{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T07:01:49Z","timestamp":1780038109788,"version":"3.53.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"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. Neurorobot."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Landslide disasters cause severe casualties and economic losses, demanding rapid and accurate detection from high-resolution remote sensing imagery. Traditional methods struggle with insufficient landslide samples and low detection accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address this, we propose a dual solution: (1) DCGAN-based data augmentation generating 3,429 synthetic landslide samples from Google Earth imagery, significantly improving model generalization; (2) an NL-YOLOv5 model integrating non-local attention (NLA) and an improved LK-SPP module (based on large-kernel convolution concepts) to enhance global information capture.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The NL-YOLOv5 model achieves 80% detection accuracy (a 5% improvement over baseline), with 7% higher precision, 2% higher recall, and 5% higher F1-score, while maintaining real-time speed at 69 f\/s.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This work delivers a practical solution for high-precision landslide detection in remote sensing applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnbot.2026.1764856","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:03:36Z","timestamp":1780034616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NL-YOLOv5: a model with a larger receptive field and the ability to globally acquire features"],"prefix":"10.3389","volume":"20","author":[{"given":"Zhiyu","family":"Li","sequence":"first","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhu","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongfa","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"Guangdong Power Grid Company Zhuhai Electric Power Supply Bureau","place":["Zhuhai, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"4011","DOI":"10.3390\/rs13194011","article-title":"A new integrated approach for landslide data balancing and spatial prediction based on generative adversarial networks (GAN)","volume":"13","author":"Al-Najjar","year":"2021","journal-title":"Remote Sens."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/s41062-025-02378-z","article-title":"Deep neural network-based landslide hazard assessment and infrastructure exposure mapping: a case study of National Highway 279, Bac Kan province, Vietnam","volume":"10","author":"Bui","year":"2025","journal-title":"Innov. Infrastruct. Solut."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1848","DOI":"10.3390\/rs14081848","article-title":"DRs-UNet: a deep semantic segmentation network for the recognition of active landslides from InSAR imagery in the three rivers region of the Qinghai\u2013Tibet plateau","volume":"14","author":"Chen","year":"2022","journal-title":"Remote Sens."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"5517","DOI":"10.3390\/rs14215517","article-title":"Deep learning method of landslide inventory map with imbalanced samples in optical remote sensing","volume":"14","author":"Chen","year":"2022","journal-title":"Remote Sens."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.isprsjprs.2023.12.015","article-title":"TransLandslide: a transformer-based framework for large-scale landslide mapping from high-resolution satellite imagery","volume":"208","author":"Chen","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1007\/s10346-021-01694-6","article-title":"A small attentional YOLO model for landslide detection from satellite remote sensing images","volume":"18","author":"Cheng","year":"2021","journal-title":"Landslides"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"108451","DOI":"10.1016\/j.enggeo.2025.108451","article-title":"Protection barriers impacted by multiple surges of flow-like landslides: a material point method numerical study","volume":"359","author":"Cuomo","year":"2025","journal-title":"Eng. Geol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/s10064-025-04395-9","article-title":"Physics-driven scenario deduction of the Xinhua Village landslide disaster chain","volume":"84","author":"Du","year":"2025","journal-title":"Bull. Eng. Geol. Environ."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"012033","DOI":"10.1088\/1742-6596\/1544\/1\/012033","article-title":"Overview of two-stage object detection algorithms","volume":"1544","author":"Du","year":"2020","journal-title":"J. Phys."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"105320","DOI":"10.1016\/j.ijdrr.2025.105320","article-title":"Climate change has increased rainfall-induced landslide damages in Central China","volume":"119","author":"Fang","year":"2025","journal-title":"Int. J. Disaster Risk Reduct."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"109951","DOI":"10.1016\/j.soildyn.2025.109951","article-title":"Failure probability analysis of highway bridges under coupled seismic and landslide hazards based on copula modelling approach","volume":"201","author":"Feng","year":"2026","journal-title":"Soil Dyn. Earthq. Eng."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"196","DOI":"10.3390\/rs11020196","article-title":"Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection","volume":"11","author":"Ghorbanzadeh","year":"2019","journal-title":"Remote Sens."},{"key":"ref13","author":"Girshick","year":"2015"},{"key":"ref14","author":"He","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"35","DOI":"10.20944\/preprints202203.0337.v2","article-title":"Stacking ensemble of machine learning methods for landslide susceptibility mapping in Zhangjiajie City, Hunan Province, China","volume":"82","author":"Huan","year":"2023","journal-title":"Environ. Earth Sci."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.isprsjprs.2025.09.010","article-title":"AdaptVFMs-RSCD: advancing remote sensing change detection from binary to semantic with SAM and CLIP","volume":"230","author":"Jiang","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5490","DOI":"10.3390\/rs14215490","article-title":"Deep learning for landslide detection and segmentation in high-resolution optical images along the Sichuan-Tibet transportation corridor","volume":"14","author":"Jiang","year":"2022","journal-title":"Remote Sens."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"100815","DOI":"10.1016\/j.eij.2025.100815","article-title":"Fake news detection on social media using triple-attention mechanism optimized by advanced tailor optimization algorithm","volume":"32","author":"Jin","year":"2025","journal-title":"Egypt. Inform. J."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"489","DOI":"10.12785\/ijcds\/120139","article-title":"Improved YOLOv4 approach: a real time occluded vehicle detection","volume":"11","author":"Kumar","year":"2022","journal-title":"Int. J. Comput. Digit. Syst."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"100181","DOI":"10.1016\/j.iintel.2025.100181","article-title":"Methodologies for functional recovery assessment of hilly roads situated in the Indian Himalayan region","volume":"4","author":"Kumar","year":"2025","journal-title":"J. Infrastruct. Intell. Resist."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e2025GL117356","DOI":"10.1029\/2025GL117356","article-title":"Physics-informed deep learning for revealing the evolutionary characteristics of landslides induced by rainfall process","volume":"52","author":"Li","year":"2025","journal-title":"Geophys. Res. Lett."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s12145-022-00764-0","article-title":"Methods for landslide detection based on lightweight YOLOv4 convolutional neural network","volume":"15","author":"Li","year":"2022","journal-title":"Earth Sci. Inform."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"13","DOI":"10.15199\/48.2025.05.36","article-title":"Dangerous items\u2019 detection in surveillance camera images using faster R-CNN","volume":"5","author":"Omiotek","year":"2025","journal-title":"Przegl. Elektrotech."},{"key":"ref25","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"105355","DOI":"10.1016\/j.catena.2021.105355","article-title":"Landslide susceptibility analyses using random forest, C4. 5, and C5. 0 with balanced and unbalanced datasets","volume":"203","author":"Tanyu","year":"2021","journal-title":"Catena"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1177\/03091333241276523","article-title":"Automatic recognition of active landslides by surface deformation and deep learning","volume":"48","author":"Wang","year":"2024","journal-title":"Prog. Phys. Geogr. Earth Environ."},{"key":"ref28","author":"Wang","year":"2021"},{"key":"ref29","author":"Wang","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"113588","DOI":"10.1016\/j.chaos.2023.113588","article-title":"A novel adaptive weak fault diagnosis method based on modulation periodic stochastic pooling networks","volume":"173","author":"Wenyue","year":"2023","journal-title":"Chaos Solit. Fract."},{"key":"ref31","author":"Woo","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3321456","article-title":"Landslide detection in remote sensing images using a hybrid CNN-transformer architecture","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2383309","DOI":"10.1080\/19475705.2024.2383309","article-title":"Multi-scale convolutional neural networks (CNNs) for landslide inventory mapping from remote sensing imagery and landslide susceptibility mapping (LSM)","volume":"15","author":"Zhang","year":"2024","journal-title":"Geomat. Nat. Hazards Risk"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"847","DOI":"10.3390\/land14040847","article-title":"Spatial coupling and resilience differentiation characteristics of landscapes in populated karstic areas in response to landslide disaster risk: an empirical study from a typical Karst Province in China","volume":"14","author":"Zhou","year":"2025","journal-title":"Land"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s10346-025-02651-3","article-title":"Temporal validity of landslide inventories in hazard mapping: insights from Hubei Province, China","volume":"23","author":"Zhu","year":"2025","journal-title":"Landslides"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1764856\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:03:36Z","timestamp":1780034616000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1764856\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":35,"alternative-id":["10.3389\/fnbot.2026.1764856"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2026.1764856","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"article-number":"1764856"}}