Abstract
Multitask sparse representation method improves the detection performance by constructing multiple associated sub-sparse representation tasks and jointly learning multiple sub-sparse representation tasks, and this method can make use of the spectral information. However, the using of spatial information needs to be improved. This paper designs a hyperspectral image target detection method which can both make use of spectral and spatial information, that is a weighted joint k-nearest neighbor and multitask learning sparse representation method (WJNN-MTL-SR) is proposed. This method mainly consists of the following steps:1) using multitask sparse representation to obtain the representation residuals. 2) weighted joint k-nearest neighbor is used into the joint region of test pixels to obtain the weighted joint Euclidean distance. 3) a decision function, combining the weighted joint Euclidean distance and residuals of the multitask sparse representation, is used to get target detection result. Experimental results demonstrate that the proposed method show better detection performance than state-of-the-art methods.
Highlights
Hyperspectral image (HSIs) have a wealth of spectral information because they have hundreds of spectral bands, which can represent and distinguish different substances accurately
We propose the weighted joint k-nearest neighbor and Multitask Learning Sparse Representation method (WJNN-MULTITASK LEARNING SPARSE REPRESENTATION (MTL-SR)), which is able to combines the advantages of weighted joint k-nearest neighbor (WJNN) [26] and multitask learning sparse representation [27]
We can see that the performance of our proposed algorithm has been upgraded based on joint sparse representation (JSR)-Multitask learning (MTL), the results show that our proposed algorithm obtains a better detection performance than the other algorithms for all of the three datasets even in noisy environments
Summary
Hyperspectral image (HSIs) have a wealth of spectral information because they have hundreds of spectral bands, which can represent and distinguish different substances accurately. In sparse target detection methods, a few training samples were selected to construct dictionary, the spectral variability phenomenon would lead to bad performance. In many sparse representation methods, a target dictionary formed by target samples were selected from the global image, while target samples chosen by this method was often insufficient, this way usually resulted in weakened detection performance To solve this problem, a target dictionary construction method [22] was employed. As for HSI target detection, the dictionary is constructed by appropriate target and background training samples based on prior information and the sparse vector can be obtained by solving a constrained minimization problem [20]. The residual determined by background and target residual, and the threshold is set to classify the target and background
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
