Weighted Collaborative Sparse and <i>L</i>
                  <sub>1/2</sub> Low-Rank Regularizations With Superpixel Segmentation for Hyperspectral Unmixing

Sun, Le; Wu, Feiyang; He, Chengxun; Zhan, Tianming; Liu, Wei; Zhang, Daopan

doi:10.1109/lgrs.2020.3019427

Cited by 26 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our proposed CF2PN network, for the backbone feature extraction network we employ the popular VGG-16. The VGG network has the following main characteristics: (1) to explore the relationship between depth and performance of convolutional neural networks, and VGG networks employ iterative overlapping of 3 × 3 small convolutional kernels and 2 × 2 maximum pooling layers; (2) the VGG model has a simple structure in that each part of the network employs the same convolution kernel (of size 3 × 3) and maximum pooling (of size 2 × 2); (3) it has five convolution stages, with each stage having two to three convolution layers and a maximum pooling layer at the end to shrink the image; and (4) the VGG model shown in Figure 3 uses three groups of 3 × 3 kernels in place of a 7 × 7 kernel. In the VGG-16 network, three groups of 3 × 3 kernels are used continuously (with a stride of 1) in the deep network, which not only increases the model's linear expression ability but also reduces the amount of calculation.…”

Section: Backbone Networkmentioning

confidence: 99%

“…Traditional target detection [1,2] extracts features from candidate regions within the image using techniques such as Haar [3], HOG [4] or sparse representation [5][6][7][8] and then classifies them using the SVM [9] model. Deep learning [10][11][12][13] is characterized by automatic learning of image features, thus replacing manual feature extraction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

Huang

Chen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In the wake of developments in remote sensing, the application of target detection of remote sensing is of increasing interest. Unfortunately, unlike natural image processing, remote sensing image processing involves dealing with large variations in object size, which poses a great challenge to researchers. Although traditional multi-scale detection networks have been successful in solving problems with such large variations, they still have certain limitations: (1) The traditional multi-scale detection methods note the scale of features but ignore the correlation between feature levels. Each feature map is represented by a single layer of the backbone network, and the extracted features are not comprehensive enough. For example, the SSD network uses the features extracted from the backbone network at different scales directly for detection, resulting in the loss of a large amount of contextual information. (2) These methods combine with inherent backbone classification networks to perform detection tasks. RetinaNet is just a combination of the ResNet-101 classification network and FPN network to perform the detection tasks; however, there are differences in object classification and detection tasks. To address these issues, a cross-scale feature fusion pyramid network (CF2PN) is proposed. First and foremost, a cross-scale fusion module (CSFM) is introduced to extract sufficiently comprehensive semantic information from features for performing multi-scale fusion. Moreover, a feature pyramid for target detection utilizing thinning U-shaped modules (TUMs) performs the multi-level fusion of the features. Eventually, a focal loss in the prediction section is used to control the large number of negative samples generated during the feature fusion process. The new architecture of the network proposed in this paper is verified by DIOR and RSOD dataset. The experimental results show that the performance of this method is improved by 2%-12% in the DIOR dataset and RSOD dataset compared with the current SOTA target detection methods.

show abstract

Section: Backbone Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

Huang

Chen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The joint sparse representation [20][21][22][23][24] methods achieve a smoother result by jointly representing the adjacent pixels while representing the target pixels. Furthermore, the low-rank representation [25][26][27][28][29][30] approaches have also been applied to classify the HSI. Moreover, several kernel-based spatial-spectral approaches are developed to integrate spatial-spectral features.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

Zhang

Chen

2021

Remote Sensing

View full text Add to dashboard Cite

This paper presents a composite kernel method (MWASCK) based on multiscale weighted adjacent superpixels (ASs) to classify hyperspectral image (HSI). The MWASCK adequately exploits spatial-spectral features of weighted adjacent superpixels to guarantee that more accurate spectral features can be extracted. Firstly, we use a superpixel segmentation algorithm to divide HSI into multiple superpixels. Secondly, the similarities between each target superpixel and its ASs are calculated to construct the spatial features. Finally, a weighted AS-based composite kernel (WASCK) method for HSI classification is proposed. In order to avoid seeking for the optimal superpixel scale and fuse the multiscale spatial features, the MWASCK method uses multiscale weighted superpixel neighbor information. Experiments from two real HSIs indicate that superior performance of the WASCK and MWASCK methods compared with some popular classification methods.

show abstract

“…Thus, it exhibits strong self-learning, self-organization, and self-adaptation ability [27], and is widely used in many engineering fields. Therefore, this study will first discuss the multi-objective optimization problem of DPBFZ under the constraints of the ecological protection red line [28], urban development boundary and other rules, the objective function system of DPBFZ, and the formal expression of multiple constraints. Then a clonal selection algorithm will be introduced to solve the multi-objective spatial optimization problem [29].…”

Section: Introductionmentioning

confidence: 99%

Zoning Permanent Basic Farmland Based on Artificial Immune System coupling with spatial constraints

2021

KSII TIIS

View full text Add to dashboard Cite

The red line of Permanent Basic Farmland is the most important part in the "three-line" demarcation of China's national territorial development plan. The scientific and reasonable delineation of the red line is a major strategic measure being taken by China to improve its ability to safeguard the practical interests of farmers and guarantee national food security. The delineation of Permanent Basic Farmland zoning (DPBFZ) is essentially a multi-objective optimization problem. However, the traditional method of demarcation does not take into account the synergistic development goals of conservation of cultivated land utilization, ecological conservation, or urban expansion. Therefore, this research introduces the idea of artificial immune optimization and proposes a multi-objective model of DPBFZ red line delineation based on a clone selection algorithm. This research proposes an objective functional system consisting of these three sub-objectives: optimal quality of cropland, spatially concentrated distribution, and stability of cropland. It also takes into consideration constraints such as the red line of ecological protection, topography, and space for major

show abstract

Weighted Collaborative Sparse and L _1/2 Low-Rank Regularizations With Superpixel Segmentation for Hyperspectral Unmixing

Cited by 26 publications

References 14 publications

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

Zoning Permanent Basic Farmland Based on Artificial Immune System coupling with spatial constraints

Contact Info

Product

Resources

About

Weighted Collaborative Sparse and L 1/2 Low-Rank Regularizations With Superpixel Segmentation for Hyperspectral Unmixing

Cited by 26 publications

References 14 publications

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

Zoning Permanent Basic Farmland Based on Artificial Immune System coupling with spatial constraints

Contact Info

Product

Resources

About

Weighted Collaborative Sparse and L _1/2 Low-Rank Regularizations With Superpixel Segmentation for Hyperspectral Unmixing