Field Pest Detection via Pyramid Vision Transformer and Prime Sample Attention

Background: Pest detection plays a crucial role in smart agriculture; it is one of the primary factors that significantly impact crop yield and quality. Objective: In actual field environments, pests often appear as dense and small objects, which pose a great challenge to field pest detection. Therefore, this paper addresses the problem of dense small pest detection. Methods: We combine a pyramid vision transformer and prime sample attention (named PVTPSA) to design an effective pest detection model. Firstly, a pyramid vision transformer is adopted to extract pest feature information. Pyramid vision transformer fuses multi-scale pest features through pyramid structure and can capture context information of small pests, which is conducive to the feature expression of small pests. Then, we design prime sample attention to guide the selection of pest samples in the model training process to alleviate the occlusion effect between dense pests and enhance the overall pest detection accuracy. Results: The effectiveness of each module is verified by the ablation experiment. According to the comparison experiment, the detection and inference performance of the PVT-PSA is better than the other eleven detectors in field pest detection. Finally, we deploy the PVT- PSA model on a terrestrial robot based on the Jetson TX2 motherboard for field pest detection. Conclusion: The pyramid vision transformer is utilized to extract relevant features of pests. Additionally, prime sample attention is employed to identify key samples that aid in effectively training the pest detection models. The model deployment further demonstrates the practicality and effectiveness of our proposed approach in smart agriculture applications.