Small Object Detection for Red Ant Egg Classification and Detection

Authors

  • Thummarat Boonrod Department of Business Computer, Faculty of Administrative Science, Kalasin University https://orcid.org/0009-0006-6014-2803
  • Suksun Promboonruang Department of Business Computer, Faculty of Administrative Science, Kalasin University
  • Bancha Luaphol Department of Business Computer, Faculty of Administrative Science, Kalasin University
  • Sawvaluk Jittimongkon Department of Business Administration, Faculty of Administrative Science, Kalasin University
  • Jurawan Pansathit Research Assistant, Faculty of Administrative Science, Kalasin University

Keywords:

Classification, Red Ant Egg, Small Object Detection, YOLOv11n

Abstract

This research aims to apply small object detection techniques to classify and detect red ant eggs from images captured in artificial nests, with the objective of improving detection accuracy for estimating egg quantity. The study employs a deep learning model based on YOLO, specifically the YOLOv11n version, which is an effective approach for small object detection tasks. The research methodology is divided into four main stages: data collection, image preprocessing, model training and testing, and performance evaluation. The dataset consists of 47 images of red ant eggs, divided into 32 training images, 9 validation images, and 6 testing images, corresponding to a ratio of 70:20:10. Data augmentation techniques, including image scaling, rotation, brightness and color adjustment, were applied to increase data diversity and reduce overfitting. The experimental results found that the model can detect red ant eggs with a precision was 0.66 and a recall was 0.79. The mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 0.5 (mAP@0.5) was 0.76, while the mAP@0.5:0.95 was 0.49. The results also show that the model performs better in detecting larger objects compared to smaller ones. This research shows the potential of applying deep learning-based object detection techniques in smart agriculture systems to support the detect and estimation of red ant egg production.

References

[1] กลุ่มสารสนเทศและข้อมูลสถิติ ศูนย์เทคโนโลยีสารสนเทศและการสื่อสาร, “ข้อมูลจำนวนปศุสัตว์ในประเทศไทย 2568,” [ออนไลน์]. Available: https://ict.dld.go.th/index.php/th/service/report/book/report-book-2568. [เข้าถึงเมื่อ: 7 เม.ย. 2569].

[2] นันทิญา มณีโชติ, ชวนพิศ จารัตน์, วัจนารัตน์ ควรดี, นิชาภา เฉตระการ, ฐิตาภรณ์ นิลวรรณ, และยุพเยาว์ โตคีรี, “การเพาะเลี้ยงมดแดงในครัวเรือน กรณีศึกษาพื้นที่แปลงปลูกไม้มีค่าทางเศรษฐกิจในจังหวัดสุรินทร์,” วารสารแก่นเกษตร, ปีที่ 52, ฉบับ 2, หน้า 226–236, 2567, doi: 10.14456/kaj.2024.16.

[3] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), Kauai, HI, USA, 2001, vol. 1, pp. I-511–I-518, doi: 10.1109/CVPR.2001.990517.

[4] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), San Diego, CA, USA, 2005, vol. 1, pp. 886–893, doi: 10.1109/CVPR.2005.177.

[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, Jun. 2017, doi: 10.1145/3065386.

[6] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, Jun. 2017, doi: 10.1109/TPAMI.2016.2577031.

[7] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91.

[8] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “SSD: Single shot multibox detector,” in Computer Vision – ECCV 2016, Lecture Notes in Computer Science, vol. 9905. Cham, Switzerland: Springer, 2016, pp. 21–37, doi: 10.1007/978-3-319-46448-0_2.

[9] X. Yuan, A. Chakravarty, E. M. Lichtenberg, L. Gu, Z. Wei, and T. Chen, “An empirical study of methods for small object detection from satellite imagery,” arXiv preprint arXiv:2502.03674, 2025, doi: 10.48550/arXiv.2502.03674.

[10] C. Deng, L. Chen, and S. Liu, “YOLOSCM: An improved YOLO algorithm for cars detection,” arXiv preprint arXiv:2501.13343, 2025, doi: 10.48550/arXiv.2501.13343.

[11] A. Raza, F. Hanif, and H. A. Mohammed, “Analyzing the enhancement of CNN-YOLO and transformer based architectures for real-time animal detection in complex ecological environments,” Sci. Rep., vol. 15, Art. no. 39142, Nov. 2025, doi: 10.1038/s41598-025-26645-2.

[12] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Vancouver, BC, Canada, 2023, pp. 7464–7475, doi: 10.1109/CVPR52729.2023.00721.

[13] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, 2017, pp. 2117–2125, doi: 10.1109/CVPR.2017.106.

[14] G. M. Dlussky, T. Wappler, and S. Wedmann, “New middle Eocene formicid species from Germany and the evolution of weaver ants,” Acta Palaeontol. Pol., vol. 53, no. 4, pp. 615–626, 2008, doi: 10.4202/app.2008.0406.

[15] G. Jocher and J. Qiu, “Ultralytics YOLO11,” Ultralytics, 2024. [Online]. Available: https://github.com/ultralytics/ultralytics

[16] X. Gong, J. Yu, H. Zhang, and X. Dong, “AED-YOLO11: A small object detection model based on YOLO11,” Digit. Signal Process., vol. 166, Art. no. 105411, Nov. 2025, doi: 10.1016/J.DSP.2025.105411.

Downloads

Published

2026-08-25

How to Cite

[1]
T. Boonrod, S. Promboonruang, B. Luaphol, S. Jittimongkon, and J. Pansathit, “Small Object Detection for Red Ant Egg Classification and Detection”, JEIT, vol. 4, no. 4, pp. 38–49, Aug. 2026.