A super-resolution reconstruction algorithm for surveillance images

Zhang, Liangpei; Zhang, Hongyan; Shen, Huanfeng; Li, Pingxiang

doi:10.1016/j.sigpro.2009.09.002

Cited by 318 publications

(134 citation statements)

References 30 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…Static error is a very important parameter characterizing the terrain features. Its introduction matches different-resolution terrain data with different terrain features in the multi-resolution model, in order to fully draw the terrain details of ROI region [9]. Static error is the difference between the real elevation and the interpolation average.…”

Section: Improved Methods Of Quadtreementioning

confidence: 99%

Improved LOD Based on Quadtree and Spatiotemporal Association in SVS

Li¹,

Song²,

Han³

et al. 2017

dtcse

View full text Add to dashboard Cite

Abstract. The Synthetic Vision System (SVS) is an advanced real-time display technology of 3D terrain, which is aimed at integrated display of navigation information and 3D terrain. However, we will face two key problems in SVS development. They are spatiotemporal association of various data and real-time and effective display of terrain. Therefore, in order to solve these problems, a unified representation model is set up in this paper to uniformly express multi-source, heterogeneous and multi-scale data. Besides, LOD (Levels of Detail) based on Quadtree is improved here for the real-time and effective display of terrain. The improved method can increase rendering speed and enhance display effect at the same time. Simulation on OpenGL proves that methods in this paper can realize the integrated display between real-time 3D terrain with multi-resolution and the corresponding navigation data.

show abstract

Section: Improved Methods Of Quadtreementioning

confidence: 99%

Improved LOD Based on Quadtree and Spatiotemporal Association in SVS

Li¹,

Song²,

Han³

et al. 2017

dtcse

View full text Add to dashboard Cite

show abstract

“…First, the frequency domain image registration method and the spatial domain method in [15] both account for the global motion between images, and thus provide the comparability between the two methods. Second, the spatial domain method [15] and its variants have been widely utilized and have been proven to be effective in many natural and remote sensing image super-resolution reconstruction tasks [1,2,15,32]. We choose two image regions of size 100 × 100 pixels, which are downsampled from the two images of size 200 × 200 pixels, as shown in Figure 5, by a factor of 2, to independently test the frequency domain motion estimation method.…”

Section: Registration Accuracymentioning

confidence: 99%

Super-Resolution Reconstruction for Multi-Angle Remote Sensing Images Considering Resolution Differences

et al. 2014

Self Cite

View full text Add to dashboard Cite

Multi-angle remote sensing images are acquired over the same imaging scene from different angles, and share similar but not identical information. It is therefore possible to enhance the spatial resolution of the multi-angle remote sensing images by the super-resolution reconstruction technique. However, different sensor shooting angles lead to different resolutions for each angle image, which affects the effectiveness of the super-resolution reconstruction of the multi-angle images. In view of this, we propose utilizing adaptive weighted super-resolution reconstruction to alleviate the limitations of the different resolutions. This paper employs two adaptive weighting themes. The first approach uses the angle between the imaging angle of the current image and that of the nadir image. The second is closely related to the residual error of each low-resolution angle image. The experimental results confirm the feasibility of the proposed method and demonstrate the effectiveness of the proposed adaptive weighted super-resolution approach.

show abstract

“…The recovery of high-resolution (HR) images and videos from low-resolutions (LR) content is a topic of great interest in digital image processing with applications in many areas such as HDTV [11], medical imaging [20], satellite imaging [23], face recognition [12], immersive content generation, and surveillance [27]. The global super-resolution (SR) problem assumes that the LR image is a noisy, lowpass filtered, and downsampled version of the HR image.…”

Section: Introductionmentioning

confidence: 99%