SHEEPFEARNET: Sheep fear test behaviors classification approach from video data based on optical flow and convolutional neural networks

Bati, Cafer Tayyar; Ser, Gazel

doi:10.1016/j.compag.2022.107540

Cited by 2 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The YOLO v5 algorithm has been used by different researchers for accurate identification of domestic cattle (Luo et al, 2022), cattle counting from UAV images (de Lima Weber et al, 2023), face identification in dairy cows (Dac et al, 2022), accurate and fast detection of goats (Zhang et al, 2022), and sheep behavior identification (Chen et al, 2022). Recent studies have shown that deep learning technologies that are non-invasive and do not affect animal welfare have the potential to provide ease of livestock identification and management (Bati and Ser, 2023;Subedi et al, 2023). In deep learning studies, unbalanced datasets are encountered, which affect network performance and are a chronic problem for almost every study.…”

Section: Introductionmentioning

confidence: 99%

Effects of Data Augmentation Methods on YOLO v5s: Application of Deep Learning with Pytorch for Individual Cattle Identification

BATİ,

SER

2023

Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate the performance of the YOLO v5s (You Only Look Once) model for the identification of individual cattle in a cattle herd. The model is a popular method for real-time object detection, accuracy, and speed. However, since the videos obtained from the cattle herd consist of free space images, the number of frames in the data is unbalanced. This negatively affects the performance of the YOLOv5 model. First, we investigate the model performance on the unbalanced initial dataset obtained from raw images, then we stabilize the initial dataset using some data augmentation methods and obtain the model performance. Finally, we built the target detection model and achieved excellent model performance with an mAP (mean average precision) of 99.5% on the balanced dataset compared to the model on the unbalanced data (mAP of 95.8%). The experimental results show that YOLO v5s has a good potential for automatic cattle identification, but with the use of data augmentation methods, superior performance can be obtained from the model.

show abstract