{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:08:53Z","timestamp":1787029733689,"version":"build-2736575974"},"reference-count":45,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung Electronics","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Event-based sensors provide sparse, motion-centric measurements that can reduce data bandwidth and enable always-on perception on resource-constrained edge devices. This paper presents an event-based machine vision framework for smart-home AIoT that couples a Dynamic Vision Sensor (DVS) with compute-efficient algorithms for (i) human\/object detection, (ii) 2D human pose estimation, (iii) hand posture recognition for human\u2013machine interfaces. The main methodological contributions are timestamp-based, polarity-agnostic recency encoding that preserves moving-edge structure while suppressing static background, and task-specific network optimizations (architectural reduction and mixed-bit quantization) tailored to sparse event images. With a fixed downstream network, the recency encoding improves action recognition accuracy over temporal accumulation (0.908 vs. 0.896). In a 24 h indoor monitoring experiment (640 \u00d7 480), the raw DVS stream is about 30\u00d7 smaller than conventional CMOS video and remains about 5\u00d7 smaller after standard compression. For human detection, the optimized event processing reduces computation from 5.8 G to 81 M FLOPs and runtime from 172 ms to 15 ms (more than 11\u00d7 speed-up). For pose estimation, a pruned HRNet reduces model size from 127 MB to 19 MB and inference time from 70 ms to 6 ms on an NVIDIA Titan X while maintaining a comparable accuracy (mAP from 0.95 to 0.94) on MS COCO 2017 using synthetic event streams generated by an event simulator. For hand posture recognition, a compact CNN achieves 99.19% recall and 0.0926% FAR with 14.31 ms latency on a single i5-4590 CPU core using 10-frame sequence voting. These results indicate that event-based sensing combined with lightweight inference is a practical approach to privacy-friendly, real-time perception under strict edge constraints.<\/jats:p>","DOI":"10.3390\/s26030935","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:46:11Z","timestamp":1770122771000},"page":"935","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Event-Based Machine Vision for Edge AI Computing"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1366-9822","authenticated-orcid":false,"given":"Paul K. J.","family":"Park","sequence":"first","affiliation":[{"name":"Samsung Electronics, Hwaseong 18448, Republic of Korea"},{"name":"Department of Semiconductor Display, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junseok","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Hwaseong 18448, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhyun","family":"Ko","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Hwaseong 18448, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeoungjin","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Semiconductor Display, Gachon University, Seongnam 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1038\/s41467-025-67103-x","article-title":"In-sensor image memorization, low-level processing, and high-level computing by using above-bandgap photovoltages","volume":"17","author":"Liu","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: A survey","volume":"44","author":"Gallego","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cimarelli, C., Millan-Romera, J.A., Voos, H., and Sanchez-Lopez, J.L. (2025). Hardware, algorithms, and applications of the neuromorphic vision sensor: A review. Sensors, 25.","DOI":"10.36227\/techrxiv.174494936.63871491\/v1"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Cazzato, D., and Bono, F. (2024). An application-driven survey on event-based neuromorphic computer vision. Information, 15.","DOI":"10.3390\/info15080472"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chakravarthi, B., Verma, A.A., Daniilidis, K., Ferm\u00fcller, C., and Yang, Y. (2024). Recent event camera innovations: A survey. arXiv.","DOI":"10.1007\/978-3-031-92460-6_21"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Park, P.K.J., Kim, J., and Ko, J. (2025). Motion blur-free high-speed hybrid image sensing. Sensors, 25.","DOI":"10.3390\/s25247496"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Suh, Y., Choi, S., Ito, M., Kim, J., Lee, Y., Seo, J., Jung, H., Yeo, D., Namgung, S., and Bong, J. (2020, January 10\u201321). A 1280 \u00d7 960 dynamic vision sensor with a 4.95-\u03bcm pixel pitch and motion artifact minimization. Proceedings of the IEEE International Sympo-Sium on Circuits and Systems, Seville, Spain.","DOI":"10.1109\/ISCAS45731.2020.9180436"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Son, B., Suh, Y., Kim, S., Jung, H., Kim, J., Shin, C., Park, P., Lee, K., Park, J., and Woo, J. (2017, January 5\u20139). A 640 \u00d7 480 dynamic vision sensor with a 9um pixel and 300Meps address-event representation. Proceedings of the International Solid-State Circuits Conference, San Francisco, CA, USA.","DOI":"10.1109\/ISSCC.2017.7870263"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Jogin, M., Madhulika, M.S., Divya, G.D., Meghana, R.K., and Apoorva, S. (2018, January 18\u201319). Feature extraction using convolution neural networks and deep learning. Proceedings of the IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology, Bangalore, India.","DOI":"10.1109\/RTEICT42901.2018.9012507"},{"key":"ref_10","unstructured":"(2026, January 14). Information Technology\u2014Coding of Audio-Visual Objects\u2014Part 10: Advanced Video Coding. Available online: https:\/\/www.iso.org\/obp\/ui\/#iso:std:iso-iec:14496:-10:ed-9:v1:en."},{"key":"ref_11","unstructured":"(2026, January 14). Progressive Bi-Level Image Compression. Available online: https:\/\/www.itu.int\/rec\/T-REC-T.82-199303-I\/en."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Park, P., Lee, K., Lee, J., Kang, B., Shin, C., Woo, J., Kim, J., Suh, Y., Kim, S., and Moradi, S. (2015, January 27\u201330). Computationally efficient, real-time motion recognition based on bio-inspired visual and cognitive processing. Proceedings of the IEEE International Conference on Image Processing, Quebec City, QC, Canada.","DOI":"10.1109\/ICIP.2015.7350936"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Mueggler, E., Bartolozzi, C., and Scaramuzza, D. (2017, January 4\u20137). Fast event-based corner detection. Proceedings of the British Machine Vision Conference, London, UK.","DOI":"10.5244\/C.31.33"},{"key":"ref_14","unstructured":"Gehrig, D., Loquercio, A., Derpanis, K., and Scaramuzza, D. (November, January 27). End-to-end learning of representations for asynchronous event-based data. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1109\/TPAMI.2016.2574707","article-title":"HOTS: A hierarchy of event-based time-surfaces for pattern recognition","volume":"39","author":"Lagorce","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sironi, A., Brambilla, M., Bourdis, N., Lagorce, X., and Benosman, R. (2018, January 18\u201323). HATS: Histograms of averaged time surfaces for robust event-based object classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00186"},{"key":"ref_17","unstructured":"Radomski, A., Georgiou, A., Debrunner, T., Li, C., Longinotti, L., Seo, M., Kwak, M., Shin, C., Park, P., and Ryu, H. (2021). Enhanced frame and event-based simulator and event-based video interpolation network. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","article-title":"NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding","volume":"42","author":"Liu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Cho, S., Woo, S., Jang, S., and Lee, S. (2023, January 1\u20136). Leveraging spatio-temporal dependency for skeleton-based action recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00941"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Yan, X., Cheng, Z.-Q., Yan, Y., Dai, Q., and Hua, X.-S. (2024, January 16\u201322). BlockGCN: Redefine topology awareness for skeleton-based action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00200"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Reilly, D., and Das, S. (2024, January 17\u201321). Just add \u03c0! pose induced video transformers for understanding activities of daily living. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01736"},{"key":"ref_22","unstructured":"Yang, Y. (2024). Skeleton-based action recognition with non-linear dependency modeling and hilbert-schmidt independence criterion. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"123061","DOI":"10.1016\/j.eswa.2023.123061","article-title":"A dense-sparse complementary network for human action recognition based on RGB and skeleton modalities","volume":"244","author":"Cheng","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"129781","DOI":"10.1016\/j.neucom.2025.129781","article-title":"EPAM-Net: An efficient pose-driven attention-guided multimodal network for video action recognition","volume":"633","author":"Abdelkawy","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"45297","DOI":"10.2196\/45297","article-title":"Acceptance and privacy perceptions toward video-based active and assisted living technologies: Scoping review","volume":"25","author":"Mujirishvili","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ahmad, S., Scarpellini, G., Morerio, P., and Del Bue, A. (2022, January 4\u20138). Event-driven re-Id: A new benchmark and method towards privacy-preserving person re-identification. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops, Waikoloa, HI, USA.","DOI":"10.1109\/WACVW54805.2022.00052"},{"key":"ref_27","unstructured":"Park, P.K.J., Kim, J.-S., Shin, C.-W., Lee, H., Liu, W., Wang, Q., Roh, Y., Kim, J., Ater, Y., and Soloveichik, E. (2019, January 7\u201311). Low-latency interactive sensing for machine vision. Proceedings of the IEEE International Electron Devices Meeting, San Francisco, CA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized neural networks: Training neural networks with weights and activations constrained to +1 or \u22121. arXiv."},{"key":"ref_30","unstructured":"Vanhoucke, V., Senior, A., and Mao, M.Z. (2011, January 12\u201317). Improving the speed of neural networks on CPUs. Proceedings of the Annual Conference on Neural Information Processing Systems, Granada, Spain."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Peng, Y., Li, H., Zhang, Y., Sun, X., and Wu, F. (2024, January 17\u201321). Scene adaptive sparse transformer for event-based object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01589"},{"key":"ref_32","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO series in 2021. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Azizi, S., Rabiee, R., Nair, G., and Olofsson, T. (2021). Effects of positioning of multi-sensor devices on occupancy and indoor environmental monitoring in single-occupant offices. Energies, 14.","DOI":"10.3390\/en14196296"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"115161","DOI":"10.1016\/j.enbuild.2024.115161","article-title":"Long-term field testing of the accuracy and HVAC energy savings potential of occupancy presence sensors in a single-family home","volume":"328","author":"Pang","year":"2025","journal-title":"Energy Build."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Calabrese, E., Taverni, G., Easthope, C.A., Skriabine, S., Corradi, F., Longinotti, L., Eng, K., and Delbruck, T. (2019, January 16\u201317). DHP19: Dynamic vision sensor 3D human pose dataset. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00217"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J. (2019, January 16\u201320). Deep high-resolution representation learning for human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhou, G., He, W., Zhu, H., and Cui, Y. (2025). DE-HRNet: Detail enhanced high-resolution network for human pose estimation. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0325540"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhou, H., Luo, M., Jiang, F., Ding, Y., Lu, H., and Jia, K. (2024). Boosting semi-supervised 2D human pose estimation by revisiting data augmentation and consistency training. arXiv.","DOI":"10.2139\/ssrn.5180670"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Lee, K., Ryu, H., Park, P.K.J., Shin, C.-W., Woo, J., and Kim, J.-S. (2014, January 27\u201330). Real-time motion estimation based on event-based vision sensor. Proceedings of the IEEE International Conference on Image Processing, Paris, France.","DOI":"10.1109\/ICIP.2014.7025040"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.1109\/TNNLS.2014.2308551","article-title":"Real-time gesture interface based on event-driven processing from stereo silicon retinas","volume":"25","author":"Lee","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Bissarinova, U., Rakhimzhanova, T., Kenzhebalin, D., and Varol, H.A. (2024). Faces in event streams: An annotated face dataset for event cameras. Sensors, 24.","DOI":"10.36227\/techrxiv.22826654.v3"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Feng, B., Zhu, R., Zhu, Y., Jin, Y., and Ju, J. (2025). Dynamic vision sensor-driven spiking neural networks for low-power event-based tracking and recognition. Sensors, 25.","DOI":"10.3390\/s25196048"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"9130","DOI":"10.1109\/TPAMI.2025.3586559","article-title":"Event-based stereo depth estimation: A survey","volume":"47","author":"Ghosh","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"51275","DOI":"10.1109\/ACCESS.2024.3386032","article-title":"Event cameras in automotive sensing: A review","volume":"12","author":"Shariff","year":"2024","journal-title":"IEEE Access"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Li, J., Shi, F., Liu, W., Zou, D., Wang, Q., Park, P.K.J., and Ryu, H.E. (2017, January 4\u20137). Adaptive temporal pooling for object detection using dynamic vision sensor. Proceedings of the British Machine Vision Conference, London, UK.","DOI":"10.5244\/C.31.40"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/935\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:12:18Z","timestamp":1770181938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/935"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26030935"],"URL":"https:\/\/doi.org\/10.3390\/s26030935","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]}}}