Pine wilt disease detection in high-resolution UAV images using object-oriented classification

Abstract

Pine wilt disease (PWD) is currently one of the main causes of large-scale forest destruction. To control the spread of PWD, it is essential to detect affected pine trees quickly. This study investigated the feasibility of using the object-oriented multi-scale segmentation algorithm to identify trees discolored by PWD. We used an unmanned aerial vehicle (UAV) platform equipped with an RGB digital camera to obtain high spatial resolution images, and multi-scale segmentation was applied to delineate the tree crown, coupling the use of object-oriented classification to classify trees discolored by PWD. Then, the optimal segmentation scale was implemented using the estimation of scale parameter (ESP2) plug-in. The feature space of the segmentation results was optimized, and appropriate features were selected for classification. The results showed that the optimal scale, shape, and compactness values of the tree crown segmentation algorithm were 56, 0.5, and 0.8, respectively. The producer’s accuracy (PA), user’s accuracy (UA), and F1 score were 0.722, 0.605, and 0.658, respectively. There were no significant classification errors in the final classification results, and the low accuracy was attributed to the low number of objects count caused by incorrect segmentation. The multi-scale segmentation and object-oriented classification method could accurately identify trees discolored by PWD with a straightforward and rapid processing. This study provides a technical method for monitoring the occurrence of PWD and identifying the discolored trees of disease using UAV-based high-resolution images.

Application of YOLOv5 for Point Label Based Object Detection of Black Pine Trees with Vitality Losses in UAV Data

“…However, one restriction for comparison is that not all articles fitting this description use the F 1 score as a metric [40,41]. Sun et al [42] proposed a method for RGB imagery that performs tree crown segmentation first and then classifies those segments into the classes tree crown, tree crown discolored by pine wilt disease, and forest gap. The proposed method achieved an F 1 score of 65.8% regarding trees discolored by pine wilt disease (Table 3).…”

Recent Advances in Forest Insect Pests and Diseases Monitoring Using UAV-Based Data: A Systematic Review

“…For example, the study of Briechle et al [87] was conducted using only the interpretation of the imagery collected with UAVs due to the danger of radiation in the Chernobyl Exclusion Zone. The authors of [75,77,83] performed their research through imagery interpretation, without in situ measurements or laboratory data collection, to investigate the feasibility of using the specific classification algorithms.…”

“…Multispectral image segmentation using eCognition software multiresolution segmentation tool. [12,61,83] Local maxima filter and mean shift algorithm…”

“…Spectral features Statistics of original bands, ratios between bands, vegetation indices [12,15,39,40,[43][44][45][46][48][49][50][51][54][55][56][57][58][59][60][61][62][63][64]66,[68][69][70][71][72]75,77,[79][80][81][82][83][84][85][86][87] Textural features Gray level co-occurrence matrix (GLCM), grey level difference vector (GLDV) [48,68,86] Linear transformations Hue, saturated and intensity (HSI), principal component analysis (PCA) [55,61,79] Geo-auxiliary Original and normalized digital surface models (DSM) such as digital elevation models (DEM), canopy height models (CHM), slope, aspect, height percentiles [12,…”

Detection of Pine-Wilt-Disease-Affected Trees Based on Improved YOLO v7

“…The Random Forest classifier has been used to detect and classify symptomatic trees, achieving an accuracy higher than 0.91 on both high spatial resolution multispectral and hyperspectral images [4]. Integrating a multiscale segmentation algorithm with an object-oriented approach has optimized the feature space of segmentation results, enabling accurate and rapid identification and classification of symptomatic trees [5]. Support vector machine (SVM) classifiers have exhibited overall accuracies of 94.13% and 86.59% in two areas of study in PWD detection, with an average overall accuracy of 90.36% [6].…”