Color correction matrix for sparse RGB-W image sensor without IR cutoff filter

Vaillant, Jacques; Clouet, Axel; Alleysson, David

doi:10.1117/12.2306123

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overview of the Proposed Tilapia Weight-Estimation Evaluation Phase (1) Convert an observed video input to images:

(2) Enhance images in a case of turbid water: (2.1) Image sharpening by the convolution function

where

and

denotes the original image, and

is the filter kernel, i.e., sharpen, filter. (2.2) Color correction matrix (

) [ 32 ]:

where

denote the red, green, blue, and white spaces; C is the color-component vector; and

is the offset vector. (2.3) Exposure adjustment

where

is the gain and

represents the bias parameter.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Tengtrairat

Woo

Parathai

et al. 2022

Sensors

View full text Add to dashboard Cite

Underwater fish monitoring is the one of the most challenging problems for efficiently feeding and harvesting fish, while still being environmentally friendly. The proposed 2D computer vision method is aimed at non-intrusively estimating the weight of Tilapia fish in turbid water environments. Additionally, the proposed method avoids the issue of using high-cost stereo cameras and instead uses only a low-cost video camera to observe the underwater life through a single channel recording. An in-house curated Tilapia-image dataset and Tilapia-file dataset with various ages of Tilapia are used. The proposed method consists of a Tilapia detection step and Tilapia weight-estimation step. A Mask Recurrent-Convolutional Neural Network model is first trained for detecting and extracting the image dimensions (i.e., in terms of image pixels) of the fish. Secondly, is the Tilapia weight-estimation step, wherein the proposed method estimates the depth of the fish in the tanks and then converts the Tilapia’s extracted image dimensions from pixels to centimeters. Subsequently, the Tilapia’s weight is estimated by a trained model based on regression learning. Linear regression, random forest regression, and support vector regression have been developed to determine the best models for weight estimation. The achieved experimental results have demonstrated that the proposed method yields a Mean Absolute Error of 42.54 g, R2 of 0.70, and an average weight error of 30.30 (±23.09) grams in a turbid water environment, respectively, which show the practicality of the proposed framework.

show abstract

“…Overview of the Proposed Tilapia Weight-Estimation Evaluation Phase (1) Convert an observed video input to images:

(2) Enhance images in a case of turbid water: (2.1) Image sharpening by the convolution function

where

and

denotes the original image, and

is the filter kernel, i.e., sharpen, filter. (2.2) Color correction matrix (

) [ 32 ]:

where

denote the red, green, blue, and white spaces; C is the color-component vector; and

is the offset vector. (2.3) Exposure adjustment

where

is the gain and

represents the bias parameter.…”

Section: Methodsmentioning

confidence: 99%

“…An overview of the proposed Tilapia weight-estimation evaluation phase is explained in Algorithm 1. (2.2) Color correction matrix (CCM) [32]:…”

Section: Models Independent Data Dependent Outputmentioning

confidence: 99%

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Tengtrairat

Woo

Parathai

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, some works take advantage of the mathematical basis of publicly available calibration schemes, such as Color Calibration Matrix (CCM) [28], and adapt it to optimise the process to their goals. Proposals to calculate the calibration matrix range from simple processes like linear algebra approaches [24], to other more elaborated ones involving least squares [29] or deep learning [30] have been published. Aside, other works also present custom color charts for the contexts of their own projects [31].…”

Section: Related Workmentioning

confidence: 99%

Self-Designed Colour Chart and a Multi-Dimensional Calibration Approach for Cultural Heritage Preventive Preservation

2021

View full text Add to dashboard Cite

In this paper we present a colour calibration framework for cultural heritage preventive conservation. It includes a custom colour chart based on a regular sRGB division and a multi-dimensional calibration approach based on hyper-surfaces that map the original colours to the calibrated space taking information from all the channels. As shown, our work outperforms past proposals. This solution has been designed to be automatic and match the requirements of our cultural heritage surveillance framework needs, such as non-invasiveness and easiness to deploy. Its performance has been compared to publicly available calibration proposals and charts, and their results judged basing on the context and restrictions of the intended goal, such as illumination. Conclusions on the need for adapting technological solutions to the context of the goal, its cases of use when valid and self-designed methods are drawn. This work is part of the MIPAC-CM project.

show abstract

“…Finally, the interpolated raw image is converted in a color image using a color conversion matrix (CCM) which maps the intrinsic input spectral space given by the camera to an output color space. We choose CIE-XYZ 1931 [8]- [10] as reference for output space because one can then easily convert XYZ coordinates in any display space such as sRGB. The image formation flow is schemed Figure 2.…”

Section: Model Of Signal Acquisition and Color Image Formationmentioning

confidence: 99%

Physical noise propagation in color image construction: a geometrical interpretation

Clouet¹,

Vaillant²,

Alleysson³

2019

cic

Self Cite

View full text Add to dashboard Cite

To avoid false colors, classical color sensors cut infrared wavelengths for which silicon is sensitive (with the use of an infrared cutoff filter called IR-cut). However, in low light situation, noise can alter images. To increase the amount of photons received by the sensor, in other words, the sensor's sensitivity, it has been proposed to remove the IR-cut for low light applications. In this paper, we analyze if this methodology is beneficial from a signal to noise ratio point of view when the wanted result is a color image. For this aim we recall the formalism behind physical raw image acquisition and color reconstruction. A comparative study is carried out between one classical color sensor and one specific color sensor designed for low light conditions. Simulated results have been computed for both sensors under same exposure settings and show that raw signal to noise ratio is better for the low light sensor. However, its reconstructed color image appears more noisy. Our formalism illustrates geometrically the reasons of this degradation in the case of the low light sensor. It is due on one hand to the higher correlation between spectral channels and on the other hand to the near infrared part of the signal in the raw data which is not intrinsically useful for color.

show abstract

Color correction matrix for sparse RGB-W image sensor without IR cutoff filter

Cited by 5 publications

References 9 publications

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Self-Designed Colour Chart and a Multi-Dimensional Calibration Approach for Cultural Heritage Preventive Preservation

Physical noise propagation in color image construction: a geometrical interpretation

Contact Info

Product

Resources

About