Color Constancy Algorithm Using Ambient Light Sensor

Yuemin Li; Haisong Xu; Yiming Huang; Minhang Yang; Bing Hu; Yuntao Zhang

doi:10.3788/AOS230458

Acta Optica Sinica, Volume. 43, Issue 14, 1433001(2023)

Color Constancy Algorithm Using Ambient Light Sensor

Yuemin Li, Haisong Xu^*, Yiming Huang, Minhang Yang, Bing Hu, and Yuntao Zhang

State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(11)

Fig. 1. Schematic of camera pose representation

Download full size

Fig. 2. Schematic of gray pixel extraction assisted by ALS

Download full size

Fig. 3. Distribution of the light sources in dataset for color space transformation

Download full size

Fig. 4. Distribution of the light sources in dataset for color constancy algorithm testing

Download full size

Fig. 5. Typical scenes with low color complexity in the testing dataset

Download full size

Fig. 6. Visualization of typical test images

Download full size

Table 1. Value of parameters in the confidence assessment model
View table
Table 1. Value of parameters in the confidence assessment model
$H_{i}$ $W_{i}$ $b$ $T_{H}$ $T_{C}$
64 64 18 $0.04 \times H_{i} \times W_{i}$ 0.01

Table 2. Evaluation of the confidence assessment model
View table
Table 2. Evaluation of the confidence assessment model
Condition Recall Precision False positive rating
Training fold 1.00 0.98 0.05
Testing fold 0.82 1.00 0.00

Table 3. Evaluation of the color space transformation model (angular error)
View table
Table 3. Evaluation of the color space transformation model (angular error)
Condition Mean /（°） Tri-mean /（°） Median /（°） Best 25% /（°） Worst 25% /（°）
Training fold 0.66 0.55 0.56 0.19 1.33
Testing fold 1.15 1.12 1.18 0.48 1.68

Table 4. Value of parameters in transformation from camera RGB space to $X Y_{o r t h}$ plane
View table
Table 4. Value of parameters in transformation from camera RGB space to $X Y_{o r t h}$ plane
$w_{r}$ $w_{g}$ $w_{b}$ $D_{r}^{C}$ $D_{g}^{C}$ $D_{b}^{C}$ $θ$ /（°） $σ$
0.2533 0.4935 0.2532 0.4141 1.000 0.7476 40.85 0.0453

Table 5. Performance of color constancy algorithms in the test set (angular error)

View table

Table 5. Performance of color constancy algorithms in the test set (angular error)

Method	Mean /（°）	Tri-mean /（°）	Median /（°）	Best 25% /（°）	Worst 25% /（°）
GW	6.88	7.40	7.10	1.99	11.37
GE1	5.07	3.88	4.39	1.61	10.32
GE2	5.56	5.78	5.49	1.99	9.16
SoG	4.69	3.00	3.67	1.52	10.30
WP	6.57	6.43	5.97	1.07	13.16
WGE	6.52	6.81	6.32	1.66	11.48
DO	5.02	1.97	3.26	0.46	13.55
GP	3.35	1.75	2.28	0.83	8.42
GI	4.07	1.65	2.89	0.41	10.72
ALS only	2.69	2.25	2.33	1.20	4.83
ALS grey pixels	2.14	1.34	1.57	0.37	5.11
ALS-based CC	2.27	1.59	1.81	0.46	4.99

Tools

Get Citation

Copy Citation Text

Yuemin Li, Haisong Xu, Yiming Huang, Minhang Yang, Bing Hu, Yuntao Zhang. Color Constancy Algorithm Using Ambient Light Sensor[J]. Acta Optica Sinica, 2023, 43(14): 1433001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Vision, Color, and Visual Optics

Received: Jan. 10, 2023

Accepted: Mar. 20, 2023

Published Online: Jul. 13, 2023

The Author Email: Haisong Xu (chsxu@zju.edu.cn)

DOI:10.3788/AOS230458

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Value of parameters in the confidence assessment model

Table 1. Value of parameters in the confidence assessment model

Table 2. Evaluation of the confidence assessment model

Table 2. Evaluation of the confidence assessment model

Table 3. Evaluation of the color space transformation model (angular error)

Table 3. Evaluation of the color space transformation model (angular error)

Table 4. Value of parameters in transformation from camera RGB space to XYorth plane

Table 4. Value of parameters in transformation from camera RGB space to XYorth plane

Table 5. Performance of color constancy algorithms in the test set (angular error)

Table 5. Performance of color constancy algorithms in the test set (angular error)

Table 4. Value of parameters in transformation from camera RGB space to $X Y_{o r t h}$ plane

Table 4. Value of parameters in transformation from camera RGB space to $X Y_{o r t h}$ plane