Bee Detection and Tracking at Hive Entrance using YOLO11 and ByteTrack
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a system to automatically detect and count bees entering and leaving a hive using a camera and computer algorithms. They improved detection by gradually training parts of their model instead of all at once and used mild data changes to help the model learn better. They also fine-tuned a tracking method to follow bees more accurately when the images were blurry or bees moved fast. In tests, their system correctly counted most incoming bees but had more difficulty with outgoing ones, mainly due to rapid movement causing misses. Overall, their approach made monitoring bees more reliable in real-world conditions.
YOLO11ByteTracktransfer learningdata augmentationbackbone unfreezingobject detectiontracking algorithmmotion blurprecisionmAP50
Authors
Thi Thu Thao Nguyen, Johannes Reschke
Abstract
This work presents an automatic bee entrance monitoring system based on YOLO11 transfer learning and the ByteTrack tracking algorithm. The study investigates the influence of data augmentation, backbone freezing, and tracker parameter optimization on the detection and counting of small, fast-moving bees. The detector with progressive backbone unfreezing strategy achieved about 97.0% precision and 98.7% mAP50, while providing more stable convergence than full fine-tuning. Experiments also showed that light augmentation outperformed heavy augmentation. For tracking, ByteTrack parameters were optimized to improve trajectory continuity under low-confidence detections. On an independent 25 FPS side-view video, the optimized YOLO11-ByteTrack system correctly counted 43 of 47 incoming bees (91.5%) and 7 of 30 outgoing bees (23.3%). Error analysis showed that most counting errors were caused by missed detections due to rapid bee motion and motion blur, while tracking failures became less frequent after parameter optimization. Overall, the results indicate that moderate augmentation, progressive backbone unfreezing, and ByteTrack tuning improve the reliability of automatic bee entrance monitoring under realistic recording conditions.