Abstract
How to realize the accurate recognition of 3 parts of sheep carcass is the key to the research of mutton cutting robots. The characteristics of each part of the sheep carcass are connected to each other and have similar features, which make it difficult to identify and detect, but with the development of image semantic segmentation technology based on deep learning, it is possible to explore this technology for real-time recognition of the 3 parts of the sheep carcass. Based on the ICNet, we propose a real-time semantic segmentation method for sheep carcass images. We first acquire images of the sheep carcass and use augmentation technology to expand the image data, after normalization, using LabelMe to annotate the image and build the sheep carcass image dataset. After that, we establish the ICNet model and train it with transfer learning. The segmentation accuracy, MIoU, and the average processing time of single image are then obtained and used as the evaluation standard of the segmentation effect. In addition, we verify the generalization ability of the ICNet for the sheep carcass image dataset by setting different brightness image segmentation experiments. Finally, the U-Net, DeepLabv3, PSPNet, and Fast-SCNN are introduced for comparative experiments to further verify the segmentation performance of the ICNet. The experimental results show that for the sheep carcass image datasets, the segmentation accuracy and MIoU of our method are 97.68% and 88.47%, respectively. The single image processing time is 83 ms. Besides, the MIoU of U-Net and DeepLabv3 is 0.22% and 0.03% higher than the ICNet, but the processing time of a single image is longer by 186 ms and 430 ms. Besides, compared with the PSPNet and Fast-SCNN, the MIoU of the ICNet model is increased by 1.25% and 4.49%, respectively. However, the processing time of a single image is shorter by 469 ms and expands by 7 ms, respectively.
Highlights
Mutton is the fourth largest meat consumer product in the world, and its demand is increasing with the adjustment of people’s dietary structure
F2 uses 1 × 1 dilated convs to ensure that it has the same output size as F1, fuses the output features from the F1 branch through the batch normalization layer, and obtains F2′ with the same resolution as F2 through the ReLU nonlinear activation function, leaving it ready for the level. e effect of cascaded tags is to strengthen the learning of F1, to optimize the softmax cross-entropy, and obtain a new loss value to update the model weight. e structure of cascade feature fusion (CFF) unit is shown in Figure 5 [25]
In order to quantitatively analyze the performance of the ICNet model in semantic segmentation of the sheep carcass image dataset, we introduce the PA and MIoU
Summary
Received 2 September 2020; Revised 17 March 2021; Accepted 9 April 2021; Published 20 April 2021. E characteristics of each part of the sheep carcass are connected to each other and have similar features, which make it difficult to identify and detect, but with the development of image semantic segmentation technology based on deep learning, it is possible to explore this technology for real-time recognition of the 3 parts of the sheep carcass. Based on the ICNet, we propose a real-time semantic segmentation method for sheep carcass images. The U-Net, DeepLabv, PSPNet, and Fast-SCNN are introduced for comparative experiments to further verify the segmentation performance of the ICNet. e experimental results show that for the sheep carcass image datasets, the segmentation accuracy and MIoU of our method are 97.68% and 88.47%, respectively. The MIoU of U-Net and DeepLabv is 0.22% and 0.03% higher than the ICNet, but the processing time of a single image is longer by 186 ms and 430 ms. The processing time of a single image is shorter by 469 ms and expands by 7 ms, respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
