Multiscale depthwise separable convolution based network for high-resolution image segmentation

Zhang, Ke; Bello, Inuwa Mamuda; Su, Yu; Wang, Jingyu; Maryam, Ibrahim

doi:10.1080/01431161.2022.2142081

Cited by 5 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach iterates 16 times in the middle flow [ 38 ]. Depthwise separable convolutions streamline the convolution process by first executing spatial convolutions independently for each input channel, followed by a 1 × 1 convolution that fuses the channels [ 39 , 40 ]. This stratification minimizes parameters, boosting both the efficiency and the ability of the network to extract relevant features from colored steel buildings.…”

Section: Methodsmentioning

confidence: 99%

A Triplet Network Fusing Optical and SAR Images for Colored Steel Building Extraction

Zhang,

Yang,

Yang

et al. 2023

Sensors

View full text Add to dashboard Cite

The identification of colored steel buildings in images is crucial for managing the construction sector, environmental protection, and sustainable urban development. Current deep learning methods for optical remote sensing images often encounter challenges such as confusion between the roof color or shape of regular buildings and colored steel structures. Additionally, common semantic segmentation networks exhibit poor generalization and inadequate boundary regularization when extracting colored steel buildings. To overcome these limitations, we utilized the metal detection and differentiation capabilities inherent in synthetic aperture radar (SAR) data to develop a network that integrates optical and SAR data. This network, employing a triple-input structure, effectively captures the unique features of colored steel buildings. We designed a multimodal hybrid attention module in the network that discerns the varying importance of each data source depending on the context. Additionally, a boundary refinement (BR) module was introduced to extract the boundaries of the colored steel buildings in a more regular manner, and a deep supervision strategy was implemented to improve the performance of the network in the colored steel building extraction task. A BR module and deep supervision strategy were also implemented to sharpen the extraction of building boundaries, thereby enhancing the network’s accuracy and adaptability. The results indicate that, compared to mainstream semantic segmentation, this method effectively enhances the precision of colored steel building detection, achieving an accuracy rate of 83.19%. This improvement marks a significant advancement in monitoring illegal constructions and supporting the sustainable development of the Beijing–Tianjin–Hebei metropolitan region.

show abstract

Section: Methodsmentioning

confidence: 99%

A Triplet Network Fusing Optical and SAR Images for Colored Steel Building Extraction

Zhang,

Yang,

Yang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Zhang et al [42] used the transformer architecture to construct CD encoding modules. In addition, Zhang et al [43] used depthwise separable convolution to replace the standard 3×3 convolution kernel, reducing the number of parameters of CD model training. By applying ghost convolution to a multiscale Siamese CNN network architecture, Lei et al [44] improved the network performance and further decreased the number of network parameters.…”

Section: A Feature Extractionmentioning

confidence: 99%

ACMFNet: Asymmetric Convolutional Feature Enhancement and Multiscale Fusion Network for Change Detection

Le,

Huang,

Tang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Research on Field Cotton Yield Prediction System Based on Improved Yolov5 Cotton Detection Model and Android Development

Wang,

et al. 2024

Smart Agriculture

View full text Add to dashboard Cite

Multiscale depthwise separable convolution based network for high-resolution image segmentation

Cited by 5 publications

References 31 publications

A Triplet Network Fusing Optical and SAR Images for Colored Steel Building Extraction

A Triplet Network Fusing Optical and SAR Images for Colored Steel Building Extraction

ACMFNet: Asymmetric Convolutional Feature Enhancement and Multiscale Fusion Network for Change Detection

Research on Field Cotton Yield Prediction System Based on Improved Yolov5 Cotton Detection Model and Android Development

Contact Info

Product

Resources

About