Intelligent transportation systems are rapidly growing mainly due to active development of novel hardware and software solutions. In the paper a problem of automatical number plate detection is considered. An efficient two-step approach based on plate candidates extraction with further classification by neural network is proposed. Stroke width transform and contours detection techniques are utilized for the image preprocessing and extraction of regions of interest.
The number plate detection is a key step affecting the overall performance of the number plate recognition system. In the paper a novel algorithm for this purpose is proposed. The approach is based on the detection of text areas using the stroke width transform. More plate candidates are detected using the specifically developed image preprocessing scheme based on set of morphological operators and contour analysis.
Formation of high-resolution SAR images from light-weight platforms is a challenging task primarily due to high instability of such platforms. Additional difficulties are related with the precision of navigation systems. In the paper the problem of residual trajectory deviations are analyzed. An efficient trajectory reconstruction method is proposed. Important practical aspects of the developed approach are discussed. Considered ideas are incorporated into the SAR processing chain.
Multi-look processing is a well-known technique actively used in the SAR research community. In the paper, a method is described for the extraction of the ground moving targets parameters from a sequence of SAR look images obtained with a single-antenna SAR. The method calls for the automatic road extraction from the multi-look SAR images. The proposed road detection and location algorithm is based on the Canny edge detector and the histograms of image gradient directions.
Autofocusing is one of the key steps in the high-resolution SAR imaging. In the paper several important improvements to the recently developed local-quadratic map-drift autofocus are proposed. Important SAR image preprocessing steps applied before the local Doppler rate errors estimation are described. The weighting scheme for the evaluation of residual cross-track acceleration components is developed. It is illustrated that accounting of the local image contrast leads to better estimation precision.
The accuracy of trajectory measurements is one of the crucial factors in high-resolution SAR imaging. Common navigation systems often do not fulfill the requirements that results in significant image quality degradation. In the paper, a new autofocus algorithm for the reconstruction of the SAR platform trajectory deviations is proposed. The approach is based on the estimation of the Doppler rate errors on a sequence of short-time intervals.
Synthetic aperture radar is a popular instrument for high-resolution imaging. Usage of state-of-the-art image and signal processing solutions allows to significantly increase the efficiency of such systems. In the paper two important applications of computer vision algorithms are described. In particular, usage of local feature extraction algorithms for the radar image stitching. This results in the automatical panorama creation without usage of the navigation data.
Two modifications of the range-Doppler algorithm (RDA) have been proposed to solve problems of SAR platform motion instabilities. First, the multi-look processing based on the RDA with an extended Doppler bandwidth has been introduced for correction of radiometric errors. Second, the RDA has been modified to perform SAR image formation on short-time acquisition intervals to use it in a recently-developed local-quadratic map-drift autofocus (LQMDA) method.
The quality of high-resolution SAR imaging is strictly related with the precision of the platform trajectory measurements. This is one of the crucial points in the case of image formation from light-weight aircrafts and UAV platforms, which undergone significant trajectory instabilities in real flight conditions. In the paper, a new approach for the residual range-dependent phase error restoration is proposed. According to the method, the cross-track aircraft accelerations are evaluated via a specifically developed weighted estimation procedure.
In the paper, an X-band airborne SAR system developed and produced at the Institute of Radio Astronomy is described. The system is designed to be operated from light-weight aircrafts. Implemented hardware and real-time software solutions are discussed. Several original approaches to the post-processing of the recorded data are considered. Experimental results are also presented and discussed.