{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T10:15:00Z","timestamp":1769249700479,"version":"3.49.0"},"reference-count":10,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Internet Technology Letters"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In the Internet of Vehicles (IoV), a critical subset of the Internet of Things (IoT), autonomous vehicles function as sophisticated mobile edge nodes that must process vast streams of sensor data in real\u2010time. Accurate pedestrian detection is a safety\u2010critical task for these nodes, yet delivering high recall for tiny and distant pedestrians on milliwatt\u2010class IoT hardware remains a significant challenge. We introduce a TinyML\u2010oriented detector that couples (i) a sparsity\u2010aware, pruned real\u2010time detection architecture, (ii) an ultra\u2010light channel\u2013spatial attention block, and (iii) a progressive pruning and mixed\u2010precision quantization pipeline co\u2010optimized for resource\u2010constrained IoT\u2010edge platforms. The final network is 86% smaller than its uncompressed baseline and runs at 12 FPS within a 5.3\u2009W power budget on a representative embedded IoT device. Across CityPersons, Caltech\u2010USA, and KITTI datasets, our model consistently outperforms recent lightweight detectors, achieving a 15 percentage\u2010point reduction in the log\u2010average miss rate for the challenging case of pedestrians under 50 pixels. The results demonstrate that our hardware\u2010aware, TinyML approach enables reliable, real\u2010time pedestrian perception on low\u2010power automotive IoT\u2010edge nodes.<\/jats:p>","DOI":"10.1002\/itl2.70182","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T13:23:57Z","timestamp":1763472237000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A\n                    <scp>TinyML<\/scp>\n                    \u2010Powered Pedestrian Detection Framework for\n                    <scp>IoT<\/scp>\n                    \u2010Edge Nodes in Autonomous Vehicles"],"prefix":"10.1002","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1072-729X","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"College of Automobile Engineering Jilin Engineering Vocational College  Jilin China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109864"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108385"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107149"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3365349"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339308"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3513331"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568160.3570225"},{"key":"e_1_2_8_9_1","first-page":"7507","volume-title":"EdgeYOLO: An Edge\u2010Real\u2010Time Object Detector","author":"Liu S.","year":"2023"},{"key":"e_1_2_8_10_1","first-page":"142","volume-title":"Benchmarking Deep Learning Models for Object Detection on Edge Computing Devices","author":"Alqahtani D. K.","year":"2024"},{"key":"e_1_2_8_11_1","first-page":"3825","volume-title":"Mobiledets: Searching for object detection architectures for mobile accelerators","author":"Xiong Y.","year":"2021"}],"container-title":["Internet Technology Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/itl2.70182","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/itl2.70182","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/itl2.70182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T03:37:42Z","timestamp":1769139462000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/itl2.70182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":10,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/itl2.70182"],"URL":"https:\/\/doi.org\/10.1002\/itl2.70182","archive":["Portico"],"relation":{},"ISSN":["2476-1508","2476-1508"],"issn-type":[{"value":"2476-1508","type":"print"},{"value":"2476-1508","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"2025-09-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70182"}}