Comparative Analysis of Real-Time Detection Models for Intelligent Monitoring of Cattle Condition and Behavior


Ivashchuk O. Kenzhebayeva Z. Zhigalov A. Allaniyazova M. Kaziyeva G. Makulov K. Fedorov V. Ivashchuk O.
December 2025Multidisciplinary Digital Publishing Institute (MDPI)

Algorithms
2025#18Issue 12

This study benchmarks nine state-of-the-art object detection models on a specialized cattle dataset to assess accuracy and inference speed for real-time agricultural applications. Using a unified protocol without model-specific augmentations, and evaluating all detectors on identical RTX 4090 hardware, we provide a fair architectural comparison of two-stage, one-stage, and transformer-based models. D_FINE_L and Co_DETR_R_50 achieved the highest accuracy (AP@[0.50:0.95] = 0.872 and 0.851), while RTMDet and YOLOv11_L were the fastest (15.81 and 19.14 ms/image). All models showed substantial accuracy gains on the domain dataset compared to COCO, while maintaining consistent relative speed rankings.

agriculture , benchmarking , D_FINE_L , MMDetection , object detection , real time , RTMDet_m

Text of the article Перейти на текст статьи

Department of Computer Science, Faculty of Science and Technology, Caspian University of Technology and Engineering (KUTI) Named After Sh. Yessenov, Micro District 32, Aktau, 130000, Kazakhstan
Individual Entrepreneur Zhigalov A.A. (neural.dev), Agmashenebeli Str., 1Adjara, Batumi, 6004, Georgia
Department of Information and Robotic Systems, Belgorod State National Research University, 85, Pobedy St., Belgorod, 308015, Russian Federation

Department of Computer Science
Individual Entrepreneur Zhigalov A.A. (neural.dev)
Department of Information and Robotic Systems

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026