Individual identification model and method for estimating social rank among herd of dairy cows using YOLOv5

Uchino, Tom; Ohwada, Hayato

doi:10.1109/iccicc53683.2021.9811319

Cited by 4 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reviewing various studies on cattle behavior detection, Fuentes et al [31] employed the YOLOv3 model to detect 15 classes of cow behavior in 1920 × 1080 resolution images, achieving a mAP of 78.8%. Similarly, Uchino and Ohwada [32] achieved a mAP of 91.5% utilizing the YOLOv5-L model for four classes at a resolution of 3840 × 2160. Our study has shown similar or higher performance despite utilizing lower resolutions.…”

Section: Discussionmentioning

confidence: 88%

Optimizing Cattle Behavior Analysis in Precision Livestock Farming: Integrating YOLOv7-E6E with AutoAugment and GridMask to Enhance Detection Accuracy

Sim,

Kim,

Lee

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Recently, the growing demand for meat has increased interest in precision livestock farming (PLF), wherein monitoring livestock behavior is crucial for assessing animal health. We introduce a novel cattle behavior detection model that leverages data from 2D RGB cameras. It primarily employs you only look once (YOLO)v7-E6E, which is a real-time object detection framework renowned for its efficiency across various applications. Notably, the proposed model enhances network performance without incurring additional inference costs. We primarily focused on performance enhancement and evaluation of the model by integrating AutoAugment and GridMask to augment the original dataset. AutoAugment, a reinforcement learning algorithm, was employed to determine the most effective data augmentation policy. Concurrently, we applied GridMask, a novel data augmentation technique that systematically eliminates square regions in a grid pattern to improve model robustness. Our results revealed that when trained on the original dataset, the model achieved a mean average precision (mAP) of 88.2%, which increased by 2.9% after applying AutoAugment. The performance was further improved by combining AutoAugment and GridMask, resulting in a notable 4.8% increase in the mAP, thereby achieving a final mAP of 93.0%. This demonstrates the efficacy of these augmentation strategies in improving cattle behavior detection for PLF.

show abstract

Section: Discussionmentioning

confidence: 88%

Optimizing Cattle Behavior Analysis in Precision Livestock Farming: Integrating YOLOv7-E6E with AutoAugment and GridMask to Enhance Detection Accuracy

Sim,

Kim,

Lee

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In CHN module, the original feature map X, which is the product of height H, width W, and number of channels N, is pooled to obtain the channel map, and then processed by multilayer perceptron (MLP) to obtain the feature weights, combined with the ReLU activation function to obtain the channel weight coefficients M n . The product of M n and M is used as the scaled channel feature map Y, and M n is calculated as E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 0 7 ; 1 1 4 ; 3 7 0 M n ¼ ∂ðMLPðPoolðXÞÞÞ; (7) where ∂ represents the ReLU activation function, MLP the multilayer perceptron, and Pool the adaptive pooling operation. In the SPA module, the new feature map Y is pooled to obtain the channel map for stitching, and the spatial weight coefficient M s is obtained after 3 Ã 3 layer convolution and ReLU activation function, and the product of M s and the feature map Y is used as the output feature map Z.…”

Section: Design Of Ud-yolov5s Networkmentioning

confidence: 99%

“…This improvement is achieved by introducing additional layers and convolutional kernels to improve feature extraction and understanding while utilizing the cross-entropy loss function to refine predictions for different targets. YOLOv5s has gained widespread adoption across various domains, including intelligent surveillance, smart agriculture, and automated monitoring, due to its exceptional accuracy, rapid processing capabilities, and real-time detection and tracking of multiple objects 7 …”

Section: Introductionmentioning

confidence: 99%

“…YOLOv5s has gained widespread adoption across various domains, including intelligent surveillance, smart agriculture, and automated monitoring, due to its exceptional accuracy, rapid processing capabilities, and real-time detection and tracking of multiple objects. 7 This paper introduces upper and lower you only look once version 5 small (UD-YOLOv5s), an innovative method for recognizing cattle rumination behavior based on extracting upper and lower jaw skeleton features using the YOLOv5s network. This work is the first to combine the YOLOv5s network with upper and lower jaw skeleton features for cattle rumination behavior recognition.…”

mentioning

confidence: 99%

See 1 more Smart Citation

UD-YOLOv5s: Recognition of cattle regurgitation behavior based on upper and lower jaw skeleton feature extraction

Gao,

Wang,

Wang

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

Rumination plays a pivotal role in assessing the health status of ruminants. However, conventional contact devices such as ear tags and pressure sensors raise animal welfare concerns during rumination behavior detection. Deep learning offers a promising solution for non-contact rumination recognition by training neural networks on datasets. We introduce UD-YOLOv5s, an approach for bovine rumination recognition that incorporates jaw skeleton feature extraction techniques. Initially, a skeleton feature extraction method is proposed for the upper and lower jaws, employing skeleton heatmap descriptors and the Kalman filter algorithm. Subsequently, the UD-YOLOv5s method is developed for rumination recognition. To optimize the UD-YOLOv5s model, the traditional intersection over the union loss function is replaced with the generalized one. A self-built bovine rumination dataset is used to compare the performance of three deep learning techniques: mean shift algorithm, mask region-based convolutional neural network, and you only look once version 3 (YOLOv3). The results of the ablation experiment demonstrate that UD-YOLOv5s achieves impressive precision (98.25%), recall (97.75%), and a mean average precision of 93.43%. We conducted a generalization performance evaluation in a controlled experimental environment to ensure fairness, indicating that UD-YOLOv5s converges faster than other models while maintaining comparable recognition accuracy. Moreover, our work reveals that when convergence speed is equal, UD-YOLOv5s outperforms other models regarding recognition accuracy. These findings provide robust support for accurately identifying cattle rumination behavior, showcasing the potential of the UD-YOLOv5s method in advancing ruminant health assessment.

show abstract

Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis

Dulal,

Zheng,

Kabir

et al. 2022

2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

Individual identification model and method for estimating social rank among herd of dairy cows using YOLOv5

Cited by 4 publications

References 6 publications

Optimizing Cattle Behavior Analysis in Precision Livestock Farming: Integrating YOLOv7-E6E with AutoAugment and GridMask to Enhance Detection Accuracy

Optimizing Cattle Behavior Analysis in Precision Livestock Farming: Integrating YOLOv7-E6E with AutoAugment and GridMask to Enhance Detection Accuracy

UD-YOLOv5s: Recognition of cattle regurgitation behavior based on upper and lower jaw skeleton feature extraction

Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis

Contact Info

Product

Resources

About