An Integrative Approach to Accurate Vehicle Logo Detection

Abstract

Vehicle logo detection from images captured by surveillance cameras is an important step towards the vehicle recognition that is required for many applications in intelligent transportation systems and automatic surveillance. The task is challenging considering the small target of logos and the wide range of variability in shape, color, and illumination. A fast and reliable vehicle logo detection approach is proposed following visual attention mechanism from the human vision. Two prelogo detection steps, that is, vehicle region detection and a small RoI segmentation, rapidly focalize a small logo target. An enhanced Adaboost algorithm, together with two types of features of Haar and HOG, is proposed to detect vehicles. An RoI that covers logos is segmented based on our prior knowledge about the logos' position relative to license plates, which can be accurately localized from frontal vehicle images. A two-stage cascade classier proceeds with the segmented RoI, using a hybrid of Gentle Adaboost and Support Vector Machine (SVM), resulting in precise logo positioning. Extensive experiments were conducted to verify the efficiency of the proposed scheme.

Vehicle Logo Detection Method Based on Improved YOLOv4

“…After extracting the features, the classification and recognition of the vehicle logo were achieved through machine learning methods. Pan et al [10] proposed a fast and reliable vehicle logo detection method, which included three steps: vehicle region detection, small ROI segmentation, and logo detection. Firstly, the improved AdaBoost algorithm was used to extract the vehicle region from the input image, and the ROI was segmented from the detected vehicle.…”

MSER-Vertical Sobel for Vehicle Logo Detection

“…The logo area is set at the center of the five sections. In [2], they started searching for the logo by finding the car's position using the Viola-Jones method. Furthermore, the car number plate is searched by performing edge extraction and histogram analysis.…”

“…Histogram of Oriented Gradient (HOG) feature and Adaboost are used to detect logos on ROI. Both [1] and [2] can only detect logos located exactly above a license plate. Some researchers try to combine the use of local features and global representation to find the logo area.…”