{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:52:44Z","timestamp":1770814364602,"version":"3.50.1"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02139-z","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T10:34:45Z","timestamp":1768905285000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assisting blind people with AI and audio using smart glasses: system design with YOLOv8 variants comparisons"],"prefix":"10.1007","volume":"32","author":[{"given":"Priyanka","family":"Kumari","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4764-6039","authenticated-orcid":false,"given":"Ramy","family":"Hammady","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"2139_CR1","doi-asserted-by":"crossref","unstructured":"Ali, M., Zhang, Z.: The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection. Computers 2024a, 13, 336. In. (2024)","DOI":"10.3390\/computers13120336"},{"issue":"12","key":"2139_CR2","doi-asserted-by":"publisher","first-page":"336","DOI":"10.3390\/computers13120336","volume":"13","author":"ML Ali","year":"2024","unstructured":"Ali, M.L., Zhang, Z.: The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection. Computers. 13(12), 336 (2024b)","journal-title":"Computers"},{"key":"2139_CR3","doi-asserted-by":"crossref","unstructured":"Alter, J., Xue, J., Dimnaku, A., Smirni, E.: SSD failures in the field: symptoms, causes, and prediction models. Paper presented at the Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. (2019)","DOI":"10.1145\/3295500.3356172"},{"issue":"1","key":"2139_CR4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s10916-023-01908-5","volume":"47","author":"F Amore","year":"2023","unstructured":"Amore, F., Silvestri, V., Guidobaldi, M., Sulfaro, M., Piscopo, P., Turco, S., Rizzo, S.: Efficacy and patients\u2019 satisfaction with the ORCAM MyEye device among visually impaired people: A multicenter study. J. Med. Syst. 47(1), 11 (2023)","journal-title":"J. Med. Syst."},{"key":"2139_CR5","doi-asserted-by":"publisher","first-page":"170461","DOI":"10.1109\/ACCESS.2020.3021508","volume":"8","author":"L Aziz","year":"2020","unstructured":"Aziz, L., Salam, M.S.B.H., Sheikh, U.U., Ayub, S.: Exploring deep learning-based architecture, strategies, applications and current trends in generic object detection: A comprehensive review. IEEE Access. 8, 170461\u2013170495 (2020)","journal-title":"IEEE Access."},{"key":"2139_CR6","unstructured":"Benkirat, I.: Design and Implementation of a Real-Time Object Detection and Understanding System Using Deep Neural Network To Assist the Visually Impaired Persons. running on Raspberry Pi (2023)"},{"key":"2139_CR7","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. Paper presented at the 2016 IEEE international conference on image processing (ICIP). (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"2139_CR8","doi-asserted-by":"crossref","unstructured":"Bhuyan, M.K.: Computer Vision and Image Processing: Fundamentals and Applications. CRC (2019)","DOI":"10.1201\/9781351248396"},{"key":"2139_CR9","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. (2020)"},{"key":"2139_CR10","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. Paper presented at the European conference on computer vision. (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"2\u20133","key":"2139_CR11","doi-asserted-by":"publisher","first-page":"161","DOI":"10.3233\/TAD-140414","volume":"26","author":"A Cassinelli","year":"2014","unstructured":"Cassinelli, A., Sampaio, E., Joffily, S., Lima, H., Gusm\u00e3o, B.: Do blind people move more confidently with the tactile radar? Technol. Disabil. 26(2\u20133), 161\u2013170 (2014)","journal-title":"Technol. Disabil."},{"key":"2139_CR12","doi-asserted-by":"crossref","unstructured":"Casas, E., Ramos, L., Bendek, E., Rivas-Echeverr\u00eda, F.: Assessing the effectiveness of YOLO architectures for smoke and wildfire detection. IEEE Access. (2023)","DOI":"10.1109\/ACCESS.2023.3312217"},{"key":"2139_CR13","doi-asserted-by":"crossref","unstructured":"Chen, W., Luo, J., Zhang, F., Tian, Z.: A review of object detection: Datasets, performance evaluation, architecture, applications and current trends. Multimedia Tools Appl., 1\u201359. (2024)","DOI":"10.1007\/s11042-023-17949-4"},{"key":"2139_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: Yolo-world: Real-time open-vocabulary object detection. Paper presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"2139_CR15","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. Paper presented at the 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905). (2005)"},{"key":"2139_CR16","unstructured":"Doe, J., & Smith, J.: Enhancing Out-of-Model Scope Detection with TRust Your GENerator (TRYGEN). http:\/\/www.naisjournal.com\/static\/upload\/file\/20250326\/1742974333101187.pdf. (2021)"},{"key":"2139_CR17","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems, 27 (2014)"},{"issue":"2","key":"2139_CR18","doi-asserted-by":"publisher","first-page":"459","DOI":"10.18196\/jrc.v5i2.20900","volume":"5","author":"M Elavarasu","year":"2024","unstructured":"Elavarasu, M., Govindaraju, K.: Unveiling the advancements: YOLOv7 vs YOLOv8 in pulmonary carcinoma detection. J. Rob. Control (JRC). 5(2), 459\u2013470 (2024)","journal-title":"J. Rob. Control (JRC)"},{"key":"2139_CR19","doi-asserted-by":"crossref","unstructured":"Everding, L., Walger, L., Ghaderi, V.S., Conradt, J.: A mobility device for the blind with improved vertical resolution using dynamic vision sensors. Paper presented at the 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom). (2016)","DOI":"10.1109\/HealthCom.2016.7749459"},{"key":"2139_CR20","doi-asserted-by":"crossref","unstructured":"Fani Sani, M., Vazifehdoostirani, M., Park, G., Pegoraro, M., van Zelst, S.J., van der Aalst, W.M.: Event log sampling for predictive monitoring. Paper presented at the International Conference on Process Mining. (2021)","DOI":"10.1007\/978-3-030-98581-3_12"},{"key":"2139_CR21","unstructured":"Girshick, R.: Fast r-cnn. arXiv preprint arXiv:1504.08083. (2015)"},{"key":"2139_CR22","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan, S., Kartha, A., Schuchard, R., Fletcher, D.: Comparison of visual function analysis of people with low vision using three different models of augmented reality devices. medRxiv, 2024.2009. 2011.24313484. (2024)","DOI":"10.1101\/2024.09.11.24313484"},{"issue":"4","key":"2139_CR23","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1177\/0145482X211027492","volume":"115","author":"C Granquist","year":"2021","unstructured":"Granquist, C., Sun, S.Y., Montezuma, S.R., Tran, T.M., Gage, R., Legge, G.E.: Evaluation and comparison of artificial intelligence vision Aids: Orcam Myeye 1 and seeing Ai. J. Visual Impairment Blindness. 115(4), 277\u2013285 (2021)","journal-title":"J. Visual Impairment Blindness"},{"key":"2139_CR24","doi-asserted-by":"crossref","unstructured":"Hartley, R., & Zisserman, A.: Multiple view geometry in computer vision. Cambridge university press (2004)","DOI":"10.1017\/CBO9780511811685"},{"issue":"9","key":"2139_CR25","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"2139_CR26","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/s42486-023-00136-7","volume":"5","author":"J He","year":"2023","unstructured":"He, J., Song, X., Su, Y., Xiao, Z.: A smart obstacle avoiding technology based on depth camera for blind and visually impaired people. CCF Trans. Pervasive Comput. Interact. 5(4), 382\u2013395 (2023)","journal-title":"CCF Trans. Pervasive Comput. Interact."},{"key":"2139_CR27","doi-asserted-by":"crossref","unstructured":"He, C., Saha, P.: Investigating YOLO models towards outdoor obstacle detection for visually impaired people. ArXiv Preprint. (2023). arXiv:2312.07571","DOI":"10.21203\/rs.3.rs-3733857\/v1"},{"key":"2139_CR28","unstructured":"Henrique, V.: Image Enhancement: A Brief Introduction to Image Enhancement. (2023). Retrieved from https:\/\/medium.com\/@henriquevedoveli\/image-enhancement-4e18c1767c7"},{"issue":"7","key":"2139_CR29","doi-asserted-by":"publisher","first-page":"677","DOI":"10.3390\/machines11070677","volume":"11","author":"M Hussain","year":"2023","unstructured":"Hussain, M.: YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection. Machines. 11(7), 677 (2023)","journal-title":"Machines"},{"key":"2139_CR30","unstructured":"Hussain, M.: Yolov5, yolov8 and yolov10: The go-to detectors for real-time vision. arXiv preprint arXiv:2407.02988. (2024)"},{"key":"2139_CR31","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. (2017)"},{"key":"2139_CR32","unstructured":"Imhoff, J.: The Lancet Global Health: Vision loss could be treated in one billion people worldwide, unlocking human potential and accelerating global development. (2021)., 6 Jan Retrieved from https:\/\/www.michiganmedicine.org\/news-release\/lancet-global-health-vision-loss-could-be-treated-one-billion-people-worldwide"},{"key":"2139_CR33","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/ACCESS.2017.2766579","volume":"6","author":"R Jafri","year":"2017","unstructured":"Jafri, R., Campos, R.L., Ali, S.A., Arabnia, H.R.: Visual and infrared sensor data-based obstacle detection for the visually impaired using the Google project Tango tablet development kit and the unity engine. IEEE Access. 6, 443\u2013454 (2017)","journal-title":"IEEE Access."},{"key":"2139_CR34","unstructured":"Jakob: Vuzix Blade 2 Review. (2023). Retrieved from https:\/\/vrx.vr-expert.com\/vuzix-blade-2-review-vrx-by-vr-expert\/"},{"issue":"19","key":"2139_CR35","doi-asserted-by":"publisher","first-page":"10675","DOI":"10.3390\/app131910675","volume":"13","author":"F Jia","year":"2023","unstructured":"Jia, F., Afaq, M., Ripka, B., Huda, Q., Ahmad, R.: Vision-and Lidar-Based autonomous Docking and recharging of a mobile robot for machine tending in autonomous manufacturing environments. Appl. Sci. 13(19), 10675 (2023)","journal-title":"Appl. Sci."},{"key":"2139_CR36","unstructured":"Jocher, G., Stoken, A., Chaurasia, A., Borovec, J., Kwon, Y., Michael, K., Hogan, A.: ultralytics\/yolov5: v6. 0-YOLOv5n\u2019Nano\u2019models, Roboflow integration, TensorFlow export, OpenCV DNN support. Zenodo. (2022)"},{"key":"2139_CR37","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst., 25. (2012)"},{"issue":"3","key":"2139_CR38","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1109\/TMC.2018.2842751","volume":"18","author":"B Li","year":"2018","unstructured":"Li, B., Munoz, J.P., Rong, X., Chen, Q., Xiao, J., Tian, Y., Yousuf, M.: Vision-based mobile indoor assistive navigation aid for blind people. IEEE Trans. Mob. Comput. 18(3), 702\u2013714 (2018)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"2139_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"8","key":"2139_CR40","first-page":"3267","volume":"58","author":"M-C Lorenzini","year":"2017","unstructured":"Lorenzini, M.-C., Jarry, J., Wittich, W.: The impact of using eSight eyewear on functional vision and oculo-motor control in low vision patients. Investig. Ophthalmol. Vis. Sci. 58(8), 3267\u20133267 (2017)","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"2139_CR41","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neucom.2022.09.117","volume":"513","author":"Y-F Lu","year":"2022","unstructured":"Lu, Y.-F., Yu, Q., Gao, J.-W., Li, Y., Zou, J.-C., Qiao, H.: Cross stage partial connections based weighted Bi-directional feature pyramid and enhanced Spatial transformation network for robust object detection. Neurocomputing. 513, 70\u201382 (2022)","journal-title":"Neurocomputing"},{"key":"2139_CR42","unstructured":"Metz, R.: Augmented-Reality Glasses Could Help Legally Blind Navigate. (2015). Retrieved from https:\/\/www.technologyreview.com\/2015\/06\/15\/72902\/augmented-reality-glasses-could-help-legally-blind-navigate\/"},{"issue":"1","key":"2139_CR43","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2117\/psysoc.2022-B031","volume":"65","author":"T Miura","year":"2023","unstructured":"Miura, T.: Narrative review of assistive technologies and sensory substitution in people with visual and hearing impairment. Psychologia. 65(1), 70\u201399 (2023)","journal-title":"Psychologia"},{"issue":"1","key":"2139_CR44","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/3157075","volume":"61","author":"G Mone","year":"2017","unstructured":"Mone, G.: Feeling sounds, hearing sights. Commun. ACM. 61(1), 15\u201317 (2017)","journal-title":"Commun. ACM"},{"key":"2139_CR45","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3389\/fnbeh.2016.00079","volume":"10","author":"A Pasqualotto","year":"2016","unstructured":"Pasqualotto, A., Esenkaya, T.: Sensory substitution: The Spatial updating of auditory scenes mimics The Spatial updating of visual scenes. Front. Behav. Neurosci. 10, 79 (2016)","journal-title":"Front. Behav. Neurosci."},{"key":"2139_CR46","unstructured":"Pii, J.: Vuzix Blade 2 Review. (2023). Retrieved from https:\/\/vrx.vr-expert.com\/vuzix-blade-2-review-vrx-by-vr-expert\/"},{"issue":"15","key":"2139_CR47","doi-asserted-by":"publisher","first-page":"3404","DOI":"10.3390\/s19153404","volume":"19","author":"S Real","year":"2019","unstructured":"Real, S., Araujo, A.: Navigation systems for the blind and visually impaired: Past work, challenges, and open problems. Sensors. 19(15), 3404 (2019)","journal-title":"Sensors"},{"key":"2139_CR48","doi-asserted-by":"crossref","unstructured":"Redmon, J.: You only look once: Unified, real-time object detection. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2139_CR49","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"2139_CR50","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2139_CR51","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst., 28. (2015)"},{"key":"2139_CR52","doi-asserted-by":"crossref","unstructured":"Rodrigues, J.J., Aguiar, P.M., Xavier, J.M.: Ansig\u2014an analytic signature for permutation-invariant two-dimensional shape representation. Paper presented at the 2008 IEEE Conference on Computer Vision and Pattern Recognition. (2008)","DOI":"10.1109\/CVPR.2008.4587612"},{"key":"2139_CR53","doi-asserted-by":"crossref","unstructured":"Saputra, M.R.U., Santosa, P.I.: Obstacle avoidance for visually impaired using auto-adaptive thresholding on Kinect\u2019s depth image. Paper presented at the 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops. (2014)","DOI":"10.1109\/UIC-ATC-ScalCom.2014.108"},{"key":"2139_CR54","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the TesseractOCR engine. In Ninth international conference on document analysis and recognition (ICDAR2007) (Vol. 2, pp. 629-633). IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"2139_CR55","doi-asserted-by":"crossref","unstructured":"Szeliski, R.: Image processing. In Computer Vision: Algorithms and Applications (pp. 87-180). London: Springer London (2010)","DOI":"10.1007\/978-1-84882-935-0_3"},{"key":"2139_CR56","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. Paper presented at the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"4","key":"2139_CR57","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","volume":"5","author":"J Terven","year":"2023","unstructured":"Terven, J., C\u00f3rdova-Esparza, D.-M., Romero-Gonz\u00e1lez, J.-A.: A comprehensive review of Yolo architectures in computer vision: From Yolov1 to Yolov8 and Yolo-nas. Mach. Learn. Knowl. Extr. 5(4), 1680\u20131716 (2023)","journal-title":"Mach. Learn. Knowl. Extr."},{"issue":"1","key":"2139_CR58","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3390\/s25010214","volume":"25","author":"M Trigka","year":"2025","unstructured":"Trigka, M., Dritsas, E.: A comprehensive survey of machine learning techniques and models for object detection. Sensors. 25(1), 214 (2025)","journal-title":"Sensors"},{"key":"2139_CR59","unstructured":"Ultralytics: Ultralytics YOLO Docs. (2025). Retrieved from https:\/\/docs.ultralytics.com\/tasks\/detect\/"},{"key":"2139_CR60","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vision. 57, 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"2139_CR61","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Scaled-yolov4: Scaling cross stage partial network. Paper presented at the Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition. (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"issue":"4","key":"2139_CR62","doi-asserted-by":"publisher","first-page":"e383","DOI":"10.1016\/S2214-109X(21)00035-8","volume":"9","author":"A Webson","year":"2021","unstructured":"Webson, A.: Eye health and the decade of action for the sustainable development goals. Lancet Global Health. 9(4), e383\u2013e384 (2021)","journal-title":"Lancet Global Health"},{"key":"2139_CR63","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. Paper presented at the 2017 IEEE international conference on image processing (ICIP). (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"2139_CR64","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M.: YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems. APSIPA Trans. Signal. Inform. Process., 13(1). (2024)","DOI":"10.1561\/116.20240058"},{"key":"2139_CR65","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: Yolov10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458. (2024)"},{"key":"2139_CR66","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159. (2020)"},{"key":"2139_CR67","doi-asserted-by":"crossref","unstructured":"Zerroug, A., Cassinelli, A., Ishikawa, M.: Virtual haptic radar. In ACM SIGGRAPH ASIA 2009 Sketches (pp. 1\u20131). (2009)","DOI":"10.1145\/1667146.1667158"},{"issue":"9","key":"2139_CR68","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1109\/TNSRE.2017.2682265","volume":"25","author":"H Zhang","year":"2017","unstructured":"Zhang, H., Ye, C.: An indoor wayfinding system based on geometric features aided graph SLAM for the visually impaired. IEEE Trans. Neural Syst. Rehabil. Eng. 25(9), 1592\u20131604 (2017)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2139_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, C., Ding, W., Peng, G., Fu, F., & Wang, W.: Street view text recognition with deep learning for urban scene understanding in intelligent transportation systems. IEEE Trans. Int. Trans. Syst. 22(7), 4727-4743 (2020)","DOI":"10.1109\/TITS.2020.3017632"},{"key":"2139_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Chen, J.: Detrs beat yolos on real-time object detection. Paper presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"2139_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zhao, W., Guo, L., Xu, X., & Xie, G.: Real time detection of surface defects with inception-based Mobile Net-SSD detection network. InInternational Conference on Brain Inspired Cognitive Systems (pp. 510-519). Cham: Springer International Publishing (2019)","DOI":"10.1007\/978-3-030-39431-8_49"},{"key":"2139_CR72","unstructured":"Z\u00f6llner, M., Huber, S., Jetter, H.-C., Reiterer, H.: NAVI\u2013a proof-of-concept of a mobile navigational aid for visually impaired based on the microsoft kinect. Paper presented at the Human-Computer Interaction\u2013INTERACT 2011: 13th IFIP TC 13 International Conference, Lisbon, Portugal, September 5\u20139, 2011, Proceedings, Part IV 13. (2011)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02139-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02139-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02139-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:19:06Z","timestamp":1770783546000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02139-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2139"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02139-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]},"assertion":[{"value":"29 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 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":"Conflict of interest"}}],"article-number":"73"}}