Morphological Phenotyping for Cattle Breeds Classification from Unmanned Aerial Vehicle Imagery via Computer Vision and Deep Learning
Abstract
Advancements in unmanned aerial vehicle (UAV) technologies have facilitated a novel approach to dairy cattle breed morphological identification. The objective of this study was to employ UAV images, analyzed through deep convolutional neural networks (DCNN), to classify dairy cow breeds. The dataset comprises of 2004 RGB UAV images of dairy cows, including Holstein, Simmental, and Brown-Swiss breeds, obtained from the cattle breeding facility at Van Yüzüncü Yıl University. The images were preprocessed and segmented to contain a single cow each, and subsequently categorized as training (70%), validation (20%), and testing (10%) datasets. To determine the most effective architecture for breed classification, we compared a custom DCNN (C-DCNN) model to well-established pre-trained models including Xception, VGG19, and ResNet50. The C-DCNN demonstrated remarkable performance, achieving precision, recall, accuracy, and F1 scores of 0.98. Among the pre-trained models, Xception demonstrated superior results, with perfect accuracy and an F1 score of 1.00. Conversely, the VGG19 model exhibited a higher level of accuracy; nevertheless, it exhibited lower precision, recall, and F1 scores when evaluated on the test set, compared to the C-DCNN and Xception models. In contrast, ResNet50 displayed the lowest level of performance, with an accuracy of 0.74 and the highest levels of loss. This study demonstrates the potential of integrating DCNN models with UAV technology in precision livestock farming, offering a robust and efficient system for cattle breed classification.
Keywords
Computer vision, Deep convolutional neural networks, Drone, Unmanned aerial vehicle, Xception
Ethical Statement
This study was approved by the Van Yüzüncü Yıl University Animal Experiments Local Ethics Committee on November 30, 2023 (approval number 2023/13-08).
Thanks
The authors wish to express their gratitude to the staff of the cattle breeding facility at the research farm of Van Yüzüncü Yıl University for their invaluable assistance in animal handling.
This study was presented as an abstract at the 6th International Food, Agriculture and Veterinary Sciences Congress, Ganja, Azerbaijan, 22-23 September 2023.
References
- Alfarhood, S., Alrayeh, A., Safran, M., Alfarhood, M., & Che, D. (2023). Image-Based arabian camel breed classification using transfer learning on CNNs. Applied Sciences, 13(14), 8192. https://doi.org/10.3390/app13148192
- Barbedo, J. G. A., Koenigkan, L. V., & Santos, P. M. (2020a). Cattle detection using oblique UAV images. Drones, 4(4), 75. https://doi.org/10.3390/drones4040075
- Barbedo, J. G. A., Koenigkan, L. V., Santos, P. M., & Ribeiro, A. R. B. (2020b). Counting cattle in UAV Images-dealing with clustered animals and animal/background contrast changes. Sensors, 20(7), 2126. https://doi.org/10.3390/s20072126
- Barbedo, J. G. A., Koenigkan, L. V., Santos, T. T., & Santos, P. M. (2019). A study on the detection of cattle in UAV images using deep learning. Sensors, 19(24), 5436. https://doi.org/10.3390/s19245436
- Barney, S., Dlay, S., Crowe, A., Kyriazakis, I., & Leach, M. (2023). Deep learning pose estimation for multi-cattle lameness detection. Scientific reports, 13(1), 4499. https://doi.org/10.1038/s41598-023-31297-1
- Bila, L., Malatji, D. P., & Tyasi, T. L. (2023). Morphological characterization of Sussex cattle at Huntersvlei farm, Free State Province, South Africa. Plos one, 18(9), e0292088. https://doi.org/10.1371/journal.pone.0292088
- Çakmakçı, C., Magalhaes, D. R., Pacor, V. R., de Almeida, D. H. S., Çakmakçı, Y., Dalga, S., ... & Titto, C. G. (2023). Discovering the hidden personality of lambs: harnessing the power of deep convolutional neural networks (DCNNs) to predict temperament from facial images. Applied Animal Behaviour Science, 267, 106060. https://doi.org/10.1016/j.applanim.2023.106060
- Cheng, T., Li, P., Ma, J., Tian, X., & Zhong, N. (2022). Identification of four chicken breeds by hyperspectral imaging combined with chemometrics. Processes, 10(8), 1484. https://doi.org/10.3390/pr10081484
- Chollet, F. (2017a). Deep learning with Python. First ed. New York, USA: Manning.
- Chollet, F. (2017b). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251-1258).
