{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T15:14:36Z","timestamp":1777907676791,"version":"3.51.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T00:00:00Z","timestamp":1757030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T00:00:00Z","timestamp":1757030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11760-025-04614-6","type":"journal-article","created":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T16:04:34Z","timestamp":1757088274000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Navigating beyond sight: a real-time 3D audio-enhanced object detection system for empowering visually impaired spatial awareness"],"prefix":"10.1007","volume":"19","author":[{"given":"Ankit","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Abhishek","family":"kumar","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Raja","sequence":"additional","affiliation":[]},{"given":"Amit Kumar","family":"Dewangan","sequence":"additional","affiliation":[]},{"given":"Manoj","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Aradhana","family":"Soni","sequence":"additional","affiliation":[]},{"given":"Dheeraj","family":"Agarwal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,5]]},"reference":[{"key":"4614_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.: YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. (2020)"},{"key":"4614_CR2","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788. (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"4614_CR3","first-page":"4086","volume":"16","author":"H Hu","year":"2021","unstructured":"Hu, H., et al.: End-to-end encrypted video conference. IEEE Trans. Inf. Forensics Secur. 16, 4086\u20134097 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"4614_CR4","unstructured":"Zhou, L., et al.: Scene recognition using object cues. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3137\u20133146. (2017)"},{"issue":"4","key":"4614_CR5","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1177\/0145482X1310700408","volume":"107","author":"A Fallah","year":"2013","unstructured":"Fallah, A., Khademi, M., Taherian, A.: Indoor navigation systems for the visually impaired: A review. J. Visual Impairment Blindness. 107(4), 317\u2013329 (2013)","journal-title":"J. Visual Impairment Blindness"},{"issue":"7","key":"4614_CR6","first-page":"1715","volume":"20","author":"TS Sasaki","year":"2018","unstructured":"Sasaki, T.S., Shinozaki, S., Kondo, K.: Binaural sound rendering in virtual spaces for immersive experiences. IEEE Trans. Multimedia. 20(7), 1715\u20131724 (2018)","journal-title":"IEEE Trans. Multimedia"},{"issue":"5","key":"4614_CR7","first-page":"1533","volume":"17","author":"P Ran","year":"2017","unstructured":"Ran, P., Zhang, L., Zhao, Y.: Smartphone-based assistive navigation system for the visually impaired. IEEE Sens. J. 17(5), 1533\u20131543 (2017)","journal-title":"IEEE Sens. J."},{"issue":"1","key":"4614_CR8","doi-asserted-by":"publisher","first-page":"art86","DOI":"10.1186\/s44147-025-00661-5","volume":"72","author":"MH Moktar","year":"2025","unstructured":"Moktar, M.H., Mohamed, H., Hajjaj, S.S.H., Baharuddin, M.Z.: Medical waste sorting machine development with IoT and YOLO model utilization. J. Eng. Appl. Sci. 72(1), art86 (2025). https:\/\/doi.org\/10.1186\/s44147-025-00661-5","journal-title":"J. Eng. Appl. Sci."},{"issue":"1","key":"4614_CR9","doi-asserted-by":"publisher","first-page":"art2026","DOI":"10.1038\/s41598-025-86593-9","volume":"15","author":"X Huang","year":"2025","unstructured":"Huang, X., Li, X., Yuan, L., Jiang, Z., Jin, H., Wu, W., Cai, R., Zheng, M., Bai, H.: SDES-YOLO: A high-precision and lightweight model for fall detection in complex environments. Sci. Rep. 15(1), art2026 (2025). https:\/\/doi.org\/10.1038\/s41598-025-86593-9","journal-title":"Sci. Rep."},{"issue":"1","key":"4614_CR10","doi-asserted-by":"publisher","first-page":"art5069","DOI":"10.1038\/s41598-025-89214-7","volume":"15","author":"H Wang","year":"2025","unstructured":"Wang, H., Xu, S., Chen, Y., Su, C.: LFD-YOLO: A lightweight fall detection network with enhanced feature extraction and fusion. Sci. Rep. 15(1), art5069 (2025). https:\/\/doi.org\/10.1038\/s41598-025-89214-7","journal-title":"Sci. Rep."},{"issue":"1","key":"4614_CR11","doi-asserted-by":"publisher","first-page":"art21","DOI":"10.1186\/s13007-025-01341-4","volume":"21","author":"J Qi","year":"2025","unstructured":"Qi, J., Ding, C., Zhang, R., Xie, Y., Li, L., Zhang, W., Chen, L.: UAS-based MT-YOLO model for detecting missed tassels in hybrid maize detasseling. Plant. Methods. 21(1), art21 (2025). https:\/\/doi.org\/10.1186\/s13007-025-01341-4","journal-title":"Plant. Methods"},{"issue":"1","key":"4614_CR12","doi-asserted-by":"publisher","first-page":"art45","DOI":"10.1007\/s11220-025-00575-9","volume":"26","author":"A Kumar","year":"2025","unstructured":"Kumar, A., Katal, N.: A lightweight YOLO model for detection of disease from optic disc region of eye fundus imagery. Sens. Imaging. 26(1), art45 (2025). https:\/\/doi.org\/10.1007\/s11220-025-00575-9","journal-title":"Sens. Imaging"},{"issue":"1","key":"4614_CR13","doi-asserted-by":"publisher","first-page":"art13067","DOI":"10.1038\/s41598-025-98286-4","volume":"15","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Jia, N.: A target detection model HR-YOLO for advanced driver assistance systems in foggy conditions. Sci. Rep. 15(1), art13067 (2025). https:\/\/doi.org\/10.1038\/s41598-025-98286-4","journal-title":"Sci. Rep."},{"key":"4614_CR14","doi-asserted-by":"publisher","first-page":"art128574","DOI":"10.1016\/j.eswa.2025.128574","volume":"294","author":"V Dachepalli","year":"2025","unstructured":"Dachepalli, V., Gavini, S.: A virtually assisted digital twin enabled object detection in smart industrial manufacturing. Expert Syst. Appl. 294, art128574 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.128574","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"4614_CR15","doi-asserted-by":"publisher","first-page":"art11105","DOI":"10.1038\/s41598-025-94936-9","volume":"15","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Liu, Y., Guo, X., Ling, X., Geng, Q.: Metal surface defect detection using SLF-YOLO enhanced YOLOv8 model. Sci. Rep. 15(1), art11105 (2025). https:\/\/doi.org\/10.1038\/s41598-025-94936-9","journal-title":"Sci. Rep."},{"issue":"1","key":"4614_CR16","doi-asserted-by":"publisher","first-page":"art13171","DOI":"10.1038\/s41598-025-96035-1","volume":"15","author":"K Zhao","year":"2025","unstructured":"Zhao, K., Peng, S., Li, Y., Lu, T.: A lightweight Xray-YOLO-Mamba model for prohibited item detection in X-ray images using selective state space models. Sci. Rep. 15(1), art13171 (2025). https:\/\/doi.org\/10.1038\/s41598-025-96035-1","journal-title":"Sci. Rep."},{"issue":"1","key":"4614_CR17","doi-asserted-by":"publisher","first-page":"art4753","DOI":"10.1038\/s41598-025-88857-w","volume":"15","author":"H Zhang","year":"2025","unstructured":"Zhang, H., Xiao, P., Yao, F., Zhang, Q., Gong, Y.: Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO. Sci. Rep. 15(1), art4753 (2025). https:\/\/doi.org\/10.1038\/s41598-025-88857-w","journal-title":"Sci. Rep."},{"issue":"12","key":"4614_CR18","first-page":"6125","volume":"28","author":"Q Lin","year":"2019","unstructured":"Lin, Q., et al.: Place recognition for visually impaired using large-scale image datasets. IEEE Trans. Image Process. 28(12), 6125\u20136137 (2019)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"4614_CR19","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1177\/0018720813492327","volume":"56","author":"P Sarter","year":"2014","unstructured":"Sarter, P.: Cognitive overload in human-computer interaction: A review of issues and mitigation strategies. Hum. Factors. 56(1), 151\u2013162 (2014)","journal-title":"Hum. Factors"},{"issue":"2","key":"4614_CR20","first-page":"323","volume":"18","author":"T Brown","year":"2016","unstructured":"Brown, T., et al.: Navigational aid using symbolic sounds for object detection. IEEE Trans. Multimedia. 18(2), 323\u2013334 (2016)","journal-title":"IEEE Trans. Multimedia"},{"key":"4614_CR21","volume-title":"3D Sound for Virtual Reality and Multimedia","author":"M Begault","year":"2000","unstructured":"Begault, M.: 3D Sound for Virtual Reality and Multimedia, 2nd edn. Academic, San Diego, CA (2000)","edition":"2"},{"key":"4614_CR22","unstructured":"Schmidt, J., et al.: Indoor navigation for visually impaired using binaural sound. IEEE Transactions on Human-Machine Systems, 43(6), 682\u2013695 (2013)"},{"key":"4614_CR23","doi-asserted-by":"publisher","unstructured":"Ellenberg, M.O., Krug, K., Fan, Y., Krzywinski, J., Dachselt, R., Younis, R., Wagner, M., Weitz, J., Rodriguez, A., Just, G., Bodenstedt, S., & Speidel, S. (2025). Endomersion: An immersive remote guidance and feedback system for robot-assisted minimally invasive surgery. Proceedings\u2013\u20092025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025, 1610\u20131611. https:\/\/doi.org\/10.1109\/VRW66409.2025.00450","DOI":"10.1109\/VRW66409.2025.00450"},{"key":"4614_CR24","doi-asserted-by":"publisher","unstructured":"Quintero, L., Bennaceur, E., Ahln\u00e4s, L., Bjorn, M.: Hands-on orchestra: hand-based interactive manipulation of spatial 3D audio in mixed reality. IMX 2025 - Proc. 2025 ACM Int. Conf. Interact. Media Experiences. 342\u2013345 (2025). https:\/\/doi.org\/10.1145\/3706370.3731713","DOI":"10.1145\/3706370.3731713"},{"issue":"2","key":"4614_CR25","doi-asserted-by":"publisher","first-page":"169","DOI":"10.18848\/1835-2014\/CGP\/v17i02\/169-191","volume":"17","author":"K Jablonska","year":"2025","unstructured":"Jablonska, K., Lambert, C., Lister, N., Abram, T., Dalton, C., Frontani, I.: Increasing museum accessibility for people with visual impairment using product development and additive manufacturing. Int. J. Incl. Museum. 17(2), 169\u2013191 (2025). https:\/\/doi.org\/10.18848\/1835-2014\/CGP\/v17i02\/169-191","journal-title":"Int. J. Incl. Museum"},{"key":"4614_CR26","doi-asserted-by":"publisher","unstructured":"Zou, C., Rhee, S.-Y., He, L., Chen, D., Yang, X.: Sounds of history: a digital twin approach to musical heritage preservation in virtual museums. Electronics (Switzerland), 13(12), art. no. 2388. https:\/\/doi.org\/10.3390\/electronics13122388","DOI":"10.3390\/electronics13122388"},{"key":"4614_CR27","doi-asserted-by":"publisher","unstructured":"Dong, Y., Guo, H., & Li, J. (2025). Enhancing empathy for visual impairments: a multi-modal approach in VR serious games. IEEE Transactions on Visualization and Computer Graphics, 31(5), 2954\u20132963. (2024). https:\/\/doi.org\/10.1109\/TVCG.2025.3549900","DOI":"10.1109\/TVCG.2025.3549900"},{"issue":"2","key":"4614_CR28","doi-asserted-by":"publisher","first-page":"art88","DOI":"10.1007\/s10055-025-01163-8","volume":"29","author":"P O\u2019Toole","year":"2025","unstructured":"O\u2019Toole, P., Mancini, M., Pitt, I., Maye, L.: Investigating musical Pitch-Colour associations in immersive virtual reality environments. Virtual Real. 29(2), art88 (2025)","journal-title":"Virtual Real."},{"key":"4614_CR29","doi-asserted-by":"publisher","unstructured":"DOI: https:\/\/doi.org\/10.1007\/s10055-025-01163-8","DOI":"10.1007\/s10055-025-01163-8"},{"key":"4614_CR30","first-page":"1260","volume":"1253","author":"F Coutinho","year":"2017","unstructured":"Coutinho, F., Santos, D., Ribeiro, P.: Object detection and 3D audio feedback for visually impaired navigation. Proc. IEEE Int. Conf. Comput. Vis. 1253, 1260 (2017)","journal-title":"Proc. IEEE Int. Conf. Comput. Vis."},{"issue":"3","key":"4614_CR31","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1109\/TNNLS.2019.2909425","volume":"31","author":"X Chen","year":"2020","unstructured":"Chen, X., Ma, L., Liu, Y.: Lightweight deep learning models for mobile vision systems. IEEE Trans. Neural Networks Learn. Syst. 31(3), 785\u2013798 (2020)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"4614_CR32","first-page":"22447","volume":"6","author":"Y Qi","year":"2018","unstructured":"Qi, Y., Liu, S., Tang, X.: Deep learning-based 3D object detection for visually impaired navigation. IEEE Access. 6, 22447\u201322457 (2018)","journal-title":"IEEE Access."},{"key":"4614_CR33","unstructured":"Brock, M., et al.: Real-time place recognition using YOLO and edge computing. Proc. IEEE Int. Conf. Edge Comput. 45\u201352. (2016)"},{"issue":"12","key":"4614_CR34","first-page":"5438","volume":"14","author":"Z Zhao","year":"2018","unstructured":"Zhao, Z., Xu, Y., Huang, X.: Edge computing for real-time object detection and 3D Spatial awareness. IEEE Trans. Industr. Inf. 14(12), 5438\u20135449 (2018)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"2","key":"4614_CR35","first-page":"345","volume":"16","author":"M Howard","year":"2017","unstructured":"Howard, M., Griffiths, D., Jackson, R.: Mobile device-based real-time object detection for assistive technology. IEEE Trans. Mob. Comput. 16(2), 345\u2013354 (2017)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"4614_CR36","doi-asserted-by":"publisher","first-page":"103569","DOI":"10.1016\/j.engappai.2020.103569","volume":"90","author":"L Wang","year":"2020","unstructured":"Wang, L., Wei, H.: Understanding of wheelchair ramp scenes for disabled people with visual impairments. Eng. Appl. Artif. Intell. 90, 103569 (2020). https:\/\/doi.org\/10.1016\/j.engappai.2020.103569","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"3","key":"4614_CR37","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/TAI.2021.3093505","volume":"2","author":"L Wang","year":"2021","unstructured":"Wang, L., Wei, H.: Reconstruction for indoor scenes based on an interpretable inference. IEEE Trans. Artif. Intell. 2(3), 251\u2013259 (2021). https:\/\/doi.org\/10.1109\/TAI.2021.3093505","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"5","key":"4614_CR38","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/MIS.2022.3166968","volume":"37","author":"L Wang","year":"2022","unstructured":"Wang, L., Wei, H.: Recognizing slanted deck scenes by non-Manhattan Spatial right-angle projection. IEEE. Intell. Syst. 37(5), 75\u201385 (2022). https:\/\/doi.org\/10.1109\/MIS.2022.3166968","journal-title":"IEEE. Intell. Syst."},{"issue":"3","key":"4614_CR39","first-page":"234","volume":"8","author":"R Hub","year":"2015","unstructured":"Hub, R., et al.: Human-computer interaction systems for the visually impaired: A review. IEEE Trans. Haptics. 8(3), 234\u2013245 (2015)","journal-title":"IEEE Trans. Haptics"},{"issue":"5","key":"4614_CR40","first-page":"1231","volume":"43","author":"BJ Paszke","year":"2021","unstructured":"Paszke, B.J., Chandra, A., Ghosh, R.: A comparative study of real-time object detection algorithms for autonomous navigation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1231\u20131242 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"4614_CR41","first-page":"2024","volume":"26","author":"Y Sasaki","year":"2018","unstructured":"Sasaki, Y., Nakamura, M., Okuda, S.: Combining binaural audio with object detection for enhanced Spatial awareness. IEEE Trans. Audio Speech Lang. Process. 26(12), 2024\u20132036 (2018)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"4614_CR42","first-page":"542","volume":"65","author":"J Cui","year":"2019","unstructured":"Cui, J., et al.: 3D sound generation with Spatial awareness for assistive technologies. IEEE Trans. Consum. Electron. 65(4), 542\u2013550 (2019)","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"5","key":"4614_CR43","first-page":"1421","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick, R., Donahue, J., Malik, J., Darrell, T.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(5), 1421\u20131436 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"4614_CR44","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s11263-018-1098-y","volume":"127","author":"K Lenc","year":"2019","unstructured":"Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. Int. J. Comput. Vision. 127(5), 361\u2013378 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"4614_CR45","first-page":"24547","volume":"9","author":"Y Hu","year":"2021","unstructured":"Hu, Y., Li, L., Liu, W.: Robustness analysis of deep learning object detection models for real-time applications. IEEE Access. 9, 24547\u201324561 (2021)","journal-title":"IEEE Access."},{"issue":"2","key":"4614_CR46","first-page":"359","volume":"15","author":"T Brock","year":"2018","unstructured":"Brock, T., Lindemann, S., Schneider, M.: Performance analysis of place recognition systems for assistive technology. IEEE Trans. Autom. Sci. Eng. 15(2), 359\u2013372 (2018)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"8","key":"4614_CR47","first-page":"1525","volume":"22","author":"C Brown","year":"2020","unstructured":"Brown, C., Rogers, L.: Augmented reality and 3D audio for visually impaired navigation. IEEE Trans. Multimedia. 22(8), 1525\u20131536 (2020)","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"4614_CR48","first-page":"52","volume":"22","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Sethi, J., Yadav, D.: 3D auditory feedback in assistive navigation systems: A review. IEEE Commun. Surv. Tutorials. 22(1), 52\u201374 (2020)","journal-title":"IEEE Commun. Surv. Tutorials"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04614-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04614-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04614-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T13:18:07Z","timestamp":1758547087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04614-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,5]]},"references-count":48,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4614"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04614-6","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,5]]},"assertion":[{"value":"13 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Institutional review board statement"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1009"}}