Deep Learning Models to Predict Finishing Pig Weight Using Point Clouds

Abstract

The selection of animals to be marketed is largely completed by their visual assessment, solely relying on the skill level of the animal caretaker. Real-time monitoring of the weight of farm animals would provide important information for not only marketing, but also for the assessment of health and well-being issues. The objective of this study was to develop and evaluate a method based on 3D Convolutional Neural Network to predict weight from point clouds. Intel Real Sense D435 stereo depth camera placed at 2.7 m height was used to capture the 3D videos of a single finishing pig freely walking in a holding pen ranging in weight between 20–120 kg. The animal weight and 3D videos were collected from 249 Landrace × Large White pigs in farm facilities of the FZEA-USP (Faculty of Animal Science and Food Engineering, University of Sao Paulo) between 5 August and 9 November 2021. Point clouds were manually extracted from the recorded 3D video and applied for modeling. A total of 1186 point clouds were used for model training and validating using PointNet framework in Python with a 9:1 split and 112 randomly selected point clouds were reserved for testing. The volume between the body surface points and a constant plane resembling the ground was calculated and correlated with weight to make a comparison with results from the PointNet method. The coefficient of determination (R2 = 0.94) was achieved with PointNet regression model on test point clouds compared to the coefficient of determination (R2 = 0.76) achieved from the volume of the same animal. The validation RMSE of the model was 6.79 kg with a test RMSE of 6.88 kg. Further, to analyze model performance based on weight range the pigs were divided into three different weight ranges: below 55 kg, between 55 and 90 kg, and above 90 kg. For different weight groups, pigs weighing below 55 kg were best predicted with the model. The results clearly showed that 3D deep learning on point sets has a good potential for accurate weight prediction even with a limited training dataset. Therefore, this study confirms the usability of 3D deep learning on point sets for farm animals’ weight prediction, while a larger data set needs to be used to ensure the most accurate predictions.

An Internet of Things-Based Cluster System for Monitoring Lactating Sows’ Feed and Water Intake

“…With the further development of deep learning, intelligent cameras and recording devices have begun to be used in pig farms. They play an important role in disease monitoring [51], behavior monitoring [52], and video-based weight estimation [53]. The collection and storage of unstructured data such as video and audio also face challenges.…”

Calculating Volume of Pig Point Cloud Based on Improved Poisson Reconstruction

“…Some scholars at home and abroad have used volume as a major parameter for estimating livestock weight. The main approach consists of three steps: the first step is to obtain depth images of the pig's back; the second step is to calculate the pig's volume parameters by combining the back area; the final step is to establish a model using volume, body weight, and other parameters for the purpose of weight estimation [13][14][15][16]. Fu et al [17] approximated the head and torso of a pig as a cone and a cylinder, respectively, thus obtaining a simplified three-dimensional model of a breeding pig.…”

Field Implementation of Precision Livestock Farming: Selected Proceedings from the 2nd U.S. Precision Livestock Farming Conference

“…The USPLF2023 conference featured four primary research topics: Sensors and Sensing in PLF [1][2][3][4][5], Data Management and Algorithm Development [6][7][8], Measuring, Modeling, and Managing of Dynamic Responses [9][10][11][12][13][14], and Societal Impacts of PLF [15,16]. A total of 126 submissions were received for these topics from individuals representing universities, research institutions, and PLF companies from 13 different countries across Africa, Asia, Australia, Europe, North America, and South America.…”