Classifying cow stall numbers using YOLO
This work addresses a domain-specific problem in agricultural monitoring for farmers or researchers, but it is incremental as it applies an existing method to new data.
The paper tackled the problem of detecting cow stall numbers from images of cow teats by creating the CowStallNumbers dataset and achieved a result of 95.4% accuracy using a fine-tuned YOLO model with data augmentation.
This paper introduces the CowStallNumbers dataset, a collection of images extracted from videos focusing on cow teats, designed to advance the field of cow stall number detection. The dataset comprises 1042 training images and 261 test images, featuring stall numbers ranging from 0 to 60. To enhance the dataset, we performed fine-tuning on a YOLO model and applied data augmentation techniques, including random crop, center crop, and random rotation. The experimental outcomes demonstrate a notable 95.4\% accuracy in recognizing stall numbers.