YOLO-DS: a detection model for desert shrub identification and coverage estimation in UAV remote sensing

Abstract

Desert shrubs are indispensable in maintaining ecological stability by reducing soil erosion, enhancing water retention, and boosting soil fertility, which are critical factors in mitigating desertification processes. Due to the complex topography, variable climate, and challenges in field surveys in desert regions, this paper proposes YOLO-Desert-Shrub (YOLO-DS), a detection method for identifying desert shrubs in UAV remote sensing images based on an enhanced YOLOv8n framework. This method accurately identifying shrub species, locations, and coverage. To address the issue of small individual plants dominating the dataset, the SPDconv convolution module is introduced in the Backbone and Neck layers of the YOLOv8n model, replacing conventional convolutions. This structural optimization mitigates information degradation in fine-grained data while strengthening discriminative feature capture across spatial scales within desert shrub datasets. Furthermore, a structured state-space model is integrated into the main network, and the MambaLayer is designed to dynamically extract and refine shrub-specific features from remote sensing images, effectively filtering out background noise and irrelevant interference to enhance feature representation. Benchmark evaluations reveal the YOLO-DS framework attains 79.56% mAP40weight, demonstrating 2.2% absolute gain versus the baseline YOLOv8n architecture, with statistically significant advantages over contemporary detectors in cross-validation trials. The predicted plant coverage exhibits strong consistency with manually measured coverage, with a coefficient of determination (R²) of 0.9148 and a Root Mean Square Error (RMSE) of 1.8266%. The proposed UAV-based remote sensing method utilizing the YOLO-DS effectively identify and locate desert shrubs, monitor canopy sizes and distribution, and provide technical support for automated desert shrub monitoring.

The online version is available at https://link.springer.com/

Corresponding editor: Lei Yu

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Keywords

Desert shrubs / Deep learning / Object detection / UAV remote sensing / YOLOv8 / Mamba

References

[1] Adarsh P, Rathi P, Kumar M (2020) YOLO v3-Tiny: object detection and recognition using one stage improved model. In: 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). Coimbatore, India. IEEE, 687−694. https://doi.org/10.1109/icaccs48705.2020.9074315

[2] Al-AliZM, AbdullahMM, AsadallaNB, GholoumM. A comparative study of remote sensing classification methods for monitoring and assessing desert vegetation using a UAV-based multispectral sensor. Environ Monit Assess, 2020, 1926389.

[3] AyhanB, KwanC. Tree, shrub, and grass classification using only RGB images. Remote Sens, 2020, 128. 1333

[4] BarboliniN, WoutersenA, Dupont-NivetG, SilvestroD, TardifD, CosterPMC, MeijerN, ChangC, ZhangHX, LichtA, RydinC, KoutsodendrisA, HanF, RohrmannA, LiuXJ, ZhangY, DonnadieuY, FluteauF, LadantJB, Le HirG, HoornC. Cenozoic evolution of the steppe-desert biome in Central Asia. Sci Adv, 2020, 641. eabb8227

[5] Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. Preprint at arXiv:2004.10934. https://arxiv.org/abs/2004.10934

[6] Chen SF, Sun PZ, Song YB, Luo P (2023) DiffusionDet: diffusion model for object detection. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France. IEEE. https://doi.org/10.1109/iccv51070.2023.01816

[7] DelavarpourN, KoparanC, NowatzkiJ, BajwaS, SunX. A technical study on UAV characteristics for precision agriculture applications and associated practical challenges. Remote Sens, 2021, 136. 1204

[8] FahlstromPG, GleasonTJ, SadraeyMHIntroduction to UAV systems, 2022, Hoboken. John Wiley & Sons.

[9] Ge Z (2021) Yolox: Exceeding yolo series in 2021. Preprint at arXiv:2107.08430.

[10] Gu A, Dao T (2023) Mamba: linear-time sequence modeling with selective state spaces. Preprint at arXiv:2312.00752. https://doi.org/10.48550/arXiv.2312.00752

[11] HanDD, DengJC, GuCJ, MuXM, GaoP, GaoJJ. Effect of shrub-grass vegetation coverage and slope gradient on runoff and sediment yield under simulated rainfall. Int J Sediment Res, 2021, 36(1): 29-37.

[12] KattenbornT, LeitloffJ, SchieferF, HinzS. Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS J Photogramm Remote Sens, 2021, 173: 24-49.

[13] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14 (pp. 21−37). Springer International Publishing.

[14] Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Jiao J, Liu Y (2024) VMamba: visual state space model. Preprint at arXiv:240110166, 2024. https://doi.org/10.48550/arXiv.2401.10166

[15] MaL, LiuY, ZhangX, YeY, YinG, JohnsonBA. Deep learning in remote sensing applications: a meta-analysis and review. ISPRS J Photogramm Remote Sens, 2019, 152: 166-177.

[16] MaesWH, SteppeK. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends Plant Sci, 2019, 24(2): 152-164.

[17] MekonnenZA, RileyWJ, BernerLT, BouskillNJ, TornMS, IwahanaG, BreenAL, Myers-SmithIH, CriadoMG, LiuYL, EuskirchenES, GoetzSJ, MackMC, GrantRF. Arctic tundra shrubification: a review of mechanisms and impacts on ecosystem carbon balance. Environ Res Lett, 2021, 165. 053001

[18] Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI. IEEE, 6517−6525. https://doi.org/10.1109/cvpr.2017.690

[19] Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 779−788. https://doi.org/10.1109/cvpr.2016.91

[20] RetallackA, FinlaysonG, OstendorfB, LewisM. Using deep learning to detect an indicator arid shrub in ultra-high-resolution UAV imagery. Ecol Indic, 2022, 145. 109698

[21] SafonovaA, TabikS, Alcaraz-SeguraD, RubtsovA, MaglinetsY, HerreraF. Detection of fir trees (Abies sibirica) damaged by the bark beetle in unmanned aerial vehicle images with deep learning. Remote Sens, 2019, 116643.

[22] Sunkara R, Luo T (2023) No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects. In: Machine learning and knowledge discovery in databases. Springer Nature Switzerland, pp 443–459. https://doi.org/10.1007/978-3-031-26409-2_27

[23] Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning (pp. 6105−6114). PMLR.

[24] TsourosDC, BibiS, SarigiannidisPG. A review on UAV-based applications for precision agriculture. Information, 2019, 1011349.

[25] Varghese R, Sambath M (2024) YOLOv8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS). Chennai, India. IEEE, 1−6. https://doi.org/10.1109/adics58448.2024.10533619

[26] WangXW, ZhaoQZ, JiangP, ZhengYC, YuanL, YuanPL. LDS-YOLO: a lightweight small object detection method for dead trees from shelter forest. Comput Electron Agric, 2022, 198. 107035

[27] Wang CY, Bochkovskiy A, Liao HM (2023) YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada. IEEE, 7464−7475. https://doi.org/10.1109/cvpr52729.2023.00721

[28] WhitfordWG, DuvalBDEcology of desert systems, 20202Amsterdam. Elsevier.

[29] ZerroukiY, HarrouF, ZerroukiN, DairiA, SunY. Desertification detection using an improved variational autoencoder-based approach through ETM-landsat satellite data. IEEE J Sel Top Appl Earth Observ Remote Sens, 2021, 14: 202-213.

[30] ZhangC, AtkinsonPM, GeorgeC, WenZF, DiazgranadosM, GerardF. Identifying and mapping individual plants in a highly diverse high-elevation ecosystem using UAV imagery and deep learning. ISPRS J Photogramm Remote Sens, 2020, 169: 280-291.

[31] Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, Ni LM, Shum HY (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection. Preprint at arXiv:2203.03605. https://doi.org/10.48550/arXiv.2203.03605

[32] Zhang SL, Wang XJ, Wang JQ, Pang JM, Lyu CQ, Zhang WW, Luo P, Chen K (2023) Dense distinct query for end-to-end object detection. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada. IEEE, 7329−7338. https://doi.org/10.1109/cvpr52729.2023.00708

[33] ZhaoLL, ZhuML. MS-YOLOv7: yolov7 based on multi-scale for object detection on UAV aerial photography. Drones, 2023, 73188.

[34] ZuoYL, LiX, YangJY, LiuJQ, ZhaoLL, HeXL. Fungal endophytic community and diversity associated with desert shrubs driven by plant identity and organ differentiation in extremely arid desert ecosystem. J Fungi, 2021, 77. 578

RIGHTS & PERMISSIONS

Northeast Forestry University