Current status and future directions of weed recognition by UAV remote sensing
Abstract
Abstract: Weed mapping is essential for Site Specific Weed Management (SSWM), which may reduce the negative effects of chemical control while enhancing the effects. The UAV remote sensing platform can rapidly collect the imagery of large scale fields, which may provide efficient decision making information of SSWM applications. This paper explores extensive literature on weed recognition by UAV remote sensing, and classified them into weed classification, weed detection and weed mapping categories according to the research objectives and the corresponding techniques. For each category, we introduce several state of the art researches and summarize its limitations according to the general experimental results. Further, we draw the future directions of the weed recognition, which may effectively address the technique limitation of the current research. In general, the deep learning methods may benefit the weed recognition by UAV remote sensing with its strong data interpretation capability.
Keywords: weed mapping; UAV imagery; OBIA; semantic segmentation; semi-supervised learning
DOI: 10.33440/j.ijpaa.20230601.206
Citation: Yang A Q, Lan Y B, Deng J Z, Zhang Y L and Huang H S. Current status and future directions of weed recognition by UAV remote sensing. Int J Precis Agric Aviat, 2023; 6(1): 84–88.
Full Text:
PDFReferences
Lan Y, Thomson S J and Huang Y, et al. Current status and future directions of precision aerial application for site-specific crop management in the USA, 2010, 74: 34–38. doi: 10.1016/j.compag.2010.07.001.
Huang H, Lan Y and Deng J, et al., Semi-supervised learning for accurate weed mapping of UAV imagery, 2022, 5: doi:
Tian Y P, Zhao S and Zhuang L, et al. An Optimal Model for Carbon Dioxide Emission Control in the Low-Carbon Urban Agglomeration Based on Sustainable Development of Economy, Society and Environment (1): Modeling Construction, 2013, 2115: doi:
Farooq A, Jia X and Hu J, et al. Multi-Resolution Weed Classification via Convolutional Neural Network and Superpixel Based Local Binary Pattern Using Remote Sensing Images, 2019, 11: 1692. doi: 10.3390/rs11141692.
Eide A, Koparan C and Zhang Y, et al. UAV-Assisted Thermal Infrared and Multispectral Imaging of Weed Canopies for Glyphosate Resistance Detection, 2021, 13: 4606. doi: 10.3390/rs13224606.
Lam O H Y, Dogotari M and Prüm M, et al. An open source workflow for weed mapping in native grassland using unmanned aerial vehicle: using Rumex obtusifolius as a case study, 2021, 54: 71–88. doi: 10.1080/22797254.2020.1793687.
Khan S, Tufail M and Khan M T, et al. A novel semi-supervised framework for UAV based crop/weed classification, 2021, 16: e0251008. doi: 10.1371/journal.pone.0251008.
Reedha R, Dericquebourg E and Canals R, et al. Transformer Neural Network for Weed and Crop Classification of High Resolution UAV Images, 2022, 14: 592. doi: 10.3390/rs14030592.
Anul Haq M. CNN Based Automated Weed Detection System Using UAV Imagery, 2022, 42: 837–849. doi: 10.32604/csse.2022.023016.
Veeranampalayam Sivakumar A N, Li J and Scott S, et al. Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid- to Late-Season Weed Detection in UAV Imagery, 2020, 12: 2136. doi: 10.3390/rs12132136.
Khan S, Tufail M and Khan M T, et al. Deep learning-based identification system of weeds and crops in strawberry and pea fields for a precision agriculture sprayer, 2021, 22: 1711–1727. doi: 10.1007/s11119-021-09808-9.
Etienne A, Ahmad A and Aggarwal V, et al. Deep Learning-Based Object Detection System for Identifying Weeds Using UAS Imagery, 2021, 13: 5182. doi: 10.3390/rs13245182.
Saleem M H, Potgieter J and Arif K M. Weed Detection by Faster RCNN Model: An Enhanced Anchor Box Approach, 2022, 12: 1580. doi: 10.3390/agronomy12071580.
Chen J, Wang H and Zhang H, et al. Weed detection in sesame fields using a YOLO model with an enhanced attention mechanism and feature fusion, 2022, 202: 107412. doi: https://doi.org/10.1016/ j.compag.2022.107412.
Gallo I, Rehman A U and Dehkordi R H, et al. Deep Object Detection of Crop Weeds: Performance of YOLOv7 on a Real Case Dataset from UAV Images, 2023, 15: 539. doi: 10.3390/rs15020539.
Ajayi O G, Ashi J and Guda B. Performance evaluation of YOLO v5 model for automatic crop and weed classification on UAV images, 2023, 5: 100231. doi:
Pérez-Porras F J, Torres-Sánchez J and López-Granados F, et al. Early and on-ground image-based detection of poppy (Papaver rhoeas) in wheat using YOLO architectures, 2023, 71: 50–58. doi: 10.1017/wsc.2022.64.
Zhang X, Cui J and Liu H, et al. Weed Identification in Soybean Seedling Stage Based on Optimized Faster R-CNN Algorithm, 2023, 13: 175. doi: 10.3390/agriculture13010175.
Wu H, Wang Y and Zhao P, et al. Small-target weed-detection model based on YOLO-V4 with improved backbone and neck structures, 2023, doi: 10.1007/s11119-023-10035-7.
Huang H, Lan Y and Yang A, et al. Deep learning versus Object-based Image Analysis (OBIA) in weed mapping of UAV imagery, 2020, 41: 3446-3479. doi: 10.1080/01431161.2019.1706112.
Hunter J E, Gannon T W and Richardson R J, et al. Integration of remote?weed mapping and an autonomous spraying unmanned aerial vehicle for site?specific weed management, 2020, 76: 1386–1392. doi: 10.1002/ps.5651.
Gašparovi? M, Zrinjski M and Barkovi? ?, et al. An automatic method for weed mapping in oat fields based on UAV imagery, 2020, 173: 105385. doi: 10.1016/j.compag.2020.105385.
Lan Y, Huang K and Yang C, et al. Real-Time Identification of Rice Weeds by UAV Low-Altitude Remote Sensing Based on Improved Semantic Segmentation Model, 2021, 13: 4370. doi: 10.3390/rs13214370.
de Camargo T, Schirrmann M and Landwehr N, et al. Optimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops, 2021, 13: 1704. doi: 10.3390/rs13091704.
Zou K, Chen X and Zhang F, et al. A Field Weed Density Evaluation Method Based on UAV Imaging and Modified U-Net, 2021, 13: 310. doi: 10.3390/rs13020310.
Torres-Sánchez J, Mesas-Carrascosa F J and Jiménez-Brenes F M, et al. Early Detection of Broad-Leaved and Grass Weeds in Wide Row Crops Using Artificial Neural Networks and UAV Imagery, 2021, 11: 749. doi: 10.3390/agronomy11040749.
Islam N, Rashid M M and Wibowo S, et al. Early Weed Detection Using Image Processing and Machine Learning Techniques in an Australian Chilli Farm, 2021, 11: 387. doi: 10.3390/agriculture11050387.
Che Ya N N, Dunwoody E and Gupta M. Assessment of Weed Classification Using Hyperspectral Reflectance and Optimal Multispectral UAV Imagery, 2021, 11: 1435. doi: 10.3390/agronomy11071435.
Hashemi-Beni L, Gebrehiwot A and Karimoddini A, et al. Deep Convolutional Neural Networks for Weeds and Crops Discrimination From UAS Imagery, 2022, 3: doi: 10.3389/frsen.2022.755939.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.