Pig Weight and Body Size Estimation Using a Multiple Output Regression Convolutional Neural Network: A Fast and Fully Automatic Method

Pig Weight Estimation Method Based on a Framework Combining Mask R-CNN and Ensemble Regression Model

Using computer vision technology to estimate pig live weight is an important method to realize pig welfare. But there are two key issues that affect pigs' weight estimation: one is the uneven illumination, which leads to unclear contour extraction of pigs, and the other is the bending of the pig body, which leads to incorrect pig body information. For the first one, Mask R-CNN was used to extract the contour of the pig, and the obtained mask image was converted into a binary image from which we were able to obtain a more accurate contour image. For the second one, the body length, hip width and the distance from the camera to the pig back were corrected by XGBoost and actual measured information. Then we analyzed the rationality of the extracted features. Three feature combination strategies were used to predict pig weight. In total, 1505 back images of 39 pigs obtained using Azure kinect DK were used in the numerical experiments. The highest prediction accuracy is XGBoost, with an MAE of 0.389, RMSE of 0.576, MAPE of 0.318% and R2 of 0.995. We also recommend using the Mask R-CNN + RFR method because it has fairly high precision in each strategy. The experimental results show that our proposed method has excellent performance in live weight estimation of pigs.

Improving Efficiency: Automatic Intelligent Weighing System as a Replacement for Manual Pig Weighing

To verify the accuracy of AIWS, we weighed 106 pen growing-finishing pigs' weights using both the manual and AIWS methods, respectively. Accuracy was evaluated based on the values of MAE, MAPE, and RMSE. In the growth experiment, manual weighing was conducted every two weeks and AIWS predicted weight data was recorded daily, followed by fitting the growth curves. The results showed that MAE, MAPE, and RMSE values for 60 to 120 kg pigs were 3.48 kg, 3.71%, and 4.43 kg, respectively. The correlation coefficient r between the AIWS and manual method was 0.9410, and R2 was 0.8854. The two were extremely significant correlations (p < 0.001). In growth curve fitting, the AIWS method has lower AIC and BIC values than the manual method. The Logistic model by AIWS was the best-fit model. The age and body weight at the inflection point of the best-fit model were 164.46 d and 93.45 kg, respectively. The maximum growth rate was 831.66 g/d. In summary, AIWS can accurately predict pigs' body weights in actual production and has a better fitting effect on the growth curves of growing-finishing pigs. This study suggested that it was feasible for AIWS to replace manual weighing to measure the weight of 50 to 120 kg live pigs in large-scale farming.

Estimation of Weight and Body Measurement Model for Pigs Based on Back Point Cloud Data

Pig farming is a crucial sector in global animal husbandry. The weight and body dimension data of pigs reflect their growth and development status, serving as vital metrics for assessing their progress. Presently, pig weight and body dimensions are predominantly measured manually, which poses challenges such as difficulties in herding, stress responses in pigs, and the control of zoonotic diseases. To address these issues, this study proposes a non-contact weight estimation and body measurement model based on point cloud data from pig backs. A depth camera was installed above a weighbridge to acquire 3D point cloud data from 258 Yorkshire-Landrace crossbred sows. We selected 200 Yorkshire-Landrace sows as the research subjects and applied point cloud filtering and denoising techniques to their three-dimensional point cloud data. Subsequently, a K-means clustering segmentation algorithm was employed to extract the point cloud corresponding to the pigs' backs. A convolutional neural network with a multi-head attention was established for pig weight prediction and added RGB information as an additional feature. During the data processing process, we also measured the back body size information of the pigs. During the model evaluation, 58 Yorkshire-Landrace sows were specifically selected for experimental assessment. Compared to manual measurements, the weight estimation exhibited an average absolute error of 11.552 kg, average relative error of 4.812%, and root mean square error of 11.181 kg. Specifically, for the MACNN, incorporating RGB information as an additional feature resulted in a decrease of 2.469 kg in the RMSE, a decrease of 0.8% in the MAPE, and a decrease of 1.032 kg in the MAE. Measurements of shoulder width, abdominal width, and hip width yielded corresponding average relative errors of 3.144%, 3.798%, and 3.820%. In conclusion, a convolutional neural network with a multi-head attention was established for pig weight prediction, and incorporating RGB information as an additional feature method demonstrated accuracy and reliability for weight estimation and body dimension measurement.

A Method for Obtaining 3D Point Cloud Data by Combining 2D Image Segmentation and Depth Information of Pigs

This paper proposes a method for automatic pig detection and segmentation using RGB-D data for precision livestock farming. The proposed method combines the enhanced YOLOv5s model with the Res2Net bottleneck structure, resulting in improved fine-grained feature extraction and ultimately enhancing the precision of pig detection and segmentation in 2D images. Additionally, the method facilitates the acquisition of 3D point cloud data of pigs in a simpler and more efficient way by using the pig mask obtained in 2D detection and segmentation and combining it with depth information. To evaluate the effectiveness of the proposed method, two datasets were constructed. The first dataset consists of 5400 images captured in various pig pens under diverse lighting conditions, while the second dataset was obtained from the UK. The experimental results demonstrated that the improved YOLOv5s_Res2Net achieved a mAP@0.5:0.95 of 89.6% and 84.8% for both pig detection and segmentation tasks on our dataset, while achieving a mAP@0.5:0.95 of 93.4% and 89.4% on the Edinburgh pig behaviour dataset. This approach provides valuable insights for improving pig management, conducting welfare assessments, and estimating weight accurately.

Individual Pig Identification Using Back Surface Point Clouds in 3D Vision

The individual identification of pigs is the basis for precision livestock farming (PLF), which can provide prerequisites for personalized feeding, disease monitoring, growth condition monitoring and behavior identification. Pig face recognition has the problem that pig face samples are difficult to collect and images are easily affected by the environment and body dirt. Due to this problem, we proposed a method for individual pig identification using three-dimension (3D) point clouds of the pig's back surface. Firstly, a point cloud segmentation model based on the PointNet++ algorithm is established to segment the pig's back point clouds from the complex background and use it as the input for individual recognition. Then, an individual pig recognition model based on the improved PointNet++LGG algorithm was constructed by increasing the adaptive global sampling radius, deepening the network structure and increasing the number of features to extract higher-dimensional features for accurate recognition of different individuals with similar body sizes. In total, 10,574 3D point cloud images of ten pigs were collected to construct the dataset. The experimental results showed that the accuracy of the individual pig identification model based on the PointNet++LGG algorithm reached 95.26%, which was 2.18%, 16.76% and 17.19% higher compared with the PointNet model, PointNet++SSG model and MSG model, respectively. Individual pig identification based on 3D point clouds of the back surface is effective. This approach is easy to integrate with functions such as body condition assessment and behavior recognition, and is conducive to the development of precision livestock farming.

A Pig Mass Estimation Model Based on Deep Learning without Constraint

The body mass of pigs is an essential indicator of their growth and health. Lately, contactless pig body mass estimation methods based on computer vision technology have gained attention thanks to their potential to improve animal welfare and ensure breeders' safety. Nonetheless, current methods require pigs to be restrained in a confinement pen, and no study has been conducted in an unconstrained environment. In this study, we develop a pig mass estimation model based on deep learning, capable of estimating body mass without constraints. Our model comprises a Mask R-CNN-based pig instance segmentation algorithm, a Keypoint R-CNN-based pig keypoint detection algorithm and an improved ResNet-based pig mass estimation algorithm that includes multi-branch convolution, depthwise convolution, and an inverted bottleneck to improve accuracy. We constructed a dataset for this study using images and body mass data from 117 pigs. Our model achieved an RMSE of 3.52 kg on the test set, which is lower than that of the pig body mass estimation algorithm with ResNet and ConvNeXt as the backbone network, and the average estimation speed was 0.339 s·frame^-1 Our model can evaluate the body quality of pigs in real-time to provide data support for grading and adjusting breeding plans, and has broad application prospects.

Identification of body size characteristic points based on the Mask R-CNN and correlation with body weight in Ujumqin sheep

The measurements of body size data not only reflect the physical fitness, carcass structure, excellent growth condition, and developmental relationship among tissues and organs of animals but are also critical indicators to measure the growth and development of sheep. Computer vision-based body size identification is a non-contact and stress-free method. In this study, we analyzed different body size traits (height at wither, body slanting length, chest depth, chest circumference, shank circumference, hip height, shoulder width, and rump width) and the body weight of 332 Ujumqin sheep and significant correlations (P &lt; 0.05) were obtained among all traits in Ujumqin sheep. Except for shoulder width, rump width, and shank circumference, all were positively correlated, and the effect of sex on Ujumqin sheep was highly significant. The main body size indexes affecting the body weight of rams and ewes were obtained through stepwise regression analysis of body size on body weight, in order of chest circumference, body slanting length, rump width, hip height, height at wither, and shoulder width for rams and body slanting length, chest circumference, rump width, hip height, height at wither and shoulder width for ewes. The body slanting length, chest circumference, and hip height of ewes were used to construct prediction equations for the body weight of Ujumqin sheep of different sexes. The model's prediction accuracy was 83.9% for the rams and 79.4% for ewes. Combined with a Mask R-CNN and machine vision methods, recognition models of important body size parameters of Ujumqin sheep were constructed. The prediction errors of body slanting length, height at wither, hip height, and chest circumference were ~5%, chest depth error was 9.63%, and shoulder width, rump width, and shank circumference errors were 14.95, 12.05, and 19.71%, respectively. The results show that the proposed method is effective and has great potential in precision management.

HRST: An Improved HRNet for Detecting Joint Points of Pigs

The body size of pigs is a vital evaluation indicator for growth monitoring and selective breeding. The detection of joint points is critical for accurately estimating pig body size. However, most joint point detection methods focus on improving detection accuracy while neglecting detection speed and model parameters. In this study, we propose an HRNet with Swin Transformer block (HRST) based on HRNet for detecting the joint points of pigs. It can improve model accuracy while significantly reducing model parameters by replacing the fourth stage of parameter redundancy in HRNet with a Swin Transformer block. Moreover, we implemented joint point detection for multiple pigs following two steps: first, CenterNet was used to detect pig posture (lying or standing); then, HRST was used for joint point detection for standing pigs. The results indicated that CenterNet achieved an average precision (AP) of 86.5%, and HRST achieved an AP of 77.4% and a real-time detection speed of 40 images per second. Compared with HRNet, the AP of HRST improved by 6.8%, while the number of model parameters and the calculated amount reduced by 72.8% and 41.7%, respectively. The study provides technical support for the accurate and rapid detection of pig joint points, which can be used for contact-free body size estimation of pigs.

Accuracy of image analysis for linear zoometric measurements in dromedary camels

The present study was designed to verify the effectiveness of the image analysis method for body measurement in dromedary camel compared to manual measurements as a reference method. To achieve this aim, twenty-one linear body measurements were estimated on 59 adult Sahraoui dromedary camels (22 males and 37 females) with a normal clinical condition by using a measuring stick or vernier caliper (standard method). On the other hand, image analysis on profile, front, or behind photographs was processed using Axiovision Software. Overall mean comparison, relative error, variance, Pearson's correlation coefficient, and coefficient of variance showed that the image analysis method was accurate in relation to the manual measurement. Furthermore, image analysis results indicated relevant accuracy (bias correction factor, C_b ≈1) and precision (Pearson ρ ≈1) which were significantly correlated with the results of the reference method (Lin's concordance correlation coefficients r_ccc ≈ 1). According to Bland-Altman upper and lower limits of agreement, the concordance was estimated between 93.22 and 98.3%. Passing-Bablok regression showed a good relationship between the results of the two methods displaying no significant systematic and proportional bias. The image analysis method for linear body measurements in dromedary camel showed results that are in agreement with the manual measuring method. Therefore, the image analysis could be considered a valid tool for camel conformation trait studies.

Identification of Body Size Determination Related Candidate Genes in Domestic Pig Using Genome-Wide Selection Signal Analysis

This study aimed to identify the genes related to the body size of pigs by conducting genome-wide selection analysis (GWSA). We performed a GWSA scan on 50 pigs belonging to four small-bodied pig populations (Diannan small-eared pig, Bama Xiang pig, Wuzhishan pig, and Jeju black pig from South Korea) and 124 large-bodied pigs. We used the genetic parameters of the pairwise fixation index (FST) and π ratio (case/control) to screen candidate genome regions and genes related to body size. The results revealed 47,339,509 high-quality SNPs obtained from 174 individuals, while 280 interacting candidate regions were obtained from the top 1% signal windows of both parameters, along with 187 genes (e.g., ADCK4, AMDHD2, ASPN, ASS1, and ATP6V0C). The results of the candidate gene (CG) annotation showed that a series of CGs (e.g., MSTN, LTBP4, PDPK1, PKMYT1, ASS1, and STAT6) was enriched into the gene ontology terms. Moreover, molecular pathways, such as the PI3K-Akt, HIF-1, and AMPK signaling pathways, were verified to be related to body development. Overall, we identified a series of key genes that may be closely related to the body size of pigs, further elucidating the heredity basis of body shape determination in pigs and providing a theoretical reference for molecular breeding.

A GAN-Augmented Corrosion Prediction Model for Uncoated Steel Plates

The deterioration and damage of aging steel structures have caused huge safety concerns. Corrosion has been identified as a big reason for the deterioration and damage, which causes steel members to lose materials. As a result, the structures’ stiffness and load-bearing capacity will be reduced, which brings economic losses and safety hazards. For the maintenance and repair of steel structures, fast and accurate prediction of corrosion development plays a critical role in numerical simulation analysis, which could save time and costs. In this research, we build a simulation system based on GAN data augmentation with UNet as the generator and MobileNetV2 as the discriminator. The goal is to effectively predict the corrosion behavior of uncoated steel structures over time and under different circumstances. The system can simulate three stages of corrosion based on the dataset collected from experiments. It can also predict the corrosion of steel plates in the next stage. The discriminator of the system can be used to classify the type of steel, the stage of corrosion, and days of corrosion. Based on comparative experiments, our system demonstrates outstanding performance and outperforms the baseline model.