2000 character limit reached
Classifying cow stall numbers using YOLO
Published 23 Nov 2023 in cs.CV | (2401.03340v1)
Abstract: 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.
- Yolov8. GitHub. https://docs.ultralytics.com/.
- Albumentations: Fast and flexible image augmentations. arXiv preprint arXiv:1809.06839, 2020.
- Ross B. Girshick. Fast R-CNN. CoRR, abs/1504.08083, 2015.
- Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR, abs/1311.2524, 2013.
- SSD: single shot multibox detector. CoRR, abs/1512.02325, 2015.
- Efficientnet: Rethinking model scaling for convolutional neural networks. CoRR, abs/1905.11946, 2019.
- Separable confident transductive learning for dairy cows teat-end condition classification. Animals (Basel), 12(7):886, Mar 2022.
- Unsupervised few shot key frame extraction for cow teat videos. Data, 7(5), 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
