{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:46:39Z","timestamp":1782823599322,"version":"3.54.5"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-46920-0","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T23:09:38Z","timestamp":1782774578000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An instance-aware segmentation and optical flow based DVI-SLAM for dynamic environments"],"prefix":"10.1038","volume":"16","author":[{"given":"Yemineni","family":"Ashok","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mukesh Kumar","family":"Rohil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"46920_CR1","doi-asserted-by":"publisher","unstructured":"Azuma, R.\u00a0T. A survey of augmented reality. Presence: Teleoperators and Virtual Environments 6, 355\u2013385, https:\/\/doi.org\/10.1162\/pres.1997.6.4.355 (1997).","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"46920_CR2","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1109\/TVCG.2018.2868591","volume":"24","author":"K Kim","year":"2018","unstructured":"Kim, K., Billinghurst, M., Bruder, G., Duh, H.B.-L. & Welch, G. F. Revisiting trends in augmented reality research: A review of the 2nd decade of ismar (2008\u20132017). IEEE Trans. Visual Comput. Graphics 24, 2947\u20132962. https:\/\/doi.org\/10.1109\/TVCG.2018.2868591 (2018).","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"46920_CR3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/MRA.2006.1638022","volume":"13","author":"H Durrant-Whyte","year":"2006","unstructured":"Durrant-Whyte, H. & Bailey, T. Simultaneous localization and mapping: I. IEEE Robot. & Automat. Magazine 13, 99\u2013110. https:\/\/doi.org\/10.1109\/MRA.2006.1638022 (2006).","journal-title":"IEEE Robot. & Automat. Magazine"},{"key":"46920_CR4","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J. J. G., Montiel, J. M. & Tard\u00f3s, J. D. Orb-slam3: An accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Rob. 37, 1874\u20131890 (2021).","journal-title":"IEEE Trans. Rob."},{"key":"46920_CR5","doi-asserted-by":"crossref","unstructured":"Von Stumberg, L., Usenko, V. & Cremers, D. Direct sparse visual-inertial odometry using dynamic marginalization. In 2018 IEEE International Conference on Robotics and Automation (ICRA), 2510\u20132517 (IEEE, 2018).","DOI":"10.1109\/ICRA.2018.8462905"},{"key":"46920_CR6","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","volume":"34","author":"T Qin","year":"2018","unstructured":"Qin, T., Li, P. & Shen, S. Vins-mono: A robust and versatile monocular visual-inertial state estimator. IEEE Trans. Rob. 34, 1004\u20131020 (2018).","journal-title":"IEEE Trans. Rob."},{"key":"46920_CR7","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.3390\/s19102251","volume":"19","author":"Z Shan","year":"2019","unstructured":"Shan, Z., Li, R. & Schwertfeger, S. Rgbd-inertial trajectory estimation and mapping for ground robots. Sensors 19, 2251 (2019).","journal-title":"Sensors"},{"key":"46920_CR8","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/LRA.2017.2653359","volume":"2","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R. & Tard\u00f3s, J. D. Visual-inertial monocular slam with map reuse. IEEE Robot. Automation Lett. 2, 796\u2013803 (2017).","journal-title":"IEEE Robot. Automation Lett."},{"key":"46920_CR9","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1177\/0278364914554813","volume":"34","author":"S Leutenegger","year":"2015","unstructured":"Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R. & Furgale, P. Keyframe-based visual-inertial odometry using nonlinear optimization. Int. J. Robot. Res. 34, 314\u2013334 (2015).","journal-title":"Int. J. Robot. Res."},{"key":"46920_CR10","doi-asserted-by":"crossref","unstructured":"Yu, C. et al. Ds-slam: A semantic visual slam towards dynamic environments. In 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), 1168\u20131174 (IEEE, 2018).","DOI":"10.1109\/IROS.2018.8593691"},{"key":"46920_CR11","doi-asserted-by":"publisher","unstructured":"Zhong, F., Wang, S., Zhang, Z., Chen, C. & Wang, Y. Detect-slam: Making object detection and slam mutually beneficial. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 1001\u20131010, https:\/\/doi.org\/10.1109\/WACV.2018.00115 (2018).","DOI":"10.1109\/WACV.2018.00115"},{"key":"46920_CR12","doi-asserted-by":"crossref","unstructured":"Runz, M., Buffier, M. & Agapito, L. Maskfusion: Real-time recognition, tracking and reconstruction of multiple moving objects. In 2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 10\u201320 (IEEE, 2018).","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"46920_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.robot.2019.03.012","volume":"117","author":"L Xiao","year":"2019","unstructured":"Xiao, L., Wang, J., Qiu, X., Rong, Z. & Zou, X. Dynamic-slam: Semantic monocular visual localization and mapping based on deep learning in dynamic environment. Robot. Auton. Syst. 117, 1\u201316 (2019).","journal-title":"Robot. Auton. Syst."},{"key":"46920_CR14","doi-asserted-by":"crossref","unstructured":"Seg-slam: Dynamic indoor rgb-d visual slam integrating geometric and yolov5-based semantic information. Sensors24, 2102 (2024).","DOI":"10.3390\/s24072102"},{"key":"46920_CR15","doi-asserted-by":"crossref","unstructured":"Di-slam: A real-time enhanced rgb-d slam for dynamic indoor environments. Appl. Sci.15, 4446 (2025).","DOI":"10.3390\/app15084446"},{"key":"46920_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Bujanca, M. & Luj\u00e1n, M. Ngd-slam: Towards real-time dynamic slam without gpu. In 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 3467\u20133473, https:\/\/doi.org\/10.1109\/IROS60139.2025.11246202 (2025).","DOI":"10.1109\/IROS60139.2025.11246202"},{"key":"46920_CR17","unstructured":"Howard, A.\u00a0G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"46920_CR18","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4510\u20134520, https:\/\/doi.org\/10.1109\/CVPR.2018.00474 (2018).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"46920_CR19","doi-asserted-by":"crossref","unstructured":"Howard, A. et al. Searching for mobilenetv3. In Proceedings of the IEEE\/CVF international conference on computer vision, 1314\u20131324 (2019).","DOI":"10.1109\/ICCV.2019.00140"},{"key":"46920_CR20","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"46920_CR21","unstructured":"Visin, F. et al. Renet: A recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:1505.00393 (2015)."},{"key":"46920_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"46920_CR23","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A. & Cipolla, R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481\u20132495 (2017).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"46920_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2961\u20132969 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"key":"46920_CR25","volume-title":"& LeCun, Y","author":"F Huang","year":"2007","unstructured":"Huang, F. & Boureau, Y. & LeCun, Y (Ieee conference on computer vision and pattern recognition, Unsupervised learning of invariant feature hierarchies with applications to object recognition, 2007)."},{"key":"46920_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J. & Farhadi, A. Yolo9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, 7263\u20137271 (2017).","DOI":"10.1109\/CVPR.2017.690"},{"key":"46920_CR27","unstructured":"Duan, K. et al. Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, 6569\u20136578 (2019)."},{"key":"46920_CR28","doi-asserted-by":"crossref","unstructured":"Law, H. & Deng, J. Cornernet: Detecting objects as paired Keypoints. In Proceedings of the European conference on computer vision (ECCV), 734\u2013750 (2018).","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"46920_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, 2980\u20132988 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"46920_CR30","doi-asserted-by":"crossref","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In European conference on computer vision, 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"46920_CR31","unstructured":"Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 580\u2013587 (2014)."},{"key":"46920_CR32","unstructured":"Purkait, P., Zhao, C. & Zach, C. Spp-net: Deep absolute pose regression with synthetic views. arXiv preprint arXiv:1712.03452 (2017)."},{"key":"46920_CR33","doi-asserted-by":"crossref","unstructured":"Girshick, R. Fast r-CNN. In Proceedings of the IEEE international conference on computer vision, 1440\u20131448 (2015).","DOI":"10.1109\/ICCV.2015.169"},{"key":"46920_CR34","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-CNN: Towards real-time object detection with region proposal networks. Advances in neural information processing systems28 (2015)."},{"key":"46920_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2117\u20132125 (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"46920_CR36","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J. & Schmid, C. Modeling visual context is key to augmenting object detection datasets. In Proceedings of the European Conference on Computer Vision (ECCV), 364\u2013380 (2018).","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"46920_CR37","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Ssd: Single shot multibox detector. In Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, 21\u201337 (Springer, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"46920_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Microsoft coco: Common objects in context. In European conference on computer vision, 740\u2013755 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"46920_CR39","unstructured":"Dai, J., Li, Y., He, K. & Sun, J. R-fcn: Object detection via region-based fully convolutional networks. Adv. Neural Inf. Process. Syst.29 (2016)."},{"key":"46920_CR40","unstructured":"Li, Z. et al. Light-head r-CNN: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264 (2017)."},{"key":"46920_CR41","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J. et al. An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23, 24330\u201324342 (2022).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"46920_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3346488","volume":"73","author":"J Shen","year":"2024","unstructured":"Shen, J., Liu, N., Sun, H., Li, D. & Zhang, Y. An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Meas. 73, 1\u201316. https:\/\/doi.org\/10.1109\/TIM.2023.3346488 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"46920_CR43","doi-asserted-by":"crossref","unstructured":"Shen, J. et al. Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. (2025).","DOI":"10.1109\/TITS.2025.3642410"},{"key":"46920_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3132332","volume":"71","author":"J Shen","year":"2022","unstructured":"Shen, J. et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1\u201313. https:\/\/doi.org\/10.1109\/TIM.2021.3132332 (2022).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"46920_CR45","unstructured":"R\u00fcnz, M. & Agapito, L. Co-fusion: Real-time segmentation, tracking and fusion of multiple objects. In 2017 IEEE International Conference on Robotics and Automation (ICRA), 4471\u20134478 (IEEE, 2017)."},{"key":"46920_CR46","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W. & Cremers, D. A benchmark for the evaluation of rgb-d slam systems. In 2012 IEEE\/RSJ international conference on intelligent robots and systems, 573\u2013580 (IEEE, 2012).","DOI":"10.1109\/IROS.2012.6385773"},{"key":"46920_CR47","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1109\/TRO.2019.2909168","volume":"35","author":"S Yang","year":"2019","unstructured":"Yang, S. & Scherer, S. Cubeslam: Monocular 3-d object slam. IEEE Trans. Rob. 35, 925\u2013938 (2019).","journal-title":"IEEE Trans. Rob."},{"key":"46920_CR48","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P. & Urtasun, R. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, 3354\u20133361 (IEEE, 2012).","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"46920_CR49","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Ssd: Single shot multibox detector. In European conference on computer vision, 21\u201337 (Springer, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"46920_CR50","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","volume":"3","author":"B Bescos","year":"2018","unstructured":"Bescos, B., F\u00e1cil, J. M., Civera, J. & Neira, J. Dynaslam: Tracking, mapping, and inpainting in dynamic scenes. IEEE Robot. Automat. Lett. 3, 4076\u20134083 (2018).","journal-title":"IEEE Robot. Automat. Lett."},{"key":"46920_CR51","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.3390\/s19173714","volume":"19","author":"G Liu","year":"2019","unstructured":"Liu, G., Zeng, W., Feng, B. & Xu, F. Dms-slam: A general visual slam system for dynamic scenes with multiple sensors. Sensors 19, 3714 (2019).","journal-title":"Sensors"},{"key":"46920_CR52","doi-asserted-by":"publisher","first-page":"166528","DOI":"10.1109\/ACCESS.2019.2952161","volume":"7","author":"L Cui","year":"2019","unstructured":"Cui, L. & Ma, C. Sof-slam: A semantic visual slam for dynamic environments. IEEE Access 7, 166528\u2013166539 (2019).","journal-title":"IEEE Access"},{"key":"46920_CR53","doi-asserted-by":"publisher","first-page":"202","DOI":"10.3390\/ijgi9040202","volume":"9","author":"J Cheng","year":"2020","unstructured":"Cheng, J., Wang, Z., Zhou, H., Li, L. & Yao, J. Dm-slam: A feature-based slam system for rigid dynamic scenes. ISPRS Int. J. Geo Inf. 9, 202 (2020).","journal-title":"ISPRS Int. J. Geo Inf."},{"key":"46920_CR54","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.1109\/LRA.2021.3068640","volume":"6","author":"B Bescos","year":"2021","unstructured":"Bescos, B., Campos, C., Tard\u00f3s, J. D. & Neira, J. Dynaslam II: Tightly-coupled multi-object tracking and slam. IEEE Robot. Automat. Lett. 6, 5191\u20135198 (2021).","journal-title":"IEEE Robot. Automat. Lett."},{"key":"46920_CR55","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s10846-021-01414-1","volume":"102","author":"JCV Soares","year":"2021","unstructured":"Soares, J. C. V., Gattass, M. & Meggiolaro, M. A. Crowd-slam: Visual slam towards crowded environments using object detection. J. Intell. & Robot. Syst. 102, 50 (2021).","journal-title":"J. Intell. & Robot. Syst."},{"key":"46920_CR56","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Wang, C., Wang, W., Henein, M. & Scherer, S. Airdos: Dynamic slam benefits from articulated objects. In 2022 International Conference on Robotics and Automation (ICRA), 8047\u20138053 (IEEE, 2022).","DOI":"10.1109\/ICRA46639.2022.9811667"},{"key":"46920_CR57","unstructured":"Jocher, G. et al. ultralytics\/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations. Zenodo (2022)."},{"key":"46920_CR58","unstructured":"Ypr-slam: A dynamic slam method combining object detection and geometric constraints. J. Robot. Autonomous Syst. (2024)."},{"key":"46920_CR59","unstructured":"Var-slam: Visual adaptive and robust slam for dynamic environments. arXiv preprint arXiv:2510.16205 (2025)."},{"key":"46920_CR60","unstructured":"Bochkovskiy, A., Wang, C.-Y. & Liao, H.-Y.\u00a0M. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)."},{"key":"46920_CR61","unstructured":"Il-slam: Intelligent line-assisted slam based on feature awareness for dynamic environments. arXiv preprint arXiv:2509.02972 (2025)."},{"key":"46920_CR62","unstructured":"Varghese, R. & Sambath, M. Yolov8: A novel object detection algorithm with enhanced performance and robustness. In 2024 International conference on advances in data engineering and intelligent computing systems (ADICS), 1\u20136 (IEEE, 2024)."},{"key":"46920_CR63","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R. & Malik, J. Simultaneous detection and segmentation. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII 13, 297\u2013312 (Springer, 2014).","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"46920_CR64","unstructured":"Dai, J., He, K. & Sun, J. Instance-aware semantic segmentation via multi-task network cascades. In Proceed. IEEE Conf. Comput. Vision Pattern Recognition, 3150\u20133158 (2016)."},{"key":"46920_CR65","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J. M. M. & Tardos, J. D. Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31, 1147\u20131163 (2015).","journal-title":"IEEE Trans. Rob."},{"key":"46920_CR66","doi-asserted-by":"crossref","unstructured":"Ballester, I., Font\u00e1n, A., Civera, J., Strobl, K.\u00a0H. & Triebel, R. Dot: Dynamic object tracking for visual slam. In 2021 IEEE International Conference on Robotics and Automation (ICRA), 11705\u201311711 (IEEE, 2021).","DOI":"10.1109\/ICRA48506.2021.9561452"},{"key":"46920_CR67","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1177\/0278364916669237","volume":"35","author":"T Whelan","year":"2016","unstructured":"Whelan, T., Salas-Moreno, R. F., Glocker, B., Davison, A. J. & Leutenegger, S. Elasticfusion: Real-time dense slam and light source estimation. Int. J. Robot. Res. 35, 1697\u20131716 (2016).","journal-title":"Int. J. Robot. Res."},{"key":"46920_CR68","unstructured":"Zhong, F., Wang, S., Zhang, Z. & Wang, Y. Detect-slam: Making object detection and slam mutually beneficial. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 1001\u20131010 (IEEE, 2018)."},{"key":"46920_CR69","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/s10514-021-09979-4","volume":"45","author":"S Wen","year":"2021","unstructured":"Wen, S. et al. Semantic visual slam in dynamic environment. Auton. Robot. 45, 493\u2013504 (2021).","journal-title":"Auton. Robot."},{"key":"46920_CR70","doi-asserted-by":"publisher","first-page":"87754","DOI":"10.1109\/ACCESS.2022.3199350","volume":"10","author":"P Su","year":"2022","unstructured":"Su, P., Luo, S. & Huang, X. Real-time dynamic slam algorithm based on deep learning. IEEE Access 10, 87754\u201387766. https:\/\/doi.org\/10.1109\/ACCESS.2022.3199350 (2022).","journal-title":"IEEE Access"},{"key":"46920_CR71","doi-asserted-by":"crossref","unstructured":"Xue, Y. et al. Fmtrack: Frequency-aware interaction and multi-expert fusion for rgb-t tracking. IEEE Trans. Circuit. Syst. Video Technol. (2025).","DOI":"10.1109\/TCSVT.2025.3601598"},{"key":"46920_CR72","unstructured":"Xue, Y. et al. Target-distractor aware UAV tracking via global agent. IEEE Trans. Intell. Transp. Syst. (2025)."},{"key":"46920_CR73","first-page":"6101","volume":"35","author":"D Liu","year":"2021","unstructured":"Liu, D. et al. Densernet: Weakly supervised visual localization using multi-scale feature aggregation. Proceed. AAAI Conf. Artif. intell. 35, 6101\u20136109 (2021).","journal-title":"Proceed. AAAI Conf. Artif. intell."},{"key":"46920_CR74","doi-asserted-by":"crossref","unstructured":"Yan, L. et al. Radiance field learners as UAV first-person viewers. In European Conference on Computer Vision, 88\u2013107 (Springer, 2024).","DOI":"10.1007\/978-3-031-73030-6_6"},{"key":"46920_CR75","doi-asserted-by":"crossref","unstructured":"Bian, J. et al. Gms: Grid-based motion statistics for fast, ultra-robust feature correspondence. In Proceed. IEEE Conf. Comput. Vision Patt. Recognition, 4181\u20134190 (2017).","DOI":"10.1109\/CVPR.2017.302"},{"key":"46920_CR76","doi-asserted-by":"crossref","unstructured":"Merzlyakov, A. & Macenski, S. A comparison of modern general-purpose visual slam approaches. In 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 9190\u20139197 (IEEE, 2021).","DOI":"10.1109\/IROS51168.2021.9636615"},{"key":"46920_CR77","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1109\/TETC.2021.3104555","volume":"10","author":"J Li","year":"2021","unstructured":"Li, J., Ye, D. H., Kolsch, M., Wachs, J. P. & Bouman, C. A. Fast and robust UAV to UAV detection and tracking from video. IEEE Trans. Emerg. Top. Comput. 10, 1519\u20131531 (2021).","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"46920_CR78","doi-asserted-by":"crossref","unstructured":"Shi, J. et al. Good features to track. In 1994 Proceedings of IEEE conference on computer vision and pattern recognition, 593\u2013600 (IEEE, 1994).","DOI":"10.1109\/CVPR.1994.323794"},{"key":"46920_CR79","unstructured":"Lucas, B.\u00a0D. & Kanade, T. An iterative image registration technique with an application to stereo vision. In IJCAI\u201981: 7th international joint conference on Artificial intelligence, vol.\u00a02, 674\u2013679 (1981)."},{"key":"46920_CR80","doi-asserted-by":"publisher","unstructured":"Schubert, D. et al. The tum vi benchmark for evaluating visual-inertial odometry. In 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 1680\u20131687, https:\/\/doi.org\/10.1109\/IROS.2018.8593419 (2018).","DOI":"10.1109\/IROS.2018.8593419"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46920-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46920-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46920-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:05:52Z","timestamp":1782821152000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-46920-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":80,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["46920"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-46920-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"31 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19852"}}