{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:52:50Z","timestamp":1785909170617,"version":"3.56.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Accurate and energy-efficient perception of road-surface markings is essential for Advanced Driver Assistance Systems (ADAS) and autonomous driving, particularly under real-time embedded constraints. This study proposes EdgeLane-SEG, a unified framework designed to achieve high instance segmentation accuracy while maintaining low computational cost and power consumption on resource-constrained edge platforms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed framework integrates two single-stage models, YOLO11-SEG and YOLO26-SEG, for joint object detection and instance segmentation. A dedicated dataset of 10,542 annotated images with 23,420 labeled instances was constructed, covering lane markings, directional arrows, and pedestrian crossings. Both models were trained under identical conditions using a unified multi-task loss combining IoU-based regression, objectness, classification, and hybrid Binary Cross-Entropy and Dice segmentation losses. Performance was evaluated using precision, recall, F1-score, mAP@0.5, mAP@0.5\u20130.95, FPS, and FPS\/W. Deployment was conducted on NVIDIA Jetson Nano, Raspberry Pi 5, Raspberry Pi 5 with Intel Movidius VPU, and Raspberry Pi 5 with Hailo-8 NPU.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Both models achieved high detection and segmentation performance, with mAP@0.5 exceeding 98%. YOLO26-SEG demonstrated superior inference speed and energy efficiency across all platforms, achieving higher FPS and FPS\/W than YOLO11-SEG. The Hailo-8 NPU configuration achieved the best embedded performance, reaching 50\u201352.6 FPS and 18.85 FPS\/W for YOLO26-SEG.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>EdgeLane-SEG effectively balances accuracy, efficiency, and deployment feasibility. YOLO26-SEG with Hailo-8 NPU acceleration is particularly suitable for real-time embedded ADAS applications, enabling energy-efficient and reliable road perception in resource-constrained environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1872217","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:41:44Z","timestamp":1785908504000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EdgeLane-SEG: an energy-efficient embedded edge AI framework for real-time road marking and lane lines detection with instance segmentation in ADAS and autonomous driving"],"prefix":"10.3389","volume":"9","author":[{"given":"Mohammed","family":"Chaman","sequence":"first","affiliation":[{"name":"Laboratory of Electronic Systems Information Processing Mechanics and Energetics, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anas","family":"El Maliki","sequence":"additional","affiliation":[{"name":"Laboratory of Scientific Research and Innovation, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wiame","family":"Bouyoussef","sequence":"additional","affiliation":[{"name":"Laboratory of Scientific Research and Innovation, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelmounaim","family":"Belaaribi","sequence":"additional","affiliation":[{"name":"Laboratory of Scientific Research and Innovation, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Younes","family":"Laababid","sequence":"additional","affiliation":[{"name":"Laboratory of Computer Science and Interdisciplinary Physics Normal Superior School Fez, Sidi Mohamed Ben Abdellah University","place":["Fes, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zouhair","family":"Sadoune","sequence":"additional","affiliation":[{"name":"Laboratory of Electronic Systems Information Processing Mechanics and Energetics, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelkader","family":"Mezouari","sequence":"additional","affiliation":[{"name":"Laboratory of Scientific Research and Innovation, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamad","family":"Dahou","sequence":"additional","affiliation":[{"name":"Laboratory of Scientific Research and Innovation, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelkader","family":"Hadjoudja","sequence":"additional","affiliation":[{"name":"Laboratory of Electronic Systems Information Processing Mechanics and Energetics, Ibn Tofail University","place":["Kenitra, Morocco"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"ref2","doi-asserted-by":"publisher","first-page":"61094","DOI":"10.14569\/IJACSA.2025.0161094","article-title":"RT-DETR edge deployment: real-time detection transformer for distracted driving detection","volume":"16","author":"Aljahani","year":"2025","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"70105","DOI":"10.14569\/IJACSA.2026.0170105","article-title":"DriveRight: an embedded AI-based multi-hazard detection and alert system for safe and sustainable driving","volume":"17","author":"Alsayaydeh","year":"2026","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"109952","DOI":"10.1016\/j.bspc.2026.109952","article-title":"YOLO-TeethSeg: a resource-efficient approach to multi-class teeth instance segmentation using lightweight YOLO-based models","volume":"120","author":"Barua","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3390\/s23041963","article-title":"Autonomous vehicles enabled by the integration of IoT, edge intelligence, 5G, and Blockchain","volume":"23","author":"Biswas","year":"2023","journal-title":"Sensors"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"69720","DOI":"10.1109\/ACCESS.2023.3287491","article-title":"CARINA project: visual perception systems applied for autonomous vehicles and advanced driver assistance systems (ADAS)","volume":"11","author":"Bruno","year":"2023","journal-title":"IEEE Access"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"930","DOI":"10.3390\/electronics14050930","article-title":"Real-time edge computing vs. GPU-accelerated pipelines for low-cost microscopy applications","volume":"14","author":"Bueno","year":"2025","journal-title":"Electronics"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"106388","DOI":"10.1016\/j.rineng.2025.106388","article-title":"Deep learning-based detection of wine bottle capsules for contamination prevention","volume":"27","author":"Caballero-Ram\u00edrez","year":"2025","journal-title":"Results Eng."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"108942","DOI":"10.1016\/j.rineng.2025.108942","article-title":"Benchmarking YOLO-based deep learning models for real-time object detection in hybrid ADAS and intelligent transportation systems","volume":"29","author":"Chaman","year":"","journal-title":"Results Eng."},{"key":"ref10","author":"Chaman","year":""},{"key":"ref11","doi-asserted-by":"publisher","first-page":"28077","DOI":"10.48084\/etasr.12138","article-title":"A real-time vehicle detection system for ADAS in autonomous vehicles using YOLOv11 deep neural network on embedded edge platforms","volume":"15","author":"Chaman","year":"","journal-title":"Eng. Technol. Appl. Sci. Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"396","DOI":"10.11591\/eei.v15i1.11128","article-title":"Deep learning\u2013based real time speed limit sign detection with YOLOv12 on edge AI platforms for embedded ADAS","volume":"15","author":"Chaman","year":"","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.3390\/rs16152751","article-title":"InstLane dataset and geometry-aware network for instance segmentation of lane line detection","volume":"16","author":"Cheng","year":"2024","journal-title":"Remote Sens."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"789","DOI":"10.3390\/s23020789","article-title":"Research on lane line detection algorithm based on instance segmentation","volume":"23","author":"Cheng","year":"2023","journal-title":"Sensors"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1177\/17248035251390608","article-title":"Multi-scale attention and transformer-enhanced YOLO architecture for robust traffic sign detection in complex visual environments","volume":"20","author":"Farhani","year":"2026","journal-title":"Intell. Artif."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3390\/engproc2025107049","article-title":"Improved YOLOv5 lane line real time segmentation system integrating seg head network","volume":"107","author":"Feilong","year":"2025","journal-title":"Eng. Proc."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s11554-025-01668-0","article-title":"PSC-YOLO: a lightweight model for urban road instance segmentation","volume":"22","author":"Gu","year":"2025","journal-title":"J. Real-Time Image Proc."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/s11042-026-21291-w","article-title":"Real-time lane detection for autonomous driving & GRAD-CAM visualization","volume":"85","author":"Gupta","year":"2026","journal-title":"Multim. Tools Appl."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/drones8110680","article-title":"Edge computing-driven real-time drone detection using YOLOv9 and NVIDIA Jetson Nano","volume":"8","author":"Hakani","year":"2024","journal-title":"Drones"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"114164","DOI":"10.1016\/j.engappai.2026.114164","article-title":"Signal temporal logic-based neural network for driving task generation in advanced driver assistance systems","volume":"170","author":"Hashimoto","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref24","author":"He","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"14582","DOI":"10.48550\/arXiv.2602.14582","article-title":"YOLO26: a comprehensive architecture overview and key improvements","volume":"2026","author":"Hidayatullah","year":"2026","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.3390\/electronics12051079","article-title":"Lane line detection and object scene segmentation using Otsu thresholding and the fast Hough transform for intelligent vehicles in complex road conditions","volume":"12","author":"Javeed","year":"2023","journal-title":"Electronics"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"17725","DOI":"10.48550\/arXiv.2410.17725","article-title":"YOLOv11: an overview of the key architectural enhancements","volume":"2024","author":"Khanam","year":"2024","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.3390\/electronics14173389","article-title":"Dual-path enhanced YOLO11 for lightweight instance segmentation with attention and efficient convolution","volume":"14","author":"Liao","year":"2025","journal-title":"Electronics"},{"key":"ref31","author":"Martins","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/OJVT.2025.3635022","article-title":"The road ahead: a comprehensive review of recent advances in traffic sign and lane line recognition for autonomous systems","volume":"7","author":"Medina","year":"2026","journal-title":"IEEE Open J. Veh. Technol."},{"key":"ref33","author":"Mohamed","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"020101","DOI":"10.1063\/5.0298677","article-title":"Design and implementation of an embedded system for traffic sign detection and recognition system","volume":"3345","author":"Nandy","year":"2026","journal-title":"AIP Conf. Proc."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"7083","DOI":"10.3390\/s25227083","article-title":"Integration of multi-sensor fusion and decision-making architecture for autonomous vehicles in multi-object traffic conditions","volume":"25","author":"Nguyen","year":"2025","journal-title":"Sensors"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/jimaging12010020","article-title":"Object detection on road: vehicle\u2019s detection based on re-training models on NVIDIA-Jetson platform","volume":"12","author":"Ramos-Sanchez","year":"2026","journal-title":"J. Imaging"},{"key":"ref39","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"8664","DOI":"10.3389\/frai.2025.1508664","article-title":"Edge computing for detection of ship and ship port from remote sensing images using YOLO","volume":"8","author":"Sanikommu","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3164","DOI":"10.3390\/app15063164","article-title":"Comparative performance of YOLOv8, YOLOv9, YOLOv10, and YOLOv11 for layout analysis of historical documents images","volume":"15","author":"Santos J\u00fanior","year":"2025","journal-title":"Appl. Sci."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"00168","DOI":"10.48550\/arXiv.2602.00168","article-title":"YOLOE-26: integrating YOLO26 with YOLOE for real-time open-vocabulary instance segmentation","volume":"2026","author":"Sapkota","year":"2026","journal-title":"arXiv"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"100615","DOI":"10.1016\/j.array.2025.100615","article-title":"A systematic literature review on deep learning approaches for small object detection","volume":"29","author":"Sayyad","year":"2026","journal-title":"Array"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"103870","DOI":"10.1016\/j.asej.2025.103870","article-title":"InSegNet: semantic segmentation-based lane detection network for clear and occluded roads","volume":"17","author":"Shaikh","year":"2026","journal-title":"Ain Shams Eng. J."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"188","DOI":"10.14569\/IJACSA.2026.0170188","article-title":"Lightweight dual-YOLOv8 instance-aware semantic segmentation for real-time autonomous driving on edge ARM\/GPU platforms","volume":"17","author":"Teboulbi","year":"2026","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"12524","DOI":"10.48550\/arXiv.2502.12524","article-title":"YOLOv12: attention-centric real-time object detectors","volume":"2025","author":"Tian","year":"2025","journal-title":"arXiv"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"351","DOI":"10.3390\/electronics15020351","article-title":"Real-time deterministic lane detection on CPU-only embedded systems via binary line segment filtering","volume":"15","author":"Tsai","year":"2026","journal-title":"Electronics"},{"key":"ref49","year":""},{"key":"ref50","year":""},{"key":"ref51","author":"Wang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"75154","DOI":"10.3389\/frai.2025.1675154","article-title":"Optimizing surface defect detection with YOLOv9: the role of advanced backbone models","volume":"8","author":"Zeng","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"6543","DOI":"10.3390\/s23146543","article-title":"Road traffic sign detection method based on RTS R-CNN instance segmentation network","volume":"23","author":"Zhang","year":"2023","journal-title":"Sensors"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"108815","DOI":"10.1016\/j.rineng.2025.108815","article-title":"Enhanced YOLO-security deep learning model for ship detection in maritime security","volume":"29","author":"Zhenbo","year":"2026","journal-title":"Results Eng."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1872217\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:41:46Z","timestamp":1785908506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1872217\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":45,"alternative-id":["10.3389\/frai.2026.1872217"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1872217","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1872217"}}