A Hybrid Vegetation Detection Framework: Integrating Vegetation Indices and Convolutional Neural Network

Analysis of YOLOv5 and DeepLabv3+ Algorithms for Detecting Illegal Cultivation on Public Land: A Case Study of a Riverside in Korea

Rivers are generally classified as either national or local rivers. Large-scale national rivers are maintained through systematic maintenance and management, whereas many difficulties can be encountered in the management of small-scale local rivers. Damage to embankments due to illegal farming along rivers has resulted in collapses during torrential rainfall. Various fertilizers and pesticides are applied along embankments, resulting in pollution of water and ecological spaces. Controlling such activities along riversides is challenging given the inconvenience of checking sites individually, the difficulty in checking the ease of site access, and the need to check a wide area. Furthermore, considerable time and effort is required for site investigation. Addressing such problems would require rapidly obtaining precise land data to understand the field status. This study aimed to monitor time series data by applying artificial intelligence technology that can read the cultivation status using drone-based images. With these images, the cultivated area along the river was annotated, and data were trained using the YOLOv5 and DeepLabv3+ algorithms. The performance index mAP@0.5 was used, targeting >85%. Both algorithms satisfied the target, confirming that the status of cultivated land along a river can be read using drone-based time series images.

Combining Spectral and Textural Information from UAV RGB Images for Leaf Area Index Monitoring in Kiwifruit Orchard

The use of a fast and accurate unmanned aerial vehicle (UAV) digital camera platform to estimate leaf area index (LAI) of kiwifruit orchard is of great significance for growth, yield estimation, and field management. LAI, as an ideal parameter for estimating vegetation growth, plays a significant role in reflecting crop physiological process and ecosystem function. At present, LAI estimation mainly focuses on winter wheat, corn, soybean, and other food crops; in addition, LAI on forest research is also predominant, but there are few studies on the application of orchards such as kiwifruit. Concerning this study, high-resolution UAV images of three growth stages of kiwifruit orchard were acquired from May to July 2021. The extracted significantly correlated spectral and textural parameters were used to construct univariate and multivariate regression models with LAI measured for corresponding growth stages. The optimal model was selected for LAI estimation and mapping by comparing the stepwise regression (SWR) and random forest regression (RFR). Results showed the model combining texture features was superior to that only based on spectral indices for the prediction accuracy of the modeling set, with the R2 of 0.947 and 0.765, RMSE of 0.048 and 0.102, and nRMSE of 7.99% and 16.81%, respectively. Moreover, the RFR model (R2 = 0.972, RMSE = 0.035, nRMSE = 5.80%) exhibited the best accuracy in estimating LAI, followed by the SWR model (R2 = 0.765, RMSE = 0.102, nRMSE = 16.81%) and univariate linear regression model (R2 = 0.736, RMSE = 0.108, nRMSE = 17.84%). It was concluded that the estimation method based on UAV spectral parameters combined with texture features can provide an effective method for kiwifruit growth process monitoring. It is expected to provide scientific guidance and practical methods for the kiwifruit management in the field for low-cost UAV remote sensing technology to realize large area and high-quality monitoring of kiwifruit growth, thus providing a theoretical basis for kiwifruit growth investigation.