Automatic monitoring system for individual dairy cows based on a deep learning framework that provides identification via body parts and estimation of body condition score

Abstract

Body condition score (BCS) is a common tool for indirectly estimating the mobilization of energy reserves in the fat and muscle of cattle that meets the requirements of animal welfare and precision livestock farming for the effective monitoring of individual animals. However, previous studies on automatic BCS systems have used manual scoring for data collection, and traditional image extraction methods have limited model performance accuracy. In addition, the radio frequency identification device system commonly used in ranching has the disadvantages of misreadings and damage to bovine bodies. Therefore, the aim of this research was to develop and validate an automatic system for identifying individuals and assessing BCS using a deep learning framework. This work developed a linear regression model of BCS using ultrasound backfat thickness to determine BCS for training sets and tested a system based on convolutional neural networks with 3 channels, including depth, gray, and phase congruency, to analyze the back images of 686 cows. After we performed an analysis of image model performance, online verification was used to evaluate the accuracy and precision of the system. The results showed that the selected linear regression model had a high coefficient of determination value (0.976), and the correlation coefficient between manual BCS and ultrasonic BCS was 0.94. Although the overall accuracy of the BCS estimations was high (0.45, 0.77, and 0.98 within 0, 0.25, and 0.5 unit, respectively), the validation for actual BCS ranging from 3.25 to 3.5 was weak (the F1 scores were only 0.6 and 0.57, respectively, within the 0.25-unit range). Overall, individual identification and BCS assessment performed well in the online measurement , with accuracies of 0.937 and 0.409, respectively. A system for individual identification and BCS assessment was developed, and a convolutional neural network using depth, gray, and phase congruency channels to interpret image features exhibited advantages for monitoring thin cows.

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

“…Jiang et al [ 87 ] further classified cows’ heads, backs, and legs from images by training a FLYOLOv3 model; they achieved an accuracy of 99.18%, a recall rate of 97.51%, and an average precision of 93.73%. Particularly, the combination of animal identification with additional algorithms, such as the combination with BCS, offers novel ways of using physiological and behavioral traits for management decisions [ 40 ]. The capabilities of neural networks are expanding rapidly, as shown by Salau et al [ 88 ] that were able to implement social network analysis from dairy cows by analyzing video data from multiple cameras.…”

Practices and Applications of Convolutional Neural Network-Based Computer Vision Systems in Animal Farming: A Review

“…An RGB image contains three channels and reflects abundant features in color spaces. However, lighting conditions in farms are complex and diverse, and color-space patterns learned from development datasets may not be matched to those in real applications, which may lead to poor generalization performance [115]. One solution was to convert RGB images (three channels) into grayscale images (one channel) [48,55,70,88,116], so that attention of models can be diverted from object colors to learning patterns of objects.…”

Smart Farming Becomes Even Smarter With Deep Learning—A Bibliographical Analysis

“…Kvam and Kongsro [49] proposed a method for estimating the IMF on ultrasound images. A noninvasive in vivo method, constructed using deep CNNs, by (Huang et al [50] and Yukun et al [51] provided a lowcost method based on machine vision and deep learning for evaluation of body condition scores. Zhang et al [52] proposed a real-time sow behavior detection algorithm based on deep learning.…”

“…The finding of improved model performance for thin cows with the addition of phase congruency and gray channels in a CNN suggests that a minor improvement in the average accuracy may be achievable within the absolute accuracy error range. [51] "A computer vision system to monitor the infestation level of Varroa destructor in a honeybee colony" Determine the number of bees and mites A Computer vision system for monitoring the infestation level of the Varroa destructor mite…”