{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T06:25:06Z","timestamp":1787034306657,"version":"build-2736575974"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"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. Plant Sci."],"abstract":"<jats:p>Unmanned aerial vehicles (UAVs) provide high-resolution and temporally continuous observations, offering substantial value for wide-area paddy-field inspection. Timely detection of macroscopic anomalies such as fire, intrusion, lodging, and disease is important for field management and risk assessment. However, supervised methods rely on predefined categories and large numbers of annotated abnormal samples, which are difficult to collect comprehensively in field environments. Meanwhile, UAV ego-motion, viewpoint changes, repetitive crop textures, and multi-scale appearance variations further increase the difficulty of anomaly detection, limiting the direct application of conventional image-based and fixed-camera video methods to moving UAV videos. To address these challenges, this paper proposes TFMAD, a normal-only futureframe prediction framework for frame-level macroscopic anomaly detection in UAV paddy-field videos. TFMAD adopts a U-shaped encoder\u2013decoder architecture, learns regular spatiotemporal patterns only from normal videos, and identifies anomalies according to the discrepancy between the predicted and observed frames. The framework contains three core modules: the Frequency Spatiotemporal Correlation Module (FSCM) models time\u2013frequency variation and spatial correlation; the Parallel Spatiotemporal Mamba (PSTM) module models temporal variation and local structures through bidirectional pixel-level and block-level scanning; and the DifferenceGuided Fusion (DGF) module regulates skip connections according to the discrepancy between appearance and spatiotemporal features, reducing the direct transfer of abnormal information to the decoder. To balance high-resolution feature extraction and computational efficiency, the encoder further adopts Token Statistics Self-Attention (TSSA) with linear complexity. In addition, this study constructs URVAD, a UAV paddy-field video dataset for frame-level anomaly detection, and conducts experiments on this dataset. The results show that TFMAD achieves 95.83% Micro-AUC and 96.80% Macro-AUC, obtaining the best overall performance among the compared methods under the current dataset and experimental setting.<\/jats:p>","DOI":"10.3389\/fpls.2026.1895982","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:36:14Z","timestamp":1787031374000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Macroscopic anomaly detection in paddy fields from UAV perspectives: a frequency-aware spatiotemporal mamba approach"],"prefix":"10.3389","volume":"17","author":[{"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhi","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinping","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing Aerospace Changfeng Science Technology Industry Group Co., Ltd","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7403","DOI":"10.1038\/s41598-022-11453-9","article-title":"Spatial\u00a0distribution and identification of potential risk regions to rice blast disease in different rice ecosystems of Karnataka","volume":"12","author":"Amoghavarsha","year":"2022","journal-title":"Sci. Rep."},{"key":"B2","first-page":"5450","article-title":"Domain generalization for crop segmentation with standardized ensemble knowledge distillation","author":"Angarano","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.716506","article-title":"Detecting intra-field variation in rice yield with unmanned aerial vehicle imagery and deep learning","volume":"13","author":"Bellis","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B4","first-page":"1676","article-title":"High-resolution UAV image generation for sorghum panicle detection","author":"Cai","year":"2022"},{"key":"B5","first-page":"2030","article-title":"Locating crop plant centers from UAV-based RGB imagery","author":"Chen","year":"2017"},{"key":"B6","first-page":"2825","article-title":"Agriculture-vision: A large aerial image database for agricultural pattern analysis","author":"Chiu","year":"2020"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14040548","article-title":"Crop classification combining object-oriented method and random forest model using unmanned aerial vehicle (UAV) multispectral image","volume":"14","author":"Deng","year":"2024","journal-title":"Agriculture"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"B9","first-page":"733","article-title":"Learning temporal regularity in video sequences","author":"Hasan","year":"2016"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3515","DOI":"10.48550\/arXiv.2308.07050","article-title":"Survey on video anomaly detection in dynamic scenes with moving cameras","volume":"56","author":"Jiao","year":"2023","journal-title":"Artif Intell Rev."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3198130","article-title":"Anomaly detection in aerial videos with transformers","volume":"60","author":"Jin","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B12","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s10489-024-06042-4","article-title":"HSTforU: Anomaly detection in aerial and ground-based videos with hierarchical spatio-temporal transformer for U-net","volume":"55","author":"Le","year":"2025","journal-title":"Appl. Intell."},{"key":"B13","doi-asserted-by":"publisher","first-page":"3240","DOI":"10.1007\/s10489-022-03613-1","article-title":"Attention-based residual autoencoder for video anomaly detection","volume":"53","author":"Le","year":"2023","journal-title":"Appl. Intell."},{"key":"B14","doi-asserted-by":"publisher","first-page":"237","DOI":"10.48550\/arXiv.2403.06977","article-title":"VideoMamba: State space model for efficient video understanding","volume":"15084","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2403.06977"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.20084","article-title":"STNMamba: Mamba-based spatial-temporal normality learning for video anomaly detection","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2412.20084"},{"key":"B16","first-page":"6536","article-title":"Future frame prediction for anomaly detection - a new baseline","author":"Liu","year":"2018"},{"key":"B17","doi-asserted-by":"publisher","first-page":"103031","DOI":"10.48550\/arXiv.2401.10166","article-title":"VMamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2401.10166"},{"key":"B18","first-page":"13568","article-title":"A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction","author":"Liu","year":"2021"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.958106","article-title":"Multispectral remote sensing for accurate acquisition of rice phenotypes: Impacts of radiometric calibration and unmanned aerial vehicle flying altitudes","volume":"13","author":"Luo","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"15425","DOI":"10.48550\/arXiv.2104.06689","article-title":"Learning normal dynamics in videos with meta prototype network","author":"Lv","year":"2021","journal-title":"arXiv preprint arXiv:2104.06689"},{"key":"B21","first-page":"1","article-title":"VADMamba: Exploring state space models for fast video anomaly detection","author":"Lyu","year":"2025"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1067189","article-title":"Spectral characterization and severity assessment of rice blast disease using univariate and multivariate models","volume":"14","author":"Mandal","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/s21196540","article-title":"A deep-learning-based approach for wheat yellow rust disease recognition from unmanned aerial vehicle images","volume":"21","author":"Pan","year":"2021","journal-title":"Sensors"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1256545","article-title":"Xoo-YOLO: A detection method for wild rice bacterial blight in the field from the perspective of unmanned aerial vehicles","volume":"14","author":"Pan","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B25","first-page":"14360","article-title":"Learning memory-guided normality for anomaly detection","author":"Park","year":"2020"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.996514","article-title":"Physiological and molecular implications of multiple abiotic stresses on yield and quality of rice","volume":"13","author":"Radha","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"4277","DOI":"10.3934\/era.2022218","article-title":"Machine learning methods for precision agriculture with UAV imagery: A review","volume":"30","author":"Shahi","year":"2022","journal-title":"Electron. Res. Arch."},{"key":"B28","first-page":"5440","article-title":"Label-free anomaly detection in aerial agricultural images with masked image modeling","author":"Shikhar","year":"2024"},{"key":"B29","doi-asserted-by":"publisher","first-page":"8292","DOI":"10.1109\/TCSVT.2024.3376399","article-title":"Transformer-based spatio-temporal unsupervised traffic anomaly detection in aerial videos","volume":"34","author":"Tran","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"5590","DOI":"10.1109\/JSTARS.2023.3285905","article-title":"UIT-ADrone: A novel drone dataset for traffic anomaly detection","volume":"16","author":"Tran","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B31","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s12284-021-00461-4","article-title":"Proteomics and metabolomics studies on the biotic stress responses of rice: An update","volume":"14","author":"Vo","year":"2021","journal-title":"Rice"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2019.00453","article-title":"Rice yield estimation using parcel-level relative spectral variables from UAV-based hyperspectral imagery","volume":"10","author":"Wang","year":"2019","journal-title":"Front. Plant Sci."},{"key":"B33","first-page":"5403","article-title":"End-to-end deep learning models for gap identification in maize fields","author":"Waqar","year":"2024"},{"key":"B34","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/BF02546511","article-title":"Generalized harmonic analysis","volume":"55","author":"Wiener","year":"1930","journal-title":"Acta Math."},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.17810","article-title":"Token statistics transformer: Linear-time attention via variational rate reduction","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2412.17810"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.1037760","article-title":"Research on weed identification method in rice fields based on UAV remote sensing","volume":"13","author":"Yu","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/s19183859","article-title":"Use of unmanned aerial vehicle imagery and deep learning UNet to extract rice lodging","volume":"19","author":"Zhao","year":"2019","journal-title":"Sensors"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.07454","article-title":"LGN-Net: Local-global normality network for video anomaly detection","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2211.07454"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2018.00936","article-title":"Combining unmanned aerial vehicle (UAV)-based multispectral imagery and ground-based hyperspectral data for plant nitrogen concentration estimation in rice","volume":"9","author":"Zheng","year":"2018","journal-title":"Front. Plant Sci."},{"key":"B40","doi-asserted-by":"publisher","first-page":"62429","DOI":"10.48550\/arXiv.2401.09417","article-title":"Vision Mamba: Efficient visual representation learning with bidirectional state space model","volume":"235","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv:2401.09417"},{"key":"B41","doi-asserted-by":"publisher","first-page":"89943","DOI":"10.52202\/079017-2856","article-title":"Advancing video anomaly detection: A concise review and a new dataset","volume":"37","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1895982\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:36:17Z","timestamp":1787031377000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1895982\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":41,"alternative-id":["10.3389\/fpls.2026.1895982"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1895982","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"1895982"}}