A Versatile and Accurate Monocular SLAM System","volume":"31","author":"Montiel","year":"2015","journal-title":"IEEE Trans. Robot."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1108\/AA-03-2022-0032","article-title":"Improved feature point extraction method of ORB-SLAM2 dense map","volume":"42","author":"Zhang","year":"2022","journal-title":"Assem. Autom."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","article-title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual\u2013Inertial, and Multimap SLAM","volume":"37","author":"Campos","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"ref_7","doi-asserted-by":"crossref","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. Autom. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yu, C., Liu, Z., Liu, X.J., Xie, F., Yang, Y., Wei, Q., and Fei, Q. (2018, January 1\u20135). DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments. Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.","DOI":"10.1109\/IROS.2018.8593691"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"21367","DOI":"10.1109\/ACCESS.2021.3053188","article-title":"Survey and Evaluation of RGB-D SLAM","volume":"9","author":"Zhang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1109\/LRA.2017.2724759","article-title":"RGB-D SLAM in dynamic environments using static point weighting","volume":"2","author":"Li","year":"2017","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_11","first-page":"277","article-title":"Constrained RGBD-SLAM","volume":"39","author":"Melbouci","year":"2020","journal-title":"Robotica"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.robot.2019.03.012","article-title":"Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment","volume":"117","author":"Xiao","year":"2019","journal-title":"Robot. Auton. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1007\/s11760-020-01846-6","article-title":"A dense map optimization method based on common-view geometry","volume":"15","author":"Jiang","year":"2021","journal-title":"Signal Image Video Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10846-022-01613-4","article-title":"KSF-SLAM: A Key Segmentation Frame Based Semantic SLAM in Dynamic Environments","volume":"105","author":"Zhao","year":"2022","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhang, R., Jin, S., and Yi, X. (2022). PFD-SLAM: A New RGB-D SLAM for Dynamic Indoor Environments Based on Non-Prior Semantic Segmentation. Remote Sens., 14.","DOI":"10.3390\/rs14102445"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6011","DOI":"10.1007\/s00521-021-06764-3","article-title":"YOLO-SLAM: A semantic SLAM system towards dynamic environment with geometric constraint","volume":"34","author":"Wu","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez-Otzeta, J.M., Rodr\u00edguez-Moreno, I., Mendialdua, I., and Sierra, B. (2022). RANSAC for Robotic Applications: A Survey. Sensors, 23.","DOI":"10.3390\/s23010327"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31729","DOI":"10.1007\/s11042-021-11168-5","article-title":"GMSK-SLAM: A new RGB-D SLAM method with dynamic areas detection towards dynamic environments","volume":"80","author":"Wei","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zhu, J., Wang, F., Hu, X., and Ye, X. (2022). GMS-RANSAC: A Fast Algorithm for Removing Mismatches Based on ORB-SLAM2. Symmetry, 14.","DOI":"10.3390\/sym14050849"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.ins.2022.11.001","article-title":"K-means-G*: Accelerating k-means clustering algorithm utilizing primitive geometric concepts","volume":"618","author":"Ismkhan","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chang, Z., Wu, H., Sun, Y., and Li, C. (2022). RGB-D Visual SLAM Based on Yolov4-Tiny in Indoor Dynamic Environment. Micromachines, 13.","DOI":"10.3390\/mi13020230"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1002\/rob.22145","article-title":"YOLOv4-tiny-based robust RGB-D SLAM approach with point and surface feature fusion in complex indoor environments","volume":"40","author":"Chang","year":"2023","journal-title":"J. Field Robot."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1007\/s10846-020-01222-z","article-title":"A Binocular MSCKF-Based Visual Inertial Odometry System Using LK Optical Flow","volume":"100","author":"Li","year":"2020","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5155","DOI":"10.3233\/JIFS-211615","article-title":"ESD-SLAM: An efficient semantic visual SLAM towards dynamic environments","volume":"42","author":"Xu","year":"2022","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"25442","DOI":"10.1109\/ACCESS.2020.2970238","article-title":"A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"43563","DOI":"10.1109\/ACCESS.2020.2977684","article-title":"Dynamic Scene Semantics SLAM Based on Semantic Segmentation","volume":"8","author":"Han","year":"2020","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, H., Yang, G., and Wang, Q. (2021, January 13\u201315). An Improved Image Segmentation Method of BiSeNetV2 Network. Proceedings of the the 4th International Conference on Control and Computer Vision, Macau, China.","DOI":"10.1145\/3484274.3484277"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"214685","DOI":"10.1109\/ACCESS.2020.3041038","article-title":"PSPNet-SLAM: A Semantic SLAM Detect Dynamic Object by Pyramid Scene Parsing Network","volume":"8","author":"Long","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yan, L., Hu, X., Zhao, L., Chen, Y., Wei, P., and Xie, H. (2022). DGS-SLAM: A Fast and Robust RGBD SLAM in Dynamic Environments Combined by Geometric and Semantic Information. Remote Sens., 14.","DOI":"10.3390\/rs14030795"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jung, H.K., and Choi, G.S. (2022). Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions. Appl. Sci., 12.","DOI":"10.3390\/app12147255"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, R., and Wang, X. (2022). Visual SLAM Mapping Based on YOLOv5 in Dynamic Scenes. Appl. Sci., 12.","DOI":"10.3390\/app122211548"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fu, Y., Lu, Y., and Ni, R. (2023). Chinese Lip-Reading Research Based on ShuffleNet and CBAM. Appl. Sci., 13.","DOI":"10.3390\/app13021106"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4993","DOI":"10.1007\/s12206-022-0912-1","article-title":"Tool wear state recognition under imbalanced data based on WGAN-GP and lightweight neural network ShuffleNet","volume":"36","author":"Hou","year":"2022","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ji, W., Pan, Y., Xu, B., and Wang, J. (2022). A Real-Time Apple Targets Detection Method for Picking Robot Based on ShufflenetV2-YOLOX. Agriculture, 12.","DOI":"10.3390\/agriculture12060856"},{"key":"ref_35","unstructured":"Gao, X., Zhang, T., Liu, Y., and Yan, Q. (2017). 14 Lectures on Visual SLAM: From Theory to Practice, Publishing House of Electronics Industry."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/12\/6\/211\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:40:00Z","timestamp":1760125200000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/12\/6\/211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,23]]},"references-count":35,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["ijgi12060211"],"URL":"https:\/\/doi.org\/10.3390\/ijgi12060211","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,23]]}}}