High-accuracy image segmentation for lactating sows using a fully convolutional network

Yang, Aqing; Huang, Huasheng; Zheng, Changqing; Zhu, Xunmu; Yang, Xin‐She; Chen, Pengfei; Xue, Yong

doi:10.1016/j.biosystemseng.2018.10.005

Cited by 26 publications

(15 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for enhancement in spatial domain, manipulations in histograms are commonly used to improve brightness and contrast of an image. Examples include histogram equalization [ 73 , 121 ], adaptive histogram equalization [ 52 , 67 ], and contrast limited adaptive histogram equalization [ 70 , 89 , 122 ]. Other intensity transformation methods (e.g., adaptive segmented stretching, adaptive nonlinear S-curve transform, and weighted fusion) were also used to enhance the intensities or intensity changes in images [ 53 ].…”

Section: Preparationsmentioning

confidence: 99%

“…The DeepLab [ 200 ], UNet [ 198 ], and Mask R-CNN [ 38 ] were applied in animal farming quite often because of their optimized architectures and performance as mentioned above. Combining segmentation models with simple image processing algorithms (e.g., FCN + Otsu thresholding [ 67 ]) can be helpful in dealing with complex environments in animal farming. Sometimes, such a combination can be simplified via using lightweight object detection models (e.g., YOLO) to detect objects of concern and simple image processing algorithms (e.g., thresholding) to segment objects enclosed in bounding boxes [ 82 , 208 ].…”

Section: Convolutional Neural Network Architecturesmentioning

confidence: 99%

“…[200] Atrous convolution, field of view, ASPP, fully-connected CRF, sampling rate Bitbucket [203] (Caffe) [62,105,111] ERFNet [201] Residual connection, factorized convolution, high speed with remarkable accuracy, 83 fps GitHub [204] (PyTorch) [112] FCIS [199] Position-sensitive inside/outside score map, object classification, and instance segmentation jointly GitHub [205] (MXNet) [93] FCN8s [197] Classification networks as backbones, fully convolutional network, 8-pixel stride GitHub [206] (PyTorch) [93] UNet [198] Data The DeepLab [200], UNet [198], and Mask R-CNN [38] were applied in animal farming quite often because of their optimized architectures and performance as mentioned above. Combining segmentation models with simple image processing algorithms (e.g., FCN + Otsu thresholding [67]) can be helpful in dealing with complex environments in animal farming. Sometimes, such a combination can be simplified via using lightweight object detection models (e.g., YOLO) to detect objects of concern and simple image processing algorithms (e.g., thresholding) to segment objects enclosed in bounding boxes [82,208].…”

Section: Architectures For Semantic/instance Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

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

Huang

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

Convolutional neural network (CNN)-based computer vision systems have been increasingly applied in animal farming to improve animal management, but current knowledge, practices, limitations, and solutions of the applications remain to be expanded and explored. The objective of this study is to systematically review applications of CNN-based computer vision systems on animal farming in terms of the five deep learning computer vision tasks: image classification, object detection, semantic/instance segmentation, pose estimation, and tracking. Cattle, sheep/goats, pigs, and poultry were the major farm animal species of concern. In this research, preparations for system development, including camera settings, inclusion of variations for data recordings, choices of graphics processing units, image preprocessing, and data labeling were summarized. CNN architectures were reviewed based on the computer vision tasks in animal farming. Strategies of algorithm development included distribution of development data, data augmentation, hyperparameter tuning, and selection of evaluation metrics. Judgment of model performance and performance based on architectures were discussed. Besides practices in optimizing CNN-based computer vision systems, system applications were also organized based on year, country, animal species, and purposes. Finally, recommendations on future research were provided to develop and improve CNN-based computer vision systems for improved welfare, environment, engineering, genetics, and management of farm animals.

show abstract

Section: Preparationsmentioning

confidence: 99%

Section: Convolutional Neural Network Architecturesmentioning

confidence: 99%

Section: Architectures For Semantic/instance Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

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

Huang

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…A clustering validation method was adapted to design a clustering stability, to automatically segment images was designed and proposed in [11] and their results were good. In [12] the authors have included two steps. As the first step, lactating sows were segmented using top‐view images using a fully‐connected convolution network.…”

Section: Literature Reviewmentioning

confidence: 99%

Segmentation using fuzzy cluster‐based thresholding method for apple fruit sorting

Henila

Chithra

2020

IET image process

View full text Add to dashboard Cite

Apple fruit sorting has been an important postharvest process carried on for the sorting of diseased apple fruits. A fuzzy cluster-based thresholding (FCBT) method for segmenting the region of interest from an apple image has been proposed for sorting apples in this study. As the first step, the acquired RGB colour image of an apple fruit was converted into a greyscale image. Then, five different fuzzy cluster bins with overlapped pixel ranges were taken and greypixel values were binned into them. A cluster with the maximum number of pixels was selected for calculating the threshold value. The region of interest from the apple image was then segmented using the proposed FCBT value. Features extracted from the segmented images were given as input to a fully-connected deep neural network for a classification. The performance of the FCBT method was compared with similar greyscale thresholding methods like Otsu's and Kapur's methods. The visual segmentation accuracy and the execution speed showed that the FCBT outperformed the other methods in segmenting the diseased area. A fullyconnected deep neural network model with the FCBT image extracted features as input values gave a 98.33% accuracy rate in sorting the apple images. 10 IET Image Process.

show abstract

“…Their proposed method was able to recognise pigs’ feeding behaviours with an accuracy of 99.6% during the study. Segmentation of sow images from background in top view 2D images was also addressed by means of Fully Convolutional Network (FCN), built in Visual Geometry Group Network with 16 layers (VGG16), in another study by [19]. Their results showed the possibility of employing deep learning approaches for segmentation of the animal from different background conditions.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning and Machine Vision Approaches for Posture Detection of Individual Pigs

Nasirahmadi

Sturm

Edwards

et al. 2019

Sensors

108

View full text Add to dashboard Cite

Posture detection targeted towards providing assessments for the monitoring of health and welfare of pigs has been of great interest to researchers from different disciplines. Existing studies applying machine vision techniques are mostly based on methods using three-dimensional imaging systems, or two-dimensional systems with the limitation of monitoring under controlled conditions. Thus, the main goal of this study was to determine whether a two-dimensional imaging system, along with deep learning approaches, could be utilized to detect the standing and lying (belly and side) postures of pigs under commercial farm conditions. Three deep learning-based detector methods, including faster regions with convolutional neural network features (Faster R-CNN), single shot multibox detector (SSD) and region-based fully convolutional network (R-FCN), combined with Inception V2, Residual Network (ResNet) and Inception ResNet V2 feature extractions of RGB images were proposed. Data from different commercial farms were used for training and validation of the proposed models. The experimental results demonstrated that the R-FCN ResNet101 method was able to detect lying and standing postures with higher average precision (AP) of 0.93, 0.95 and 0.92 for standing, lying on side and lying on belly postures, respectively and mean average precision (mAP) of more than 0.93.

show abstract

High-accuracy image segmentation for lactating sows using a fully convolutional network

Cited by 26 publications

References 25 publications

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

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

Segmentation using fuzzy cluster‐based thresholding method for apple fruit sorting

Deep Learning and Machine Vision Approaches for Posture Detection of Individual Pigs

Contact Info

Product

Resources

About