{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:34:55Z","timestamp":1785429295866,"version":"3.56.0"},"reference-count":48,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["682661"],"award-info":[{"award-number":["682661"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]},{"award":["682661"],"award-info":[{"award-number":["682661"]}],"id":[{"id":"https:\/\/ror.org\/01h531d29","id-type":"ROR","asserted-by":"publisher"}]},{"name":"IAMGOLD President\u2019s Innovation","award":["6062621"],"award-info":[{"award-number":["6062621"]}]},{"DOI":"10.13039\/501100015669","name":"Laurentian University","doi-asserted-by":"crossref","award":["1092634"],"award-info":[{"award-number":["1092634"]}],"id":[{"id":"10.13039\/501100015669","id-type":"DOI","asserted-by":"crossref"}]},{"award":["1092634"],"award-info":[{"award-number":["1092634"]}],"id":[{"id":"https:\/\/ror.org\/03rcwtr18","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Deploying modern deep learning-based vision systems on humanoid robots remains challenging due to limited onboard computational resources and legacy software constraints. This paper presents a modular vision system for practical object detection on resource-constrained humanoid platforms, based on the YOLOv9 framework. The proposed architecture adopts a dual-environment design, decoupling the perception pipeline from the robot control system to enable compatibility between modern deep learning libraries and a ROS-based platform. To support efficient deployment, task-specific lightweight models are trained and integrated into a modular pipeline optimized for CPU-only inference. The system is evaluated across multiple task scenarios derived from the FIRA RoboWorld Cup (Hurocup) competition, including Marathon, Basketball, and Archery. Performance is assessed in terms of detection accuracy and computational efficiency, demonstrating that reliable perception can be achieved at 4\u20138 FPS under constrained hardware conditions. The results show that the proposed approach improves robustness compared to traditional geometric vision methods, particularly in dynamic and visually complex environments, while maintaining practical responsive task-level perception for robotic decision-making. The work highlights the trade-offs between accuracy, computational cost, and system responsiveness and demonstrates the feasibility of deploying modern object detection models on embedded humanoid platforms.<\/jats:p>","DOI":"10.3390\/biomimetics11060363","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T16:06:08Z","timestamp":1779465968000},"page":"363","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Modular Vision System for Practical Object Detection on Resource-Constrained Humanoid Robots"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3517-4900","authenticated-orcid":false,"given":"Meng Cheng","family":"Lau","sequence":"first","affiliation":[{"name":"School of Engineering and Computer Science, Laurentian University, Greater Sudbury, ON P3E 2C6, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Pottier","sequence":"additional","affiliation":[{"name":"School of Engineering and Computer Science, Laurentian University, Greater Sudbury, ON P3E 2C6, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","article-title":"A Survey on 3D Object Detection Methods for Autonomous Driving Applications","volume":"20","author":"Arnold","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5471","DOI":"10.1007\/s00521-019-04645-4","article-title":"Real-time behavior detection and judgment of egg breeders based on YOLO v3","volume":"32","author":"Wang","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Salazar-Gomez, A., Darbyshire, M., Gao, J., Sklar, E.I., and Parsons, S. (2021). Towards practical object detection for weed spraying in precision agriculture. arXiv.","DOI":"10.1109\/IROS47612.2022.9982139"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"108201","DOI":"10.1016\/j.compeleceng.2022.108201","article-title":"Agricultural monitoring system in video surveillance object detection using feature extraction and classification by deep learning techniques","volume":"102","author":"Khan","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"23273","DOI":"10.1007\/s11042-018-5671-8","article-title":"A study on various methods used for video summarization and moving object detection for video surveillance applications","volume":"77","author":"Murugan","year":"2018","journal-title":"Multimed. Tools Appl."},{"key":"ref_7","first-page":"1033","article-title":"A Review on Object Detection and Tracking in Video Surveillance","volume":"11","author":"Angadi","year":"2020","journal-title":"Int. J. Adv. Res. Eng. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-024-10979-w","article-title":"Deep learning for surgical instrument recognition and segmentation in robotic-assisted surgeries: A systematic review","volume":"58","author":"Ahmed","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"103945","DOI":"10.1016\/j.robot.2021.103945","article-title":"Visual detection and tracking algorithms for minimally invasive surgical instruments: A comprehensive review of the state-of-the-art","volume":"149","author":"Wang","year":"2022","journal-title":"Robot. Auton. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Suard, F., Rakotomamonjy, A., Bensrhair, A., and Broggi, A. (2006). Pedestrian Detection using Infrared Images and Histograms of Oriented Gradients. Proceedings of the Intelligent Vehicles Symposium, Tokyo, Japan, 13\u201315 June 2006, IEEE.","DOI":"10.1109\/IVS.2006.1689629"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1016\/j.patrec.2011.01.004","article-title":"Face recognition using Histograms of Oriented Gradients","volume":"32","author":"Bueno","year":"2011","journal-title":"Pattern Recognit. Lett."},{"key":"ref_12","first-page":"44","article-title":"Palm pattern recognition using scale invariant feature transform","volume":"1","author":"Kasiselvanathan","year":"2020","journal-title":"Int. J. Intell. Sustain. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9248","DOI":"10.3390\/s130709248","article-title":"Retinal Identification Based on an Improved Circular Gabor Filter and Scale Invariant Feature Transform","volume":"13","author":"Meng","year":"2013","journal-title":"Sensors"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1016\/j.patrec.2012.08.002","article-title":"Visual tracking and learning using speeded up robust features","volume":"33","author":"Li","year":"2012","journal-title":"Pattern Recognit. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"24035","DOI":"10.1007\/s11042-019-7209-0","article-title":"Multimedia based fast face recognition algorithm of speed up robust features","volume":"78","author":"He","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhao, M., Shi, P., Ren, R., He, X., Wei, X., and Yang, H. (2022). Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN. Sensors, 22.","DOI":"10.3390\/s22031215"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.procs.2017.03.069","article-title":"Facial Expression Recognition with Faster R-CNN","volume":"107","author":"Li","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"ref_19","unstructured":"Kanda, T., Ishiguro, H., Ono, T., Imai, M., and Nakatsu, R. (2002, January 11\u201315). Development and evaluation of an interactive humanoid robot \u201cRobovie\u201d. Proceedings of the Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292), Online."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Oztop, E., Chaminade, T., and Franklin, D. (2004, January 10\u201312). Human-humanoid interaction: Is a humanoid robot perceived as a human?. Proceedings of the 4th IEEE\/RAS International Conference on Humanoid Robots, Santa Monica, CA, USA.","DOI":"10.1109\/ICHR.2004.1442688"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1016\/j.scib.2023.04.019","article-title":"Integrated intelligent tactile system for a humanoid robot","volume":"68","author":"Bao","year":"2023","journal-title":"Sci. Bull."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hester, T., Quinlan, M., and Stone, P. (2010, January 3\u20137). Generalized model learning for Reinforcement Learning on a humanoid robot. Proceedings of the 2010 IEEE International Conference on Robotics and Automation, Anchorage, Alaska.","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref_23","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1007\/s44163-025-00398-3","article-title":"MOLO: A Hybrid Approach Using MobileNet and YOLO for Object Detection on Resource-Constrained Devices","volume":"5","author":"Khurana","year":"2025","journal-title":"Discov. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 14\u201319). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_26","unstructured":"NVIDIA Corporation (2025, June 08). NVIDIA TensorRT: High-Performance Deep Learning Inference Optimizer and Runtime. Available online: https:\/\/developer.nvidia.com\/tensorrt."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huang, X., Wang, H., Qin, S., and Tang, S.K. (2025). Embedded Artificial Intelligence: A Comprehensive Literature Review. Electronics, 14.","DOI":"10.20944\/preprints202507.1972.v1"},{"key":"ref_28","first-page":"411","article-title":"Experimental Analysis of Lightweight CNNs for Real-Time Object Detection on Low-Power Devices","volume":"1","author":"Singh","year":"2025","journal-title":"J. Sci. Innov. Adv. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"710","DOI":"10.52152\/801932","article-title":"Novel Approach for Object Detection in Embedded Systems Using YOLO","volume":"23","author":"Mishra","year":"2025","journal-title":"Lex Localis"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, C., Zheng, Z., Xu, T., Guo, S., Feng, S., Yao, W., and Lan, Y. (2023). YOLO-Based UAV Technology: A Review of the Research and Its Applications. Drones, 7.","DOI":"10.3390\/drones7030190"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hussain, M. (2023). YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection. Machines, 11.","DOI":"10.3390\/machines11070677"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. arXiv.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2016). YOLO9000: Better, Faster, Stronger. arXiv.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_34","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_35","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_36","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_38","first-page":"1969834","article-title":"A Novel Edge Detection Algorithm for Mobile Robot Path Planning","volume":"2018","author":"Roth","year":"2018","journal-title":"J. Robot."},{"key":"ref_39","unstructured":"Iosifidis, A., and Tefas, A. (2022). Chapter 12\u2014Semantic scene segmentation for robotics. Deep Learning for Robot Perception and Cognition, Academic Press."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e2632","DOI":"10.7717\/peerj-cs.2632","article-title":"Integrating humanoid robots with human musicians for synchronized musical performances","volume":"11","author":"Lau","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3834","DOI":"10.1007\/s10489-019-01565-7","article-title":"A Robust Interactive Entertainment Robot for Robot Magic Performances","volume":"49","author":"Morris","year":"2019","journal-title":"Appl. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pellegrino, R.V., Lacuesta, J.H.T., and Dela Cuesta, C.F.L. (2024, January 14\u201317). Nail Abnormality Identification Using Roboflow and Yolov8. Proceedings of the 2024 14th International Conference on Biomedical Engineering and Technology, New York, NY, USA.","DOI":"10.1145\/3678935.3678956"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gupta, H.S., Sameer, M., and Ahmad, G. (2023, January 7\u20138). Real-Time Vehicle Detection using YOLOv8 and Data Augmentation Approach. Proceedings of the 2023 IEEE Fifth International Conference on Advances in Electronics, Computers and Communications (ICAECC), Bengaluru, India.","DOI":"10.1109\/ICAECC59324.2023.10560330"},{"key":"ref_44","unstructured":"Ultralytics (2025, May 03). YOLOv9: A Leap Forward in Object Detection Technology, 2024. Available online: https:\/\/docs.ultralytics.com\/models\/yolov9."},{"key":"ref_45","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Pico, N., Mite, G., Mor\u00e1n, D., Alvarez-Alvarado, M.S., Auh, E., and Moon, H. (2025). Web-Based Real-Time Alarm and Teleoperation System for Autonomous Navigation Failures Using ROS 1 and ROS 2. Actuators, 14.","DOI":"10.3390\/act14040164"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Christensen, H.I., and Khatib, O. (2017). Rosbridge: ROS for Non-ROS Users. Robotics Research: The 15th International Symposium ISRR, Springer International Publishing.","DOI":"10.1007\/978-3-319-29363-9"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Song, B.Y., and Choi, H. (2024). ROS Gateway: Enhancing ROS Availability across Multiple Network Environments. Sensors, 24.","DOI":"10.3390\/s24196297"}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/6\/363\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:19:11Z","timestamp":1780460351000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/6\/363"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":48,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["biomimetics11060363"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics11060363","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}