Correlation-based joint acquisition and demosaicing of visible and near-infrared images

Sadeghipoor, Zahra; Lu, Yue M.; Süsstrunk, Sabine

doi:10.1109/icip.2011.6116339

Cited by 37 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Currently, we use a multi-image approach, as we capture the visible and the NIR part of the spectrum separately. The feasibility of a visible plus NIR sensor shown in [16], [17] motivates our belief that in the near-future, digital camera sensors will jointly capture visible and NIR, which will turn our method into a single-image approach. The results are refined by combining this map with a color to NIR ratio map.…”

Section: Multi-image Approachesmentioning

confidence: 88%

“…Combining visible and NIR images has been successfully used to improve various image processing and computer vision tasks, such as skin smoothing [10], high dynamic range image rendering [11], haze removal [12], [13], scene recognition [14], and semantic region labeling [15]. In addition, enabling simultaneous capture of both visible and NIR radiation with a single sensor [16], [17] is currently being researched. Because our method is computationally inexpensive and works on RAW images, it can easily be implemented in-camera to provide assistance where shadow detection is beneficial, e.g., white-balancing or automatic image enhancement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic and Accurate Shadow Detection Using Near-Infrared Information

Rüfenacht

Fredembach

Süsstrunk

2014

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Abstract-We present a method to automatically detect shadows in a fast and accurate manner by taking advantage of the inherent sensitivity of digital camera sensors to the near-infrared (NIR) part of the spectrum. Dark objects, which confound many shadow detection algorithms, often have much higher reflectance in the NIR. We can thus build an accurate shadow candidate map based on image pixels that are dark both in the visible and NIR representations. We further refine the shadow map by incorporating ratios of the visible to the NIR image, based on the observation that commonly encountered light sources have very distinct spectra in the NIR band. The results are validated on a new database, which contains visible/NIR images for a large variety of real-world shadow creating illuminant conditions, as well as manually labelled shadow ground truth. Both quantitative and qualitative evaluations show that our method outperforms current state-of-the-art shadow detection algorithms in terms of accuracy and computational efficiency.

show abstract

Section: Multi-image Approachesmentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Automatic and Accurate Shadow Detection Using Near-Infrared Information

Rüfenacht

Fredembach

Süsstrunk

2014

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [44], [45], the authors simultaneously optimized the MSFA (more specifically, optimized a combination ratio of RGB and NIR filters to form each spectral filter) and a linear demosaicking matrix by describing the whole imaging system in a linear form. This approach can be generalized for multispectral imaging in theory.…”

Section: Rgb-nir Filtersmentioning

confidence: 99%

A Practical One-Shot Multispectral Imaging System Using a Single Image Sensor

Monno

Kikuchi

Tanaka

et al. 2015

IEEE Trans. on Image Process.

131

View full text Add to dashboard Cite

Single-sensor imaging using the Bayer color filter array (CFA) and demosaicking is well established for current compact and low-cost color digital cameras. An extension from the CFA to a multispectral filter array (MSFA) enables us to acquire a multispectral image in one shot without increased size or cost. However, multispectral demosaicking for the MSFA has been a challenging problem because of very sparse sampling of each spectral band in the MSFA. In this paper, we propose a high-performance multispectral demosaicking algorithm, and at the same time, a novel MSFA pattern that is suitable for our proposed algorithm. Our key idea is the use of the guided filter to interpolate each spectral band. To generate an effective guide image, in our proposed MSFA pattern, we maintain the sampling density of the G -band as high as the Bayer CFA, and we array each spectral band so that an adaptive kernel can be estimated directly from raw MSFA data. Given these two advantages, we effectively generate the guide image from the most densely sampled G -band using the adaptive kernel. In the experiments, we demonstrate that our proposed algorithm with our proposed MSFA pattern outperforms existing algorithms and provides better color fidelity compared with a conventional color imaging system with the Bayer CFA. We also show some real applications using a multispectral camera prototype we built.

show abstract

“…[11] [12]), becomes critical in the FIR-VS image registration, especially when the images are further away from the visible spectrum (LWIR-FIR). The difficulty in FIR-VS image registration corresponds to the nonlinear relationship between pixel intensities, which is one of the differences with respect to NIR-VS and MIR-VS images.…”

Section: -15mentioning

confidence: 99%

A Novel SIFT-Like-Based Approach for FIR-VS Images Registration

Aguilera¹,

Barrera²,

Sappa³

et al. 2012

Proceedings of the 2012 International Conference on Quantitative InfraRed Thermography

View full text Add to dashboard Cite

This paper presents a novel approach, based on a SIFT-like scale-space pyramidal scheme, for registering FarInfrared and Visible Spectrum images. The proposed approach consists of 3 stages. Initially, a key point detector is used to find interest points. This first stage is a SIFT-like based scale space representation. Then, each key point is characterized using an edge-oriented-histogram (EOH) in its neighborhood. Finally, a matching stage finds the nearest pairs in the couple of multispectral images. Experimental results are provided showing the validity of the proposed approach for registering such a kind of multispectral pair of images.

show abstract

Correlation-based joint acquisition and demosaicing of visible and near-infrared images

Cited by 37 publications

References 10 publications

Automatic and Accurate Shadow Detection Using Near-Infrared Information

Automatic and Accurate Shadow Detection Using Near-Infrared Information

A Practical One-Shot Multispectral Imaging System Using a Single Image Sensor

A Novel SIFT-Like-Based Approach for FIR-VS Images Registration

Contact Info

Product

Resources

About