{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:18:35Z","timestamp":1760059115393,"version":"build-2065373602"},"reference-count":28,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["8252019","20232ABC03A07","U24A20277"],"award-info":[{"award-number":["8252019","20232ABC03A07","U24A20277"]}]},{"name":"Jiangxi Provincial Nataural Science Foundataion","award":["8252019","20232ABC03A07","U24A20277"],"award-info":[{"award-number":["8252019","20232ABC03A07","U24A20277"]}]},{"name":"Natural Science Foundation of China","award":["8252019","20232ABC03A07","U24A20277"],"award-info":[{"award-number":["8252019","20232ABC03A07","U24A20277"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Effectively capturing multi-scale object features is crucial for vision sensors used in road object detection tasks. Traditional spatial pyramid pooling methods fuse multi-scale feature information but lack adaptability in dynamically adjusting convolution operations based on their actual needs. This limitation prevents them from fully utilizing spatial hierarchies and contextual information. To address this challenge, we propose a Transformation Dilated Grouped Layer (TDGL) module, a fast multi-scale vision sensor based on deep learning, designed to enhance both efficiency and accuracy in road target feature extraction networks. The TDGL is built upon the Global Layer Normalization Convolution (GLConv) unit, which mitigates internal covariate shift by introducing scaling and offset parameters, modifying dilation strategies, and employing grouped convolution. These improvements enable the network to distinguish features at different scales effectively while optimizing spatial information processing and reducing computational costs. To validate its effectiveness, we integrate the TDGL module into the backbone of several YOLO models, forming the TDGL Net feature extractor. The experimental results obtained on the BDD100K dataset show that the mAP of the TDGL net reaches 40.3% with around 3.1M parameters. The inference speed of the TDGL net after transformation optimization reaches 58 FPS, which meets the requirement for the real-time detection of road obstacle targets by autonomous vehicles.<\/jats:p>","DOI":"10.3390\/s25113339","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T05:52:52Z","timestamp":1748325172000},"page":"3339","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The TDGL Module: A Fast Multi-Scale Vision Sensor Based on a Transformation Dilated Grouped Layer"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3157-7325","authenticated-orcid":false,"given":"Leilei","family":"Xie","sequence":"first","affiliation":[{"name":"School of Rail Transportation, Shandong Jiaotong University, Jinan 250357, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2886-6968","authenticated-orcid":false,"given":"Fenghua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixue","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"15290","DOI":"10.1109\/TVT.2023.3292401","article-title":"Fast multi-lane detection based on cnn differentiation for adas\/ad","volume":"72","author":"Zhan","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"124808","DOI":"10.1109\/ACCESS.2023.3330858","article-title":"Multi-point rcnn for predicting deformation in deep excavation pit surrounding soil mass","volume":"11","author":"Song","year":"2023","journal-title":"IEEE Access"},{"key":"ref_3","unstructured":"Duth, S., Vedavathi, S., and Roshan, S. (2023, January 18\u201319). Herbal leaf classification using rcnn, fast rcnn, faster rcnn. Proceedings of the IEEE 2023 7th International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India."},{"key":"ref_4","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":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","unstructured":"Yu, F., Xian, W., Chen, Y., Liu, F., Liao, M., Madhavan, V., and Darrell, T. (2018). Bdd100k: A diverse driving video database with scalable annotation tooling. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft coco: Common objects in context. Proceedings of the Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland. Proceedings, Part V 13.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_8","first-page":"40","article-title":"Based on attention mechanism and characteristics of the polymerization of the lane line detection","volume":"39","author":"Ma","year":"2022","journal-title":"J. Microelectron. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Malaiarasan, S., Ravi, R., Maheswari, D., Rubavathi, C.Y., Ramnath, M., and Hemamalini, V. (2023, January 5\u20136). Towards enhanced deep cnn for early and precise skin cancer diagnosis. Proceedings of the IEEE 2023 International Conference on Networking and Communications (ICNWC), Chennai, India.","DOI":"10.1109\/ICNWC57852.2023.10127521"},{"key":"ref_10","first-page":"22","article-title":"Autopilot based on a semi-supervised learning situations of target detection","volume":"40","author":"Wen","year":"2023","journal-title":"J. Microelectron. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"32927","DOI":"10.1109\/ACCESS.2024.3365559","article-title":"Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8","volume":"12","author":"Niu","year":"2024","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, S., and Huang, D. (2018, January 8\u201314). Receptive field block net for accurate and fast object detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5082","DOI":"10.1109\/TNNLS.2020.3026784","article-title":"Revisiting internal covariate shift for batch normalization","volume":"32","author":"Awais","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5715","DOI":"10.1109\/TVT.2022.3232135","article-title":"Yolo-ore: A deep learning-aided object recognition approach for radar systems","volume":"72","author":"Huang","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_17","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2014). Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, Y., and Yu, Y. (2020, January 13\u201319). An internal covariate shift bounding algorithm for deep neural networks by unitizing layers\u2019 outputs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00849"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, X., and Wang, J. (2023, January 8\u201314). Energy saving based on transformer models with leakyrelu activation function. Proceedings of the IEEE 2023 13th International Conference on Information Science and Technology (ICIST), Cairo, Egypt.","DOI":"10.1109\/ICIST59754.2023.10367091"},{"key":"ref_20","first-page":"58","article-title":"Research on improved activation function trelu","volume":"40","author":"Zhang","year":"2019","journal-title":"mall Microcomput. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"33401","DOI":"10.1109\/ACCESS.2023.3263145","article-title":"Abstract layer for leakyrelu for neural network verification based on abstract interpretation","volume":"11","author":"Khedher","year":"2023","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Deng, G., Zhao, Y., Zhang, L., Li, Z., Liu, Y., Zhang, Y., and Li, B. (2020, January 15\u201318). Image classification and detection of cigarette combustion cone based on inception resnet v2. Proceedings of the IEEE 2020 5th International Conference on Computer and Communication Systems (ICCCS), Shanghai, China.","DOI":"10.1109\/ICCCS49078.2020.9118570"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., and Li, S.Z. (2020, January 13\u201319). Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref_24","unstructured":"Zhu, B., Wang, J., Jiang, Z., Zong, F., Liu, S., Li, Z., and Sun, J. (2020). Autoassign: Differentiable label assignment for dense object detection. arXiv."},{"key":"ref_25","unstructured":"Zhou, X., Wang, D., and Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Ye, R., Wang, P., Ren, D., Zuo, W., Hou, Q., and Cheng, M.M. (2022, January 18\u201324). Localization distillation for dense object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00919"},{"key":"ref_27","first-page":"545","article-title":"Video face detection based on improved ssd model and target tracking algorithm","volume":"21","author":"Liu","year":"2022","journal-title":"J. Web Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4730","DOI":"10.1109\/JSTARS.2022.3181594","article-title":"Double fcos: A two-stage model utilizing fcos for vehicle detection in various remote sensing scenes","volume":"15","author":"Gao","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/11\/3339\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:40:34Z","timestamp":1760031634000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/11\/3339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":28,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["s25113339"],"URL":"https:\/\/doi.org\/10.3390\/s25113339","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2025,5,26]]}}}