Pine wilt disease is a significant global plant epidemic and a management priority for numerous countries worldwide. Pine wood nematodes can parasitize a wide range of pine species, making early detection of infected trees essential for preventing further spread of the disease. Recent advances in deep learning and remote sensing technologies have enabled efficient automated detection of diseased trees. Most existing methods rely on convolutional neural network layers for feature extraction and spatial dimension reduction, which may cause the loss of fine-grained texture details and lead to misdetection of background elements and visually similar objects. To enhance diseased tree recognition accuracy, this paper proposes an object detection model using images captured by unmanned aerial vehicles. The proposed method incorporates discrete wavelet transform (DWT) to reduce spatial resolution while preserving critical information for further analysis, and integrates a cross-modal channel enhancement module within a two-stream feature extraction network. Furthermore, the method incorporates a RoI-based similarity constraint that applies cosine similarity loss and classification supervision to ensure coherent feature representations between processing branches. This approach achieves 89.2% accuracy on the pine wilt disease dataset and outperforms advanced methods on the VisDrone dataset. Several object detection models are compared based on the mean average precision (mAP) metric. Results demonstrate that the DWT-based detection algorithm achieves superior performance in detecting individual small targets and clustered infected pine trees.
Zhou et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: