Classification of Plant Pests Using the Real-Time Detection Transformer (RT-DETR) Algorithm in Oil Palm Plants

Bayu Ath Thariq Syams (Institut Teknologi Sawit Indonesia)
Ratu Mutiara Siregar (Institut Teknologi Sawit Indonesia)
Muhammad Akbar Syahbana Pane (Universitas Negeri Medan)

Sisfo: Jurnal Ilmiah Sistem Informasi
Vol. 10 No. 1 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2026

Plant Pests (PP) are one of the main factors causing a decline in oil palm productivity. This study focuses on the classification of PP, limited to the three main pest species: the rhinoceros beetle (Oryctes rhinoceros), the fireworm (Setora nitens), and the Tioman rat (Rattus tiomanicus). The dataset consists of digital images representing these three pest types. The method used is the Real-Time Detection Transformer (RT-DETR), which is capable of real-time, end-to-end object detection. The research stages include data collection, preprocessing, model training, and evaluation using confusion matrix, precision, recall, and F1-score metrics. The research results are expected to produce an accurate and efficient crop pest classification system to support decision-making in pest management in oil palm plantations.