Object-oriented and multi-scale target classification and recognition based on hierarchical ensemble learning. (August 2017)

• Record Type: Journal Article
• Authors: Liu, Yang; Zheng, Feng-bin
• Is Part Of: Computers & electrical engineering. Volume 62(2017)
• Page Start: 538
• Page End: 554
• Publication Date: 2017-08
• Subjects: Target classification and recognition -- Deep spiking convolutional neural network -- Hierarchical latent Dirichlet allocation -- Brain inspired computing -- Multimedia neural cognitive computing -- High resolution remote-sensing image; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.12.026
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Hierarchical sensations features extraction based on DSCN. Hierarchical perceptions features extraction based on HLDA. Multi-hierarchical ensemble learning framework via DSCN and HLDA. Incremental and reinforcement learning of TCR. Object-oriented and multi-scale data augmentation. High accuracy TCR of high resolution remote sensing image. Abstract: Target classification and recognition (TCR) of high resolution remote-sensing image is the important ability for earth observation system and unmanned autonomous system. It is difficult to improve the precision of TCR because of different imaging mechanism. In this paper, we propose a brain-inspired computing model for TCR using cognitive computing and deep learning. Accordingly, we have built an ensemble learning algorithm based on deep spiking convolutional neural network and hierarchical latent Dirichlet allocation. The hierarchical features were extracted from remote-sensing image. Then a TCR algorithm for small sample sizes and complex target was designed, which uses the incremental and reinforcement learning based on object-oriented and multi-scale data argumentation. Experimental results demonstrate that our algorithm has state-of-the-art performance on public data sets of optical remote-sensing image and synthetic aperture image. The model proposed can provide reference to explore an essential significance in brain-inspired intelligence, and has significant value in military and civil affairs. Graphical abstract: