TP-YOLO: A Lightweight Attention-Based Architecture for Tiny Pest Detection

• Published in: 2023 IEEE International Conference on Image Processing (ICIP) pp. 3394 - 3398
• Main Authors: Di, Yang, Phung, Son Lam, Van Den Berg, Julian, Clissold, Jason, Bouzerdoum, Abdesselam
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.10.2023
• Subjects: attention mechanism; CNN; Convolution; Feature extraction; Image edge detection; Object detection; Performance evaluation; Pest detection; Predictive models; Transformers; vision transformers; YOLO
• DOI: 10.1109/ICIP49359.2023.10222202

Automatic detection of agricultural pests is a challenging problem that is of great interest in biosecurity and precision agriculture. The detection model must cope well with the dense distribution of small-sized pests in complex backgrounds. This paper proposes a lightweight attention-based network, called TP-YOLO, for tiny pest detection. We introduce two attention-based components, namely Contextual Transformer and Omni-Dimensional Dynamic Convolution modules, to enhance feature extraction. The proposed modules are integrated into the YOLOv8 backbone, a state-of-the-art baseline for object detection. This paper also introduces a new benchmark dataset consisting of 1,600 images of Khapra beetles for objective evaluation of pest detection algorithms. Extensive experiments on two datasets indicate that TP-YOLO achieves competitive detection accuracy while having a significantly smaller model size and fast prediction time. We have made the code available to the public at: https://github.com/yangdi-cv/TP-YOLO.