Intelligent Systems.
Theory and Applications

(Intellektual'nye Sistemy. Teoriya i Prilozheniya)

Cattle identification and counting in single-camera and multi-camera video monitoring

Abstract

Manual cattle counting is labour-intensive, while automation is complicated by occlusions and repeated appearances. A system combining YOLO26L, ByteTrack and ResNet50 is presented. Image selection and track merging are used for single-camera counting, and geometric verification is developed for cross-camera matching. Experiments on MmCows yielded mAP@0.5 \(\approx 0.994\) and Rank-1 Accuracy of 90.6%.

Keywords: computer vision, individual animal identification, multi-camera monitoring, animal counting.

BibTeX
@article{IS-Luzhetskaia-Esaulova-Karavaeva-Balavnev2026,
  author  = {Luzhetskaia, Anastasiia Viktorovna and Esaulova, Diana Sergeevna and Karavaeva, Ksenia Eduardovna and Balavnev, Semen Nikolaevich},
  title   = {{Cattle identification and counting in single-camera and multi-camera video monitoring}},
  journal = {Intelligent Systems. Theory and Applications},
  year    = {2026},
  volume  = {30},
  number  = {4},
  pages   = {377--380},
}
AMSBIB
\Bibitem{IS-Luzhetskaia-Esaulova-Karavaeva-Balavnev2026}
\by A.\,V.~Luzhetskaia, D.\,S.~Esaulova, K.\,E.~Karavaeva, S.\,N.~Balavnev
\paper Cattle identification and counting in single-camera and multi-camera video monitoring
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 377--380
\lang In Russian
Published under Creative Commons Attribution 4.0 International (CC BY 4.0)

← Back to issue

× Issue cover