Vehicle Color Classification Under Different Lighting Conditions Through Color Correction

Abstract

This paper presents a novel vehicle color classification technique for classifying vehicles into seven categories under different lighting conditions via color correction. First, to reduce lighting effects, a mapping function is built to minimize the color distortions between frames. In addition to color distortions, the effect of specular highlights can also make the window of a vehicle appear white and degrade the accuracy of vehicle classification. To reduce this effect, a window-removal task is performed to make vehicle pixels with the same color more concentrated on the analyzed vehicle. Thus, a vehicle can be more accurately classified into its corresponding category even when it is shone by strong sunlight. One major problem in vehicle color classification is that there are many shade colors; for example, white versus silver and black versus navy. Traditional methods lack the ability to classify vehicles with shade colors because a wrong classifier is designed by putting vehicles with the same label together even though their chromatic attributes are different. To treat this problem, a novel tree-based classifier is designed for classifying vehicles into chromatic/nonchromatic classes with their nonchromatic strengths and then into detailed color classes with their color features. The separation can significantly improve the accuracy of vehicle color classification even that vehicles are with various shade colors and captured under different lighting conditions. Index Terms-Vehicle color classification, color correction, SVM, vehicle window removal.

A new comparison framework to survey neural networks‐based vehicle detection and classification approaches

“…The majority of publications focused on ground vehicles, especially motor vehicles. There are various types of vehicles that are similar in lights, retina, and window shapes 14,51–53 . These issues pose several challenges to the VDC systems.…”

“…Machine learning methods are broadly classified into three groups: Supervised: In this category, all data are labeled and the algorithms learn to predict the output from the input data. Two popular supervised vehicle classification methods are convolution NNs (CNNs), 24,46,51,57,62,103,104 and SVM 2,52,105,106 Unsupervised: In this method, all data are unlabeled, and the algorithms learn to inherent structure from the input data.…”

A Review on Vehicle Classification and Potential Use of Smart Vehicle-Assisted Techniques

“…There are some other classifiers and learning machines that are also used for VC, such as forest tree [145] nearest neighbor [146][147][148], decision tree learning [149], extreme learning machine classifier [55], genetic fuzzy classifier, [150] kernel principal component classifier [151] and histogram-based nonlinear kernel classifier [38]. For the cases where multiple sensors are used for the detection and classification of vehicles, the data are fused.…”

“…The objective and purpose of this research is to study the capability of different vehicle-assisted techniques to extract the kinematic and physical characteristics of vehicles in real time and in a global manner. This information can be used for a wide variety of applications such as parking management, traffic control, safety, and accident avoidance [149].…”

A Gene Expression Programming Approach for Vehicle Body Segmentation and Color Recognition

“…To classify a car image regarding its color, several difficulties have to be overcome. Although it may look like a simple task for the human eye, it is a fundamental problem in computer vision, since the apparent color of a vehicle changes as a function of time, space, and light conditions [7].…”