Sorghum aphid, Melanaphis sorghi (Theobald) have become a major economic pest in sorghum causing 70% yield loss without timely insecticide applications. The overarching goal is to develop a monitoring system for sorghum aphids using remote sensing technologies to detect changes in plant-aphid density interactions, thereby reducing scouting time. We studied the effect of aphid density on sorghum spectral responses near the feeding site and on distal leaves from infestation and quantified potential systemic effects to determine if aphid feeding can be detected. A leaf spectrometer at 400–1000 nm range was used to measure reflectance changes by varying levels of sorghum aphid density on lower leaves and those distant to the caged infestation. Our study results demonstrate that sorghum aphid infestation can be determined by changes in reflected light, especially between the green–red range (550–650 nm), and sorghum plants respond systemically. This study serves as an essential first step in developing more effective pest monitoring systems for sorghum aphids, as leaf reflection sensors can be used to identify aphid feeding regardless of infestation location on the plant. Future research should address whether such reflectance signatures can be detected autonomously using small unmanned aircraft systems or sUAS equipped with comparable sensor technologies.
Aphid infestations are one of the primary causes of extensive damage to wheat and sorghum fields and are one of the most common vectors for plant viruses, resulting in significant agricultural yield losses. To address this problem, farmers often employ the inefficient use of harmful chemical pesticides that have negative health and environmental impacts. As a result, a large amount of pesticide is wasted on areas without significant pest infestation. This brings to attention the urgent need for an intelligent autonomous system that can locate and spray sufficiently large infestations selectively within the complex crop canopies. We have developed a large multi-scale dataset for aphid cluster detection and segmentation, collected from actual sorghum fields and meticulously annotated to include clusters of aphids. Our dataset comprises a total of 54,742 image patches, showcasing a variety of viewpoints, diverse lighting conditions, and multiple scales, highlighting its effectiveness for real-world applications. In this study, we trained and evaluated four real-time semantic segmentation models and three object detection models specifically for aphid cluster segmentation and detection. Considering the balance between accuracy and efficiency, Fast-SCNN delivered the most effective segmentation results, achieving 80.46% mean precision, 81.21% mean recall, and 91.66 frames per second (FPS). For object detection, RT-DETR exhibited the best overall performance with a 61.63% mean average precision (mAP), 92.6% mean recall, and 72.55 on an NVIDIA V100 GPU. Our experiments further indicate that aphid cluster segmentation is more suitable for assessing aphid infestations than using detection models.
The performance of computer vision models for object detection and classification is heavily influenced by the number of classes and quality of input images, particularly in biological applications such as species-level identification of bumblebees. Bee identification is time-consuming, costly, and requires specialized taxonomic training. Different deep learning based computer vision models have been proven to overcome this methodological bottleneck through automated identification of bee species from captured images. However, accurate identification of bee species in images containing multiple objects of various classes poses significant challenges due to ambiguity, poor image quality, and noisy backgrounds. Existing pipelines (baselines) primarily rely on object detection to crop bees from images and classify the species for each cropped instance. This approach is limited by the inclusion of noisy backgrounds, low resolution, and poor image quality. To address these limitations, we propose an enhanced pipeline that integrates object detection with segmentation to generate body masks for bees and remove background noise. This process is complemented by a classification model that identifies the top k species for each masked image. The proposed methodology significantly improves both detection and classification performance in most cases, demonstrating its potential to advance automated identification of bee species in complex image datasets. For the cases where the baselines performed much better, we investigated using a state-of-the-art explainable AI model (Grad-CAM) to explain the reason.