HYBRID CASCADE STRUCTURE FOR LICENSE PLATE DETECTION IN LARGE VISUAL SURVEILLANCE SCENES

Abstract

Though license plate detection has been successfully applied in some commercial products, the detection of small and vague license plates in real applications is still an open problem. In this paper, we propose a novel hybrid cascade structure for fast detecting small and vague license plates in large and complex visual surveillance scenes. For rapid license plate candidate extraction, we propose two cascade detectors, including the Cascaded Color Space Transformation of Pixel detector and the Cascaded Contrast-Color Haar-like detector; these two cascade detectors can do coarse-to-fine detection in the front and in the middle of the hybrid cascade. In the end of the hybrid cascade, we propose a cascaded convolutional network structure (Cascaded ConvNet), including two detection- ConvNets and a calibration-ConvNet, which is designed to do fine detection. Through experiments with different evaluation data sets with many small and vague plates, we show that the proposed framework is able to rapidly detect license plates with different resolutions and different sizes in large and complex visual surveillance scenes.

Existing System

Region proposal network (RPN), Color Space Transformation of Pixel (CST-pixel), Gabor filters and discrete Fourier transform (DFT)

Proposed System

The presented LPD system can detect and extract license plates with different resolutions and different sizes in large and complex visual surveillance scenes. we design a hybrid cascade including three parts: the cascaded CST-pixel detector, the cascaded CC-Haarlike detector, and the cascaded ConvNet detector. Color Space Transformation of Pixel (CST-pixel), to transform color information into threshold-based weak classifiers that can be trained with AdaBoost method. CC-Haar-like features enhance the ability of expressing contrasted colors in license plates. The proposed cascaded ConvNet has a front detection- ConvNet, a calibration-ConvNet, and a back detection- ConvNet. The front detection-ConvNet is designed to reject part of the background subwindows. The calibration- ConvNet is designed to align the detection windows for further background rejection. The back detection-ConvNet is designed to do further detection of the subwindows after calibration.  

Architecture

BLOCK DIAGRAM