Abstract
In the field of multiple features Object-Based Change Detection (OBCD) for very-high-resolution remotely sensed images, image objects have abundant features and feature selection affects the precision and efficiency of OBCD. Through object-based image analysis, this paper proposes a Genetic Particle Swarm Optimization (GPSO)-based feature selection algorithm to solve the optimization problem of feature selection in multiple features OBCD. We select the Ratio of Mean to Variance (RMV) as the fitness function of GPSO, and apply the proposed algorithm to the object-based hybrid multivariate alternative detection model. Two experiment cases on Worldview-2/3 images confirm that GPSO can significantly improve the speed of convergence, and effectively avoid the problem of premature convergence, relative to other feature selection algorithms. According to the accuracy evaluation of OBCD, GPSO is superior at overall accuracy (84.17% and 83.59%) and Kappa coefficient (0.6771 and 0.6314) than other algorithms. Moreover, the sensitivity analysis results show that the proposed algorithm is not easily influenced by the initial parameters, but the number of features to be selected and the size of the particle swarm would affect the algorithm. The comparison experiment results reveal that RMV is more suitable than other functions as the fitness function of GPSO-based feature selection algorithm.
Highlights
Object change detection in Very-High-Resolution (VHR) remotely sensed imagery has become a hot topic in the field of remotely sensed imagery analysis, and object-oriented image analysis has been the primary way to solve the “salt and pepper” problem [1], which commonly occurred in pixel-based image analysis
In the field of object-based change detection (OBCD), VHR imagery is usually segmented to several objects and the image objects are regarded as the basic processing units
This paper proposes a Genetic Particle Swarm Optimization (GPSO) feature selection algorithm to be utilized in OBCD by using object-based hybrid multivariate alternative detection (OB-HMAD) model, and analyzes the fitness convergence and OBCD accuracy of the algorithms using the ratio of mean to variance (RMV) as the fitness function
Summary
Object change detection in Very-High-Resolution (VHR) remotely sensed imagery has become a hot topic in the field of remotely sensed imagery analysis, and object-oriented image analysis has been the primary way to solve the “salt and pepper” problem [1], which commonly occurred in pixel-based image analysis. The main difference between pixel-based change detection and object-based change detection is that image objects have more feature information, so multi-feature image analysis can identify more change information for VHR remotely sensed imagery [2,3]. Existing feature selection algorithms can be broadly classified into two categories: filter approaches and wrapper approaches [4]. Wrappers achieve better results than filters, because wrappers include a learning algorithm as part of the evaluation
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.
