{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T19:46:54Z","timestamp":1764704814104,"version":"3.46.0"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2025,12,2]]},"abstract":"<jats:p>Failing to be aware of speeding vehicles approaching from behind poses a huge threat to the road safety of pedestrians and cyclists. In this paper, we propose BlinkBud, which utilizes a single earbud and a paired phone to online detect hazardous objects approaching from behind of a user. The core idea is to accurately track visually identified objects utilizing a small number of sampled camera images taken from the earbud. To minimize the power consumption of the earbud and the phone while guaranteeing the best tracking accuracy, a novel 3D object tracking algorithm is devised, integrating both a Kalman filter based trajectory estimation scheme and an optimal image sampling strategy based on reinforcement learning. Moreover, the impact of constant user head movements on the tracking accuracy is significantly eliminated by leveraging the estimated pitch and yaw angles to correct the object depth estimation and align the camera coordinate system to the user's body coordinate system, respectively. We implement a prototype BlinkBud system and conduct extensive real-world experiments. Results show that BlinkBud is lightweight with ultra-low mean power consumptions of 29.8 mW and 702.6 mW on the earbud and smartphone, respectively, and can accurately detect hazards with a low average false positive ratio (FPR) and false negative ratio (FNR) of 4.90% and 1.47%, respectively.<\/jats:p>","DOI":"10.1145\/3770707","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T19:42:32Z","timestamp":1764704552000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BlinkBud: Detecting Hazards from Behind via Sampled Monocular 3D Detection on a Single Earbud"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5073-5561","authenticated-orcid":false,"given":"Yunzhe","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6279-6540","authenticated-orcid":false,"given":"Jiajun","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2850-7643","authenticated-orcid":false,"given":"Yuzhou","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1047-3317","authenticated-orcid":false,"given":"Kechen","family":"Liu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4629-7769","authenticated-orcid":false,"given":"Yize","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8857-0144","authenticated-orcid":false,"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southwest Petroleum University, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8657-5064","authenticated-orcid":false,"given":"Hongzi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4361-012X","authenticated-orcid":false,"given":"Li","family":"Lu","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5253-2549","authenticated-orcid":false,"given":"Shan","family":"Chang","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Donghua University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Pedestrians Traffic Safety Facts 2022 Data","author":"National Highway Traffic Safety Administration (NHTSA)","year":"2024","unstructured":"National Highway Traffic Safety Administration (NHTSA), \u201cPedestrians Traffic Safety Facts 2022 Data,\u201d 2024. Available at: https:\/\/crashstats.nhtsa.dot.gov\/Api\/Public\/Publication\/813590."},{"key":"e_1_2_1_2_1","first-page":"259","volume-title":"Transportation research part F: traffic psychology and behaviour","author":"Yadav A. K.","year":"2022","unstructured":"A. K. Yadav and N. R. Velaga, \u201cA systematic review of observational studies investigating the influence of mobile phone distraction on road crossing behaviour of pedestrians,\u201d Transportation research part F: traffic psychology and behaviour, vol. 91, pp. 236\u2013259, 2022."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712284"},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.trf.2025.03.001","article-title":"Does listening to music impact pedestrian safety while crossing the road? investigating using the vr approach","volume":"111","author":"Krishna K. V.","year":"2025","unstructured":"K. V. Krishna and P. Choudhary, \u201cDoes listening to music impact pedestrian safety while crossing the road? investigating using the vr approach,\u201d Transportation Research Part F: Traffic Psychology and Behaviour, vol. 111, pp. 162\u2013176, 2025.","journal-title":"Transportation Research Part F: Traffic Psychology and Behaviour"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/0361198119838519"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2020.10.083"},{"key":"e_1_2_1_7_1","first-page":"146","volume-title":"Proceedings of ACM MobiCom","author":"Shi S.","year":"2022","unstructured":"S. Shi, J. Cui, Z. Jiang, Z. Yan, G. Xing, J. Niu, and Z. Ouyang, \u201cVips: Real-time perception fusion for infrastructure-assisted autonomous driving,\u201d in Proceedings of ACM MobiCom, pp. 133\u2013146, 2022."},{"key":"e_1_2_1_8_1","first-page":"15","volume-title":"Proceedings of ACM MobiCom","author":"He Y.","year":"2023","unstructured":"Y. He, C. Bian, J. Xia, S. Shi, Z. Yan, Q. Song, and G. Xing, \u201cVi-map: Infrastructure-assisted real-time hd mapping for autonomous driving,\u201d in Proceedings of ACM MobiCom, pp. 1\u201315, 2023."},{"key":"e_1_2_1_9_1","volume-title":"Mobile safety application for pedestrians utilizing","author":"Gelbal S. Y.","year":"2022","unstructured":"S. Y. Gelbal, M. R. Cantas, B. A. Guvenc, L. Guvenc, G. Surnilla, and H. Zhang, \u201cMobile safety application for pedestrians utilizing p2v communication over bluetooth,\u201d tech. rep., SAE Technical Paper, 2022."},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","first-page":"1324060","DOI":"10.3389\/frobt.2024.1324060","article-title":"Augmented reality for supporting the interaction between pedestrians and automated vehicles: an experimental outdoor study","volume":"11","author":"Aleva T. K.","year":"2024","unstructured":"T. K. Aleva, W. Tabone, D. Dodou, and J. C. de Winter, \u201cAugmented reality for supporting the interaction between pedestrians and automated vehicles: an experimental outdoor study,\u201d Frontiers in robotics and AI, vol. 11, p. 1324060, 2024.","journal-title":"Frontiers in robotics and AI"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2163154"},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of FORUM ACUSTICUM","author":"Conter M.","year":"2014","unstructured":"M. Conter, M. Czuka, and R. Wehr, \u201cAustrian study on the acoustic perception of electric cars,\u201d in Proceedings of FORUM ACUSTICUM, 2014."},{"key":"e_1_2_1_13_1","volume-title":"Apple is \u2018actively developing\u2019 airpods with cameras","author":"Burkhardt M.","year":"2025","unstructured":"M. Burkhardt, \u201cApple is \u2018actively developing\u2019 airpods with cameras,\u201d 2025. Available at: https:\/\/9to5mac.com\/2025\/03\/09\/airpods-with-cameras-what-to-expect\/."},{"key":"e_1_2_1_14_1","volume-title":"Samsung is working on galaxy buds with cameras","year":"2025","unstructured":"GizmoChina, \u201cSamsung is working on galaxy buds with cameras,\u201d 2025. Available at: https:\/\/www.gizmochina.com\/2025\/01\/22\/samsung-in-working-on-galaxy-buds-with-cameras-claims-new-report."},{"key":"e_1_2_1_15_1","volume-title":"Meta is reportedly developing ai-enabled \u2018camerabuds\u2019","year":"2024","unstructured":"Hypebeast, \u201cMeta is reportedly developing ai-enabled \u2018camerabuds\u2019,\u201d 2024. Available at: https:\/\/hypebeast.com\/2024\/5\/meta-ai-enabled-headphones-earbuds-camerabuds-development-reports."},{"issue":"4","key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/S1369-8478(02)00033-5","article-title":"An evaluation of crosswalk warning systems: effects on pedestrian and vehicle behaviour","volume":"5","author":"Hakkert A. S.","year":"2002","unstructured":"A. S. Hakkert, V. Gitelman, and E. Ben-Shabat, \u201cAn evaluation of crosswalk warning systems: effects on pedestrian and vehicle behaviour,\u201d Transportation Research Part F: Traffic Psychology and Behaviour, vol. 5, no. 4, pp. 275\u2013292, 2002.","journal-title":"Transportation Research Part F: Traffic Psychology and Behaviour"},{"key":"e_1_2_1_17_1","first-page":"2815","volume-title":"Proceedings of IEEE ITSC","author":"Mohapatra S.","year":"2021","unstructured":"S. Mohapatra, S. Yogamani, H. Gotzig, S. Milz, and P. Mader, \u201cBevdetnet: Bird's eye view lidar point cloud based real-time 3d object detection for autonomous driving,\u201d in Proceedings of IEEE ITSC, pp. 2809\u20132815, IEEE, 2021."},{"issue":"18","key":"e_1_2_1_18_1","doi-asserted-by":"crossref","first-page":"6701","DOI":"10.3390\/ijerph17186701","article-title":"New risk situations related to low noise from electric vehicles: Perception of workers as pedestrians and other vehicle drivers","volume":"17","author":"Pardo-Ferreira M. C.","year":"2020","unstructured":"M. C. Pardo-Ferreira, J. A. Torrecilla-Garc\u00eda, C. L. Heras-Rosas, and J. C. Rubio-Romero, \u201cNew risk situations related to low noise from electric vehicles: Perception of workers as pedestrians and other vehicle drivers,\u201d International Journal of Environmental Research and Public Health, vol. 17, no. 18, p. 6701, 2020.","journal-title":"International Journal of Environmental Research and Public Health"},{"key":"e_1_2_1_19_1","first-page":"587","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Girshick R.","year":"2014","unstructured":"R. Girshick, J. Donahue, T. Darrell, et al., \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 580\u2013587, 2014."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_1_21_1","first-page":"16911","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Cheng T.","year":"2024","unstructured":"T. Cheng, L. Song, Y. Ge, W. Liu, X. Wang, and Y. Shan, \u201cYolo-world: Real-time open-vocabulary object detection,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 16901\u201316911, 2024."},{"key":"e_1_2_1_22_1","first-page":"17036","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Zhao C.","year":"2024","unstructured":"C. Zhao, Y. Sun, W. Wang, Q. Chen, E. Ding, Y. Yang, and J. Wang, \u201cMs-detr: Efficient detr training with mixed supervision,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 17027\u201317036, 2024."},{"key":"e_1_2_1_23_1","first-page":"4520","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Sandler M.","year":"2018","unstructured":"M. Sandler et al., \u201cMobilenetv2: Inverted residuals and linear bottlenecks,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 4510\u20134520, 2018."},{"key":"e_1_2_1_24_1","first-page":"2988","volume-title":"Proceedings of IEEE\/CVF ICCV","author":"Lin T. Y.","year":"2017","unstructured":"T. Y. Lin, P. Goyal, R. Girshick, et al., \u201cFocal loss for dense object detection,\u201d in Proceedings of IEEE\/CVF ICCV, pp. 2980\u20132988, 2017."},{"key":"e_1_2_1_25_1","first-page":"2049","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Chabot F.","year":"2017","unstructured":"F. Chabot, M. Chaouch, J. Rabarisoa, et al., \u201cDeep manta: A coarse-to-fine many-task network for joint 2d and 3d vehicle analysis from monocular image,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 2040\u20132049, 2017."},{"key":"e_1_2_1_26_1","article-title":"Exploiting ground depth estimation for mobile monocular 3d object detection","author":"Zhou Y.","year":"2025","unstructured":"Y. Zhou, Q. Liu, H. Zhu, Y. Li, S. Chang, and M. Guo, \u201cExploiting ground depth estimation for mobile monocular 3d object detection,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_27_1","first-page":"2374","volume-title":"Proceedings of NeurIPS","author":"Eigen D.","year":"2014","unstructured":"D. Eigen, C. Puhrsch, and R. Fergus, \u201cDepth map prediction from a single image using a multi-scale deep network,\u201d in Proceedings of NeurIPS, pp. 2366\u20132374, 2014."},{"key":"e_1_2_1_28_1","first-page":"3838","volume-title":"Proceedings of IEEE\/CVF ICCV","author":"Godard C.","year":"2019","unstructured":"C. Godard, O. Mac Aodha, M. Firman, et al., \u201cDigging into self-supervised monocular depth estimation,\u201d in Proceedings of IEEE\/CVF ICCV, pp. 3828\u20133838, 2019."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3699758"},{"key":"e_1_2_1_30_1","article-title":"Omnitracker: Unifying visual object tracking by tracking-with-detection","author":"Wang J.","year":"2025","unstructured":"J. Wang, Z. Wu, D. Chen, C. Luo, X. Dai, L. Yuan, and Y.-G. Jiang, \u201cOmnitracker: Unifying visual object tracking by tracking-with-detection,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of IEEE\/RSJ IROS","author":"Weng X.","year":"2020","unstructured":"X. Weng, J. Wang, D. Held, and K. Kitani, \u201c3D Multi-Object Tracking: A Baseline and New Evaluation Metrics,\u201d Proceedings of IEEE\/RSJ IROS, 2020."},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","first-page":"6504","DOI":"10.1609\/aaai.v38i7.28471","article-title":"Hybrid-sort: Weak cues matter for online multi-object tracking","volume":"38","author":"Yang M.","year":"2024","unstructured":"M. Yang, G. Han, B. Yan, W. Zhang, J. Qi, H. Lu, and D. Wang, \u201cHybrid-sort: Weak cues matter for online multi-object tracking,\u201d in Proceedings of AAAI, vol. 38, pp. 6504\u20136512, 2024.","journal-title":"Proceedings of AAAI"},{"key":"e_1_2_1_33_1","first-page":"19155","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Zheng G.","year":"2024","unstructured":"G. Zheng, S. Lin, H. Zuo, C. Fu, and J. Pan, \u201cNettrack: Tracking highly dynamic objects with a net,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 19145\u201319155, 2024."},{"key":"e_1_2_1_34_1","first-page":"8854","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Meinhardt T.","year":"2022","unstructured":"T. Meinhardt, A. Kirillov, L. Leal-Taixe, et al., \u201cTrackformer: Multi-object tracking with transformers,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 8844\u20138854, 2022."},{"key":"e_1_2_1_35_1","first-page":"8780","volume-title":"Proceedings of IEEE\/CVF CVPR","author":"Zhou X.","year":"2022","unstructured":"X. Zhou, T. Yin, V. Koltun, and P. Kr\u00e4henb\u00fchl, \u201cGlobal tracking transformers,\u201d in Proceedings of IEEE\/CVF CVPR, pp. 8771\u20138780, 2022."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3659592"},{"issue":"1","key":"e_1_2_1_37_1","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1037\/0096-3445.111.1.135","article-title":"Human reaction time: Toward a general theory","volume":"111","author":"Grice G. R.","year":"1982","unstructured":"G. R. Grice, R. Nullmeyer, and V. A. Spiker, \u201cHuman reaction time: Toward a general theory,\u201d Journal of Experimental Psychology: General, vol. 111, no. 1, pp. 135\u2013153, 1982.","journal-title":"Journal of Experimental Psychology: General"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2016.01.002"},{"issue":"1","key":"e_1_2_1_39_1","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s11831-022-09815-7","article-title":"A review on kalman filter models","volume":"30","author":"Khodarahmi M.","year":"2023","unstructured":"M. Khodarahmi and V. Maihami, \u201cA review on kalman filter models,\u201d Archives of Computational Methods in Engineering, vol. 30, no. 1, pp. 727\u2013747, 2023.","journal-title":"Archives of Computational Methods in Engineering"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2003281"},{"key":"e_1_2_1_41_1","volume-title":"Zenodo","author":"Jocher G.","year":"2022","unstructured":"G. Jocher, A. Chaurasia, A. Stoken, J. Borovec, Y. Kwon, K. Michael, J. Fang, C. Wong, Z. Yifu, D. Montes, et al., \u201cultralytics\/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations,\u201d Zenodo, 2022."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2020.101887"},{"key":"e_1_2_1_43_1","volume-title":"Openpcdet: An open-source toolbox for 3d object detection from point clouds","author":"Team O. D.","year":"2020","unstructured":"O. D. Team, \u201cOpenpcdet: An open-source toolbox for 3d object detection from point clouds.\u201d https:\/\/github.com\/open-mmlab\/OpenPCDet, 2020."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T19:42:37Z","timestamp":1764704557000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,2]]}},"alternative-id":["10.1145\/3770707"],"URL":"https:\/\/doi.org\/10.1145\/3770707","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"2025-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}