Artificial Intelligence and Remote Sensing Application

A lightweight SSV2-YOLO based model for detection of sugarcane aphids

A lightweight deep-learning model was developed to detect sugarcane aphids in broad-leaf crops. The model was developed based You Only Look Once-v5-small by reconstructing the backbone network with Stem and ShuffleNet V2 and adjusting the neck network width. We further refactored the feature level, data augmentation method, and loss function to improve detection performance for small, high-density, and overlapping targets. The proposed model outperformed other state-of-the-art algorithms [Xu et al., 2023] and can be potentially used for the automatic section of SCAs on mobile device.

See here for the YOLO-Tpest app and SCAs-SSV2-YOLO algorithm download.

A novel lightweight model for real-time multiclass tiny pest detection and mobile platform deployment

We developed a mobile application (GBiDC-PEST) that incorporates an improved, lightweight detection algorithm based on the you only look once (YOLO) series single-stage architecture for real-time detection of four tiny pests (wheat mites, sugarcane aphids, wheat aphids, and rice planthoppers). The newly developed GBiDC-PEST was trained and validated using a multitarget agricultural tiny pest dataset (Tpest-3960) that covered various field environments. The GBiDC-PEST optimization algorithm and its mobile deployment proposed in this study offer a robust technical framework for the rapid, onsite identification and localization of tiny pests. This advancement provides valuable insights for effective pest monitoring, counting, and control in various agricultural settings. [Xu et al., 2024].