Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera

Intelligent weight prediction of cows based on semantic segmentation and back propagation neural network

Accurate prediction of cattle weight is essential for enhancing the efficiency and sustainability of livestock management practices. However, conventional methods often involve labor-intensive procedures and lack instant and non-invasive solutions. This study proposed an intelligent weight prediction approach for cows based on semantic segmentation and Back Propagation (BP) neural network. The proposed semantic segmentation method leveraged a hybrid model which combined ResNet-101-D with the Squeeze-and-Excitation (SE) attention mechanism to obtain precise morphological features from cow images. The body size parameters and physical measurements were then used for training the regression-based machine learning models to estimate the weight of individual cattle. The comparative analysis methods revealed that the BP neural network achieved the best results with an MAE of 13.11 pounds and an RMSE of 22.73 pounds. By eliminating the need for physical contact, this approach not only improves animal welfare but also mitigates potential risks. The work addresses the specific needs of welfare farming and aims to promote animal welfare and advance the field of precision agriculture.

Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision

Computer vision (CV), a non-intrusive and cost-effective technology, has furthered the development of precision livestock farming by enabling optimized decision-making through timely and individualized animal care. The availability of affordable two- and three-dimensional camera sensors, combined with various machine learning and deep learning algorithms, has provided a valuable opportunity to improve livestock production systems. However, despite the availability of various CV tools in the public domain, applying these tools to animal data can be challenging, often requiring users to have programming and data analysis skills, as well as access to computing resources. Moreover, the rapid expansion of precision livestock farming is creating a growing need to educate and train animal science students in CV. This presents educators with the challenge of efficiently demonstrating the complex algorithms involved in CV. Thus, the objective of this study was to develop ShinyAnimalCV, an open-source cloud-based web application designed to facilitate CV teaching in animal science. This application provides a user-friendly interface for performing CV tasks, including object segmentation, detection, three-dimensional surface visualization, and extraction of two- and three-dimensional morphological features. Nine pre-trained CV models using top-view animal data are included in the application. ShinyAnimalCV has been deployed online using cloud computing platforms. The source code of ShinyAnimalCV is available on GitHub, along with detailed documentation on training CV models using custom data and deploying ShinyAnimalCV locally to allow users to fully leverage the capabilities of the application. ShinyAnimalCV can help to support the teaching of CV, thereby laying the groundwork to promote the adoption of CV in the animal science community.

Deep Learning Models to Predict Finishing Pig Weight Using Point Clouds

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.

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.

A state-of-the-art review of image motion deblurring techniques in precision agriculture

Image motion deblurring is a crucial technology in computer vision that has gained significant attention attracted by its outstanding ability for accurate acquisition of motion image information, processing and intelligent decision making, etc. Motion blur has recently been considered as one of the major challenges for applications of computer vision in precision agriculture. Motion blurred images seriously affect the accuracy of information acquisition in precision agriculture scene image such as testing, tracking, and behavior analysis of animals, recognition of plant phenotype, critical characteristics of pests and diseases, etc. On the other hand, the fast motion and irregular deformation of agriculture livings, and motion of image capture device all introduce great challenges for image motion deblurring. Hence, the demand of more efficient image motion deblurring method is rapidly increasing and developing in the applications with dynamic scene. Up till now, some studies have been carried out to address this challenge, e.g., spatial motion blur, multi-scale blur and other types of blur. This paper starts with categorization of causes of image blur in precision agriculture. Then, it gives detail introduction of general-purpose motion deblurring methods and their the strengthen and weakness. Furthermore, these methods are compared for the specific applications in precision agriculture e.g., detection and tracking of livestock animal, harvest sorting and grading, and plant disease detection and phenotyping identification etc. Finally, future research directions are discussed to push forward the research and application of advancing in precision agriculture image motion deblurring field.

Automated acquisition of top-view dairy cow depth image data using an RGB-D sensor camera

Animal dimensions are essential indicators for monitoring their growth rate, diet efficiency, and health status. A computer vision system is a recently emerging precision livestock farming technology that overcomes the previously unresolved challenges pertaining to labor and cost. Depth sensor cameras can be used to estimate the depth or height of an animal, in addition to two-dimensional information. Collecting top-view depth images is common in evaluating body mass or conformational traits in livestock species. However, in the depth image data acquisition process, manual interventions are involved in controlling a camera from a laptop or where detailed steps for automated data collection are not documented. Furthermore, open-source image data acquisition implementations are rarely available. The objective of this study was to 1) investigate the utility of automated top-view dairy cow depth data collection methods using picture- and video-based methods, 2) evaluate the performance of an infrared cut lens, 3) and make the source code available. Both methods can automatically perform animal detection, trigger recording, capture depth data, and terminate recording for individual animals. The picture-based method takes only a predetermined number of images whereas the video-based method uses a sequence of frames as a video. For the picture-based method, we evaluated 3- and 10-picture approaches. The depth sensor camera was mounted 2.75 m above-the-ground over a walk-through scale between the milking parlor and the free-stall barn. A total of 150 Holstein and 100 Jersey cows were evaluated. A pixel location where the depth was monitored was set up as a point of interest. More than 89% of cows were successfully captured using both picture- and video-based methods. The success rates of the picture- and video-based methods further improved to 92% and 98%, respectively, when combined with an infrared cut lens. Although both the picture-based method with 10 pictures and the video-based method yielded accurate results for collecting depth data on cows, the former was more efficient in terms of data storage. The current study demonstrates automated depth data collection frameworks and a Python implementation available to the community, which can help facilitate the deployment of computer vision systems for dairy cows.

VTag: a Semi-Supervised Pipeline for Tracking Pig Activity with a Single Top-View Camera

Precision livestock farming has become an important research focus with the rising demand of meat production in the swine industry. Currently, the farming practice is widely conducted by the technology of computer vision (CV), which automates monitoring pig activity solely based on video recordings. Automation is fulfilled by deriving imagery features that can guide CV systems to recognize animals' body contours, positions, and behavioral categories. Nevertheless, the performance of the CV systems is sensitive to the quality of imagery features. When the CV system is deployed in a variable environment, its performance may decrease as the features are not generalized enough under different illumination conditions. Moreover, most CV systems are established by supervised learning, in which intensive effort in labeling ground truths for the training process is required. Hence, a semi-supervised pipeline, VTag, is developed in this study. The pipeline focuses on long-term tracking of pig activity without requesting any pre-labeled video but a few human supervisions to build a CV system. The pipeline can be rapidly deployed as only one top-view RGB camera is needed for the tracking task. Additionally, the pipeline was released as a software tool with a friendly graphical interface available to general users. Among the presented datasets, the average tracking error was 17.99 centimeters. Besides, with the prediction results, the pig moving distance per unit time can be estimated for activity studies. Lastly, as the motion is monitored, a heat map showing spatial hot spots visited by the pigs can be useful guidance for farming management. The presented pipeline saves massive laborious work in preparing training dataset. The rapid deployment of the tracking system paves the way for pig behavior monitoring.