A Novel Neural Network for Remote Sensing Image Matching

Zhu, Hao; Jiao, Licheng; Ma, Wenping; Liu, Fang; Zhao, Wei

doi:10.1109/tnnls.2018.2888757

Cited by 69 publications

(35 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, convolutional neural networks (CNNs), though widely investigated and highly praised for classification tasks [40], are rarely used for AGB estimation. Drawbacks inherent in CNNs and VHSR images constrain the use of CNNs for biomass estimation: spatial heterogeneity and, especially, the lack of sufficient training samples [41]. Unlike classification tasks that samples could be obtained less costly, AGB samples are relatively expensive.…”

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Dong

Han

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Above-ground biomass (AGB) directly relates to the productivity of forests. Precisely, AGB mapping for regional forests based on very high resolution (VHR) imagery is widely needed for evaluation of productivity. However, the diversity of variables and algorithms and the difficulties inherent in high resolution optical imagery make it complex. In this paper, we explored the potentials of the state-of-art algorithm convolutional neural networks (CNNs), which are widely used for its high-level representation, but rarely applied for AGB estimation. Four experiments were carried out to compare the performance of CNNs and other state-of-art Machine Learning (ML) algorithms: (1) performance of CNN using bands, (2) performance of Random Forest (RF), support vector regression (SVR), artificial neural network (ANN) on bands, and vegetation indices (VIs). (3) Performance of RF, SVR, and ANN on gray-level co-occurrence matrices (GLCM), and exploratory spatial data analysis (ESDA), and (4) performance of RF, SVR, and ANN based on all combined data and ESDA+VIs. CNNs reached satisfactory results (with R2 = 0.943) even with limited input variables (i.e., only bands). In comparison, RF and SVR with elaborately designed data obtained slightly better accuracy than CNN. For examples, RF based on GLCM textures reached an R2 of 0.979 and RF based on all combined data reached a close R2 of 0.974. However, the results of ANN were much worse (with the best R2 of 0.885).

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Dong

Han

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…This hierarchy produces layer S4 again, as does layer S2. Finally, these pixel values are rasterized and connected into a vector input to the traditional neural network to get the output (Zhu et al, 2019).…”

Section: Target Detection Of Soil Remote Sensing Image Based On Deep Learningmentioning

confidence: 99%

Maximum Likelihood Classification of Soil Remote Sensing Image Based on Deep Learning

2020

View full text Add to dashboard Cite

Soil remote sensing image classification is the most difficult in the National Soil Census work. Current soil remote sensing image classification methods based on deep learning and maximum likelihood estimation are challenging to meet the actual needs. Therefore, this paper combines deep learning with maximum likelihood estimation and proposes a maximum likelihood classification method for soil remote sensing images based on deep learning. The method is divided into four parts. Firstly, the pretreatment of soil remote sensing image is carried out, including three processes: image gray, image denoising, and image correction; secondly, the target of soil remote sensing image is detected by deep learning algorithm; thirdly, the maximum likelihood algorithm is used to classify soil remote sensing image; finally, the classification performance is tested by an example. The results show that this method can effectively segment the remote sensing image of soil, and the segmentation accuracy is high, which proves the effectiveness and superiority of the method.

show abstract

“…The second approach involves directly using a DNN to match key points [24]- [26], which translates the image matching problem into two types of classification problems. This approach has a high matching accuracy, but the number of calculations required increases with the square of the number of key points, significantly increasing the registration time.…”

Section: Introductionmentioning

confidence: 99%

Registration of Multiresolution Remote Sensing Images Based on L2-Siamese Model

Fan

Hou

Liu

et al. 2021

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

View full text Add to dashboard Cite

The registration of multi-resolution optical remote sensing images has been widely used in image fusion, change detection, and image stitching. However, traditional registration methods achieve poor accuracy in the registration of multiresolution remote sensing images. In this study, we propose a framework for generating deep features via a deep residual encoder (DRE) fused with shallow features for multi-resolution remote sensing image registration. Through an L2 normalization Siamese network (L2-Siamese) based on the DRE, the multiscale loss function is used to learn the attribute characteristics and distance characteristics of two key points and obtain the trained feature extractor. Finally, the DRE is used to extract the deep features of the key points and their neighbors, which are concatenated with the shallow features into a fusion feature vector to complete the image registration. We performed comprehensive experiments on four sets of multi-resolution optical remote sensing images and two sets of synthetic aperture radar images. The results demonstrate that the proposed registration model can achieve sub-pixel registration. The relative registration accuracy improved by 1.6 − 7.5%, whereas the overall performance improved by 4.5 − 14.1%.

show abstract

A Novel Neural Network for Remote Sensing Image Matching

Cited by 69 publications

References 43 publications

Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Maximum Likelihood Classification of Soil Remote Sensing Image Based on Deep Learning

Registration of Multiresolution Remote Sensing Images Based on L2-Siamese Model

Contact Info

Product

Resources

About