ADCC: An Effective and Intelligent Attention Dense Color Constancy System for Studying Images in Smart Cities

TL;DR

This paper introduces ADCC, a novel CNN-based color constancy method that leverages spatial information and log-histogram augmentation to improve illuminant estimation accuracy for smart city applications.

Contribution

The paper proposes a new attention-based DenseNet approach using log-chrominance histograms and image augmentation to enhance color constancy accuracy.

Findings

ADCC outperforms state-of-the-art methods on benchmark datasets.

The use of augmented images improves feature extraction and ambiguity elimination.

ADCC demonstrates high effectiveness for smart city vision applications.

Abstract

As a novel method eliminating chromatic aberration on objects, computational color constancy has becoming a fundamental prerequisite for many computer vision applications. Among algorithms performing this task, the learning-based ones have achieved great success in recent years. However, they fail to fully consider the spatial information of images, leaving plenty of room for improvement of the accuracy of illuminant estimation. In this paper, by exploiting the spatial information of images, we propose a color constancy algorithm called Attention Dense Color Constancy (ADCC) using convolutional neural network (CNN). Specifically, based on the 2D log-chrominance histograms of the input images as well as their specially augmented ones, ADCC estimates the illuminant with a self-attention DenseNet. The augmented images help to tell apart the edge gradients, edge pixels and non-edge ones in log-histogram, which contribute significantly to the feature extraction and color-ambiguity elimination, thereby advancing the accuracy of illuminant estimation. Simulations and experiments on benchmark datasets demonstrate that the proposed algorithm is effective for illuminant estimation compared to the state-of-the-art methods. Thus, ADCC offers great potential in promoting applications of smart cities, such as smart camera, where color is an important factor for distinguishing objects.