A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A Novel Multi-Scale Attention PFE-UNet for Forest Image Segmentation
The precise segmentation of forest areas is essential for monitoring tasks related to forest exploration, extraction, and statistics. However, the effective and accurate segmentation of forest images will be affected by factors such as blurring and discontinuity of forest boundaries. Therefore, a Pyramid Feature Extraction-UNet network (PFE-UNet) based on traditional UNet is proposed to be applied to end-to-end forest image segmentation. Among them, the Pyramid Feature Extraction module (PFE) is introduced in the network transition layer, which obtains multi-scale forest image information through different receptive fields. The spatial attention module (SA) and the channel-wise attention module (CA) are applied to low-level feature maps and PFE feature maps, respectively, to highlight specific segmentation task features while fusing context information and suppressing irrelevant regions. The standard convolution block is replaced by a novel depthwise separable convolutional unit (DSC Unit), which not only reduces the computational cost but also prevents overfitting. This paper presents an extensive evaluation with the DeepGlobe dataset and a comparative analysis with several state-of-the-art networks. The experimental results show that the PFE-UNet network obtains an accuracy of 94.23% in handling the real-time forest image segmentation, which is significantly higher than other advanced networks. This means that the proposed PFE-UNet also provides a valuable reference for the precise segmentation of forest images.
A Novel Multi-Scale Attention PFE-UNet for Forest Image Segmentation
The precise segmentation of forest areas is essential for monitoring tasks related to forest exploration, extraction, and statistics. However, the effective and accurate segmentation of forest images will be affected by factors such as blurring and discontinuity of forest boundaries. Therefore, a Pyramid Feature Extraction-UNet network (PFE-UNet) based on traditional UNet is proposed to be applied to end-to-end forest image segmentation. Among them, the Pyramid Feature Extraction module (PFE) is introduced in the network transition layer, which obtains multi-scale forest image information through different receptive fields. The spatial attention module (SA) and the channel-wise attention module (CA) are applied to low-level feature maps and PFE feature maps, respectively, to highlight specific segmentation task features while fusing context information and suppressing irrelevant regions. The standard convolution block is replaced by a novel depthwise separable convolutional unit (DSC Unit), which not only reduces the computational cost but also prevents overfitting. This paper presents an extensive evaluation with the DeepGlobe dataset and a comparative analysis with several state-of-the-art networks. The experimental results show that the PFE-UNet network obtains an accuracy of 94.23% in handling the real-time forest image segmentation, which is significantly higher than other advanced networks. This means that the proposed PFE-UNet also provides a valuable reference for the precise segmentation of forest images.
A Novel Multi-Scale Attention PFE-UNet for Forest Image Segmentation
Boyang Zhang (author) / Hongbo Mu (author) / Mingyu Gao (author) / Haiming Ni (author) / Jianfeng Chen (author) / Hong Yang (author) / Dawei Qi (author)
2021
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Concatenated Residual Attention UNet for Semantic Segmentation of Urban Green Space
| DOAJ | 2021
MD-UNet: a medical image segmentation network based on mixed depthwise convolution
| Springer Verlag | 2024
Crack segmentation method and device based on Res-Unet multipath image feature multiplexing
| European Patent Office | 2024
Retinal vessel segmentation method based on RSP-SA Unet network
| Springer Verlag | 2024