Automatic scoring of postures in grouped pigs using depth image and CNN-SVM

Xu, Jinyang; Zhou, Suyin; Xu, Aijun; Ye, Junhua; Zhao, Ayong

doi:10.1016/j.compag.2022.106746

Cited by 27 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their efficacy in automated porcine cough event identification has been well-documented [ 38 ]. Secondly, the shallow CNN architecture proves well-matched for feature extraction from thermal images [ 39 ]. The amalgamation of this architecture with SVM classification engenders highly accurate classification outcomes while significantly boosting execution speed [ 40 ].…”

Section: Methodsmentioning

confidence: 99%

Heterogeneous fusion of biometric and deep physiological features for accurate porcine cough recognition

Wang,

Qi,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Accurate identification of porcine cough plays a vital role in comprehensive respiratory health monitoring and diagnosis of pigs. It serves as a fundamental prerequisite for stress-free animal health management, reducing pig mortality rates, and improving the economic efficiency of the farming industry. Creating a representative multi-source signal signature for porcine cough is a crucial step toward automating its identification. To this end, a feature fusion method that combines the biological features extracted from the acoustic source segment with the deep physiological features derived from thermal source images is proposed in the paper. First, acoustic features from various domains are extracted from the sound source signals. To determine the most effective combination of sound source features, an SVM-based recursive feature elimination cross-validation algorithm (SVM-RFECV) is employed. Second, a shallow convolutional neural network (named ThermographicNet) is constructed to extract deep physiological features from the thermal source images. Finally, the two heterogeneous features are integrated at an early stage and input into a support vector machine (SVM) for porcine cough recognition. Through rigorous experimentation, the performance of the proposed fusion approach is evaluated, achieving an impressive accuracy of 98.79% in recognizing porcine cough. These results further underscore the effectiveness of combining acoustic source features with heterogeneous deep thermal source features, thereby establishing a robust feature representation for porcine cough recognition.

show abstract

Section: Methodsmentioning

confidence: 99%

Heterogeneous fusion of biometric and deep physiological features for accurate porcine cough recognition

Wang,

Qi,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The core of intelligent damage assessment based on CV and AR is to perceive information in real time and respond according to the target task [43]. According to research and practical experience in the literature [44][45][46], this paper selected the CNN as the deep learning algorithm to complete intelligent damage assessment.…”

Section: Cnn In the Damage Assessment Of Post-earthquake Buildingsmentioning

confidence: 99%

Intelligent Damage Assessment for Post-Earthquake Buildings Using Computer Vision and Augmented Reality

et al. 2023

View full text Add to dashboard Cite

The most negative effects caused by earthquakes are the damage and collapse of buildings. Seismic building retrofitting and repair can effectively reduce the negative impact on post-earthquake buildings. The priority to repair the construction after being damaged by an earthquake is to perform an assessment of seismic buildings. The traditional damage assessment method is mainly based on visual inspection, which is highly subjective and has low efficiency. To improve the intelligence of damage assessments for post-earthquake buildings, this paper proposed an assessment method using CV (Computer Vision) and AR (Augmented Reality). Firstly, this paper proposed a fusion mechanism for the CV and AR of the assessment method. Secondly, the CNN (Convolutional Neural Network) algorithm and gray value theory are used to determine the damage information of post-earthquake buildings. Then, the damage assessment can be visually displayed according to the damage information. Finally, this paper used a damage assessment case of seismic-reinforced concrete frame beams to verify the feasibility and effectiveness of the proposed assessment method.

show abstract

“…There is thus a strong need for a method that can effectively predict animal weight in natural farm settings and conditions. In recent days 3D deep learning methods have been studied for precision livestock farming such as identification [ 23 ], posture classification [ 24 ], and weight prediction [ 25 , 26 ] as they are robust even with changes in posture and lighting conditions. However, these methods have yet to be tested in commercial farms.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Models to Predict Finishing Pig Weight Using Point Clouds

Paudel,

de Sousa,

Sharma

et al. 2023

Animals

View full text Add to dashboard Cite

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.

show abstract

Automatic scoring of postures in grouped pigs using depth image and CNN-SVM

Cited by 27 publications

References 45 publications

Heterogeneous fusion of biometric and deep physiological features for accurate porcine cough recognition

Heterogeneous fusion of biometric and deep physiological features for accurate porcine cough recognition

Intelligent Damage Assessment for Post-Earthquake Buildings Using Computer Vision and Augmented Reality

Deep Learning Models to Predict Finishing Pig Weight Using Point Clouds

Contact Info

Product

Resources

About