Lianfa Bai

  • Citations Per Year
Learn More
Salient object detection remains one of the most important and active research topics in computer vision, with wide-ranging applications to object recognition, scene understanding, image retrieval, context aware image editing, image compression, etc. Most existing methods directly determine salient objects by exploring various salient object features. Here,(More)
The goal of saliency detection is to locate important regions in an image which attract viewers’ attention the most. In this paper, we propose a dynamic Bayesian model for saliency detection in which both Boolean-based and foreground-based models are exploited. First, a preliminary saliency map is constructed based on multi-channel Boolean maps, and a(More)
Sparse and redundant representations perform well in image denoising. However, sparsity-based methods fail to denoise low-light-level (LLL) images because of heavy and complex noise. They consider sparsity on image patches independently and tend to lose the texture structures. To suppress noises and maintain textures simultaneously, it is necessary to embed(More)
In dual-spectrum night vision technology, the fusion image quality is the key to appraise the fusion method The target of dual-spectrum night vision technology is to enhance the definition of the scenery and the target identification probability, according to the above requirement, using the target identification probability, the signal to noise ratio and(More)
In this paper, on the base of analysis on low light level (LLL) image and infrared (IR) thermal image's characteristics, the researches on the processing and fusion on LLL and IR image has been done. The dual-channel image registration techniques of LLL and IR image are put forward, including digital real-time shift technique and dual-channel fusion(More)
The stimulus response of the classical receptive field (CRF) of neuron in primary visual cortex is affected by its periphery [i.e., non-CRF (nCRF)]. This modulation exerts inhibition, which depends primarily on the correlation of both visual stimulations. The theory of periphery and center interaction with visual characteristics can be applied in night(More)
Wavelet transform has the feature of multi-difference and has been used in image fusion. After image decomposed by wavelet, different entropy of low and high frequency parts are obtained in different decomposed layers. The emphases of image fusion can be obtained by analyzing the entropy of low and high frequency parts in different wavelet decomposed(More)
Sparse coding performs well in image classification. However, robust target recognition requires a lot of comprehensive template images and the sparse learning process is complex. We incorporate sparsity into a template matching concept to construct a local sparse structure matching (LSSM) model for general infrared target recognition. A local structure(More)