Context Aggregation Network for Semantic Labeling in Aerial Images

Cheng, Wensheng; Yang, Wen; Pan, Youqi; Guo, Haowen; Cheng, Yu

doi:10.1109/icip.2019.8803583

Cited by 7 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [ 40 ] suggests applying a multi-channel attention approach integrated with multi-layer features and residual convolution module for efficient object recognition and location. TreeUNet [ 41 ] uses Tree-CNN block coupled with a concatenating operation to fuse and interchange the information of the feature map so that different parameter information can be shared in the multi-layer neural network.…”

Section: Related Workmentioning

confidence: 99%

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

Shi

Qin

Yun

et al. 2021

Sensors

View full text Add to dashboard Cite

It is essential for researchers to have a proper interpretation of remote sensing images (RSIs) and precise semantic labeling of their component parts. Although FCN(Fully Convolutional Networks)-like deep convolutional network architectures have been widely applied in the perception of autonomous cars, there are still two challenges in the semantic segmentation of RSIs. The first is to identify details in high-resolution images with complex scenes and to solve the class-mismatch issues; the second is to capture the edge of objects finely without being confused by the surroundings. HRNET has the characteristics of maintaining high-resolution representation by fusing feature information with parallel multi-resolution convolution branches. We adopt HRNET as a backbone and propose to incorporate the Class-Oriented Region Attention Module (CRAM) and Class-Oriented Context Fusion Module (CCFM) to analyze the relationships between classes and patch regions and between classes and local or global pixels, respectively. Thus, the perception capability of the model for the detailed part in the aerial image can be enhanced. We leverage these modules to develop an end-to-end semantic segmentation model for aerial images and validate it on the ISPRS Potsdam and Vaihingen datasets. The experimental results show that our model improves the baseline accuracy and outperforms some commonly used CNN architectures.

show abstract

Section: Related Workmentioning

confidence: 99%

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

Shi

Qin

Yun

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In [28], GCN [27] is enhanced with the channel attention module and the domain-specific transfer learning technique. CAN [43] is an encoder-decoder-like architecture with the aggregation of affluent context information and the fusion of attentionbased multi-level features. DCCN [44] introduces a Coord-Conv module to improve the spatial information by putting the coordinate information into feature maps to reduce the loss of spatial features and strengthen the object boundaries.…”

Section: B Semantic Segmentation Of Aerial Imagerymentioning

confidence: 99%

“…These two datasets contain the high-resolution true ortho photo (TOP), the digital surface model (DSM), and the normalized DSM (nDSM) data, with the corresponding ground truth labels. While both DSM and nDSM data are included in the two datasets, we only focused on the raw TOP images in this work, following [40], [43], [46].…”

Section: A Datasetsmentioning

confidence: 99%

CSE-HRNet: A Context and Semantic Enhanced High-Resolution Network for Semantic Segmentation of Aerial Imagery

2020

View full text Add to dashboard Cite

Semantic segmentation of high-resolution aerial images is a concerning issue of remote sensing applications. To address the issues of intra-class heterogeneity and inter-class homogeneity, a novel end-to-end semantic segmentation network, namely Context and Semantic Enhanced High-Resolution Network (CSE-HRNet), is proposed in this paper. Two procedures are considered comprehensively, which are multi-scale contextual feature extractor and multi-level semantic feature producer. Nested Dilated Residual Block (NDRB) is designed firstly, which could enhance the representational power of multi-scale contexts and tackle the issue of intra-class heterogeneity. The pyramidal feature hierarchy is introduced secondly, by which multi-level feature fusions could be utilized to enlarge inter-class semantic differences. Experimental results verify that, based on the Potsdam and Vaihingen benchmarks, the proposed CSE-HRNet can achieve competitive performance compared with other state-of-the-art methods. INDEX TERMS Semantic segmentation, image analysis, machine learning, remote sensing image.

show abstract

“…The cascaded convolutional neural networks [10,4] were utilized for the segmentation of remote sensing images by successively aggregating contexts. Most recently, many multiscale context-augmented models [12,13,14] have been proposed to exploit contextual information in remote sensing images. Remote sensing target segmentation problems such as object occlusion, geometric size diversity, and small objects have attracted increasing research attention [15,16,17,18].…”

Section: Review Of Semantic Segmentation Of High-resolution Remote Se...mentioning

confidence: 99%

Attention-Based Pyramid Network for Segmentation and Classification of High-Resolution and Hyperspectral Remote Sensing Images

Yuan²,

Ouyang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Unlike conventional natural (RGB) images, the inherent large scale and complex structuresof remote sensing images pose major challenges such as spatial object distribution diversity andspectral information extraction when existing models are directly applied for image classification.In this study, we develop an attention-based pyramid network for segmentation and classificationof remote sensing datasets. Attention mechanisms are used to develop the following modules: (i) anovel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectralinformation at different and same scales; (ii) a region pyramid attention mechanism using region-basedattention addresses the target geometric size diversity in large-scale remote sensing images; and(iii) cross-scale attention in our adaptive atrous spatial pyramid pooling network adapts to variedcontents in a feature-embedded space. Different forms of feature fusion pyramid frameworks areestablished by combining these attention-based modules. First, a novel segmentation framework,called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address thespatial problem of high-resolution remote sensing images. Second, an end-to-end spatial-spectralFFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingenand ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracyachieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the IndianPines and the University of Pavia hyperspectral datasets indicate that the proposed spatial-spectralFFPNet outperforms the current state-of-the-art methods in hyperspectral image classification.

show abstract

Context Aggregation Network for Semantic Labeling in Aerial Images

Cited by 7 publications

References 17 publications

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

CSE-HRNet: A Context and Semantic Enhanced High-Resolution Network for Semantic Segmentation of Aerial Imagery

Attention-Based Pyramid Network for Segmentation and Classification of High-Resolution and Hyperspectral Remote Sensing Images

Contact Info

Product

Resources

About