An infrared small target detection model via Gather-Excite attention and normalized Wasserstein distance.

Infrared small target detection (ISTD) is the main research content for defense confrontation, long-range precision strikes and battlefield intelligence reconnaissance. Targets from the aerial view have the characteristics of small size and dim signal. These characteristics affect the performance of traditional detection models. At present, the target detection model based on deep learning has made huge advances. The You Only Look Once (YOLO) series is a classic branch. In this paper, a model with better adaptation capabilities, namely ISTD-YOLOv7, is proposed for infrared small target detection. First, the anchors of YOLOv7 are updated to provide prior. Second, Gather-Excite (GE) attention is embedded in YOLOv7 to exploit feature context and spatial location information. Finally, Normalized Wasserstein Distance (NWD) replaces IoU in the loss function to alleviate the sensitivity of YOLOv7 for location deviations of small targets. Experiments on a standard dataset show that the proposed model has stronger detection performance than YOLOv3, YOLOv5s, SSD, CenterNet, FCOS, YOLOXs, DETR and the baseline model, with a mean Average Precision (mAP) of 98.43%. Moreover, ablation studies indicate the effectiveness of the improved components.

A LAMP-Based Toolbox Developed for Detecting the Major Pathogens Affecting the Production and Quality of the Chinese Medicinal Crop Aconitum carmichaelii.

Aconitum carmichaelii Debeaux is a traditional Chinese medicinal herb that has been utilized for approximately 2,000 years. However, as cultivation has increased, there have been more reports of A. carmichaelii infections caused by four major pathogenic fungal species, Fusarium oxysporum, F. solani, Mucor circinelloides, and Sclerotium rolfsii, resulting in increased disease incidences and limited production and quality. To detect these infections, we developed a LAMP-based toolbox in this study. The cytochrome c oxidase subunit 1 (cox1) gene, translation elongation factor-1α (EF-1α), internal transcribed spacer (ITS) regions of rDNA, and alcohol dehydrogenase 1 (ADH1) gene, respectively, were used to design species-specific LAMP primer sets for F. oxysporum, F. solani, S. rolfsii, and M. circinelloides. The results showed that the LAMP-based toolbox was effective at detecting pathogens in soil and plant materials. We also used this toolbox to investigate pathogen infection in the main planting regions of A. carmichaelii. Before harvesting, F. oxysporum, M. circinelloides, and S. rolfsii were commonly found in the planting fields and in infected A. carmichaelii plants. Therefore, the toolbox we developed will be useful for tracking these infections, as well as for disease control in A. carmichaelii.