Monocular color-IR imaging system applicable for various light environments

Nonaka, Yuichi; Yoshida, Daisuke; Kitamura, Shogo; Yokota, Takashi; Hasegawa, Madoka; Ootsu, Kanemitsu

doi:10.1109/icce.2018.8326238

Cited by 5 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В настоящее время ведется активная научная работа по соединению видимого и инфракрасного спектра для получения мультиспектрального изображения различными способами [7][8][9].…”

Section: двухслойные системы цветоделенияunclassified

Interpolation in microscaning two-layer matrix photoreceivers

Zhbanova,

Yakimenko

2023

Analysis and data processing systems

View full text Add to dashboard Cite

The paper presents a method for microscanning two-layer patterns of matrix photodetectors based on silicon. The developed systems register the visible and infrared spectra. Various methods of microscanning with the developed multispectral matrix photodetectors are proposed. Two colors are recorded in each cell, which simplifies the interpolation process, and using the microscanning technology, can eliminate it. For the obtained subpixels, the interpolation algorithm is reduced. In this case, the direction of a matrix shift should be taken into account when performing microscanning. For staggered cell patterns, the choice of direction is not as critical as for pseudo-random or vertical/horizontal arrangement. When microscanning, the direction of matrix shift should be taken into account. For staggered cell patterns, the choice of direction is not as critical as for pseudo-random or vertical/horizontal arrangement. So, for example, a pseudo-random arrangement is suitable for recording images of nature, where there are many small details of various shapes; and vertical/horizontal arrangement is suitable for scenes of the city and industrial areas, where everything has clear vertical and horizontal lines. The very idea of microscanning with a shift of half a pixel makes it possible to fill the "blind" zones of the matrix - pixel binding - on four sides of the pixel itself, which leads to a 4-fold increase in color resolution. For the obtained subpixels, a linear or adaptive interpolation method is suitable. It is also possible to take a more complicated path and choose bicubic, biharmonic interpolation. However, this approach contradicts the very concept of simplifying the image processing algorithm, although it leads to high-contrast color resolutions. Such systems can be used in surveys where it is necessary to record the exact details of a terrain or object, for example, in aerial photography and photogrammetry.

show abstract

Section: двухслойные системы цветоделенияunclassified

Interpolation in microscaning two-layer matrix photoreceivers

Zhbanova,

Yakimenko

2023

Analysis and data processing systems

View full text Add to dashboard Cite

show abstract

“…The usage of depth images or infrared (IR) images can be an alternative solution for the problems associated with uneven lighting conditions [27][28][29][30][31]. Since such images are acquired under invisible IR light rather than visible light, this option has the advantage of being able to obtain meaningful images, even in a dark environment that is not affected by ambient lighting.…”

Section: Introductionmentioning

confidence: 99%

Improving the Performance of Automatic Lip-Reading Using Image Conversion Techniques

Lee

2024

Electronics

View full text Add to dashboard Cite

Variation in lighting conditions is a major cause of performance degradation in pattern recognition when using optical imaging. In this study, infrared (IR) and depth images were considered as possible robust alternatives against variations in illumination, particularly for improving the performance of automatic lip-reading. The variations due to lighting conditions were quantitatively analyzed for optical, IR, and depth images. Then, deep neural network (DNN)-based lip-reading rules were built for each image modality. Speech recognition techniques based on IR or depth imaging required an additional light source that emitted light in the IR range, along with a special camera. To mitigate this problem, we propose a method that does not use an IR/depth image directly, but instead estimates images based on the optical RGB image. To this end, a modified U-net was adopted to estimate the IR/depth image from an optical RGB image. The results show that the IR and depth images were rarely affected by the lighting conditions. The recognition rates for the optical, IR, and depth images were 48.29%, 95.76%, and 92.34%, respectively, under various lighting conditions. Using the estimated IR and depth images, the recognition rates were 89.35% and 80.42%, respectively. This was significantly higher than for the optical RGB images.

show abstract

“…With this in mind, other modalities are being explored, that can be used independently or in conjunction. An example is near-infrared (NIR), robust to lack of lighting but requires a dedicated source of IR light and filters and is also sensible to different lens exposures [6]. The modality we explore in this document, thermal images, is a passive solution robust to any external light conditions.…”

Section: Introductionmentioning

confidence: 99%

Face Detection in Thermal Images with YOLOv3

Silva

Monteiro

Ferreira³

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The automotive industry is currently focusing on automation in their vehicles, and perceiving the surroundings of an automobile requires the ability to detect and identify objects, events and persons, not only from the outside of the vehicle but also from the inside of the cabin. This constitutes relevant information for defining intelligent responses to events happening on both environments. This work presents a new method for in-vehicle monitoring of passengers, specifically the task of real-time face detection in thermal images, by applying transfer learning with YOLOv3. Using this kind of imagery for this purpose brings some advantages, such as the possibility of detecting faces during the day and in the dark without being affected by illumination conditions, and also because it's a completely passive sensing solution. Due to the lack of suitable datasets for this type of application, a database of in-vehicle images was created, containing images from 38 subjects performing different head poses and at varying ambient temperatures. The tests in our database show an AP50 of 99.7% and an AP of 78.5%.

show abstract

Monocular color-IR imaging system applicable for various light environments

Cited by 5 publications

References 5 publications

Interpolation in microscaning two-layer matrix photoreceivers

Interpolation in microscaning two-layer matrix photoreceivers

Improving the Performance of Automatic Lip-Reading Using Image Conversion Techniques

Face Detection in Thermal Images with YOLOv3

Contact Info

Product

Resources

About