Target recognition method of small UAV remote sensing image based on fuzzy clustering

2021 ◽  
Author(s):  
Linyang Guo ◽  
Runxian Yang ◽  
Zhichao Zhong ◽  
Ran Zhang ◽  
Bo Zhang
Keyword(s):  
Remote Sensing ◽  
Fuzzy Clustering ◽  
Target Recognition ◽  
Remote Sensing Image ◽  
Recognition Method ◽  
Small Uav

scholarly journals Automatic target recognition method for multitemporal remote sensing image

Open Physics ◽  
2020 ◽  
Vol 18 (1) ◽  
pp. 170-181
Author(s):  
Chang Shu ◽  
Lihui Sun
Keyword(s):  
Remote Sensing ◽  
Image Recognition ◽  
Target Recognition ◽  
Automatic Segmentation ◽  
Image Data ◽  
Remote Sensing Image ◽  
Automatic Target Recognition ◽  
Image Feature ◽  
Recognition Method ◽  
Multitemporal Remote Sensing

AbstractThe traditional target recognition method for the remote sensing image is difficult to accurately identify the specified targets from the massive remote sensing image data. Based on the theory of multitemporal recognition, an automatic target recognition method for the remote sensing image is proposed in this article. The proposed recognition method includes four modules: automatic segmentation of multitemporal remote sensing image, automatic target extraction of multitemporal remote sensing image, automatic processing of multitemporal remote sensing image, and automatic recognition of multitemporal remote sensing image. The automatic segmentation of the image target is introduced. The effectiveness of the segmentation technology is verified through the kernel function bandwidth algorithm. Linear feature extraction is used to extract the segmented image. The image extraction processing is described, which includes image profile analysis, image preprocessing, image feature analysis, the region of interest localization, image enhancement processing, recognition processing, and result output. According to the theory of pattern recognition, three different feature recognition images are given, which are partial separable recognition, weakly separable recognition, and fully separable recognition, and then, a new image recognition method is designed. To verify the practical application effect of the recognition method, the proposed method is compared with the traditional recognition method. Experimental results show that the proposed method can accurately identify the specified objects from the massive remote sensing image data and has a high potential for development. This article has an important guiding significance for image recognition.

scholarly journals SPATIAL-SPECTRAL FUZZY K-MEANS CLUSTERING FOR REMOTE SENSING IMAGE SEGMENTATION

2018 ◽  
Vol 56 (2) ◽  
pp. 257 ◽  
Author(s):  
Mai Dinh Sinh ◽  
Ngo Thanh Long ◽  
Trinh Le Hang
Keyword(s):  
Remote Sensing ◽  
Fuzzy Clustering ◽  
Spectral Clustering ◽  
Clustering Algorithm ◽  
Spatial Information ◽  
Remote Sensing Image ◽  
Information Value ◽  
Local Optimum ◽  
Mathematical Framework ◽  
Data Space

Spectral clustering is a clustering method based on algebraic graph theory. The clustering effect by using spectral method depends heavily on the description of similarity between instances of the datasets. Althought, spectral clustering has been significant interest in recent times, but the raw spectral clustering is often based on Euclidean distance, but it is impossible to accurately reflect the complexity of the data. Despite having a well-defined mathematical framework, good performance and simplicity, it suffers from several drawbacks, such as it is unable to determine a reasonable cluster number, sensitive to initial condition and not robust to outliers. In this paper, we present a new approach named spatial-spectral fuzzy clustering which combines spectral clustering and fuzzy clustering with spatial information into a unified framework to solve these problems, the paper consists of three main steps: Step 1, calculate the spatial information value of the pixels, step 2 applies the spectral clustering algorithm to change the data space from the color space to the new space and step 3 clusters the data in new data space by fuzzy clustering algorithm. Experimental results on the remote sensing image were evaluated based on a number of indicators, such as IQI, MSE, DI and CSI, show that it can improve the clustering accuracy and avoid falling into local optimum. 

Sign in / Sign up

Export Citation Format

Share Document