2018
DOI: 10.1016/j.biosystemseng.2018.10.005
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
13
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 26 publications
(15 citation statements)
references
References 25 publications
0
13
0
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%
See 2 more Smart Citations
“…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%
See 1 more Smart Citation
“…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%
“…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%