This article presents a computer vision system for real-time detection and robust recognition of speed limit signs, specially designed for intelligent vehicles. First, a new segmentation method is proposed to segment the image, and the CHT transformation (circle hog transform) is used to detect circles. Then, a new method based on local binary patterns is proposed to filter segmented images in order to reduce false alarms. In the classification phase, a cascading architecture of two linear support vector machines is proposed. The first is trained on the GTSRB dataset to decide whether the detected region is a speed limit sign or not, and the second is trained on the MNIST dataset to recognize the sign numbers. The system achieves a classification recall of 99.81% with a precision of 99.08% on the GTSRB dataset; in addition, the system is also tested on the BTSD and STS datasets, and it achieves a classification recall of 99.39% and 98.82% with a precision of 99.05% and 98.78%, respectively, within a processing time of 11.22 ms.

This article presents a computer vision system for real-time detection and robust recognition of speed limit signs, specially designed for intelligent vehicles. First, a new segmentation method is proposed to segment the image, and the CHT transformation (circle hog transform) is used to detect circles. Then, a new method based on local binary patterns is proposed to filter segmented images in order to reduce false alarms. In the classification phase, a cascading architecture of two linear support vector machines is proposed. The first is trained on the GTSRB dataset to decide whether the detected region is a speed limit sign or not, and the second is trained on the MNIST dataset to recognize the sign numbers. The system achieves a classification recall of 99.81% with a precision of 99.08% on the GTSRB dataset; in addition, the system is also tested on the BTSD and STS datasets, and it achieves a classification recall of 99.39% and 98.82% with a precision of 99.05% and 98.78%, respectively, within a processing time of 11.22 ms.

This article presents a computer vision system for real-time detection and robust recognition of speed limit signs, specially designed for intelligent vehicles. First, a new segmentation method is proposed to segment the image, and the CHT transformation (circle hog transform) is used to detect circles. Then, a new method based on local binary patterns is proposed to filter segmented images in order to reduce false alarms. In the classification phase, a cascading architecture of two linear support vector machines is proposed. The first is trained on the GTSRB dataset to decide whether the detected region is a speed limit sign or not, and the second is trained on the MNIST dataset to recognize the sign numbers. The system achieves a classification recall of 99.81% with a precision of 99.08% on the GTSRB dataset; in addition, the system is also tested on the BTSD and STS datasets, and it achieves a classification recall of 99.39% and 98.82% with a precision of 99.05% and 98.78%, respectively, within a processing time of 11.22 ms.

The resonant frequencies and bandwidths of the inverted rectangular patch over anisotropic substrates are investigated in this paper. A rigorous analysis is performed using dyadic Green’s function formulation in the vector Fourier transform domain. The Galerkin’s technic is then used in the resolution of the integral equation; the complex resonance frequencies for the TM01 mode are studied with sinusoidal basis functions. The numerical results obtained are compared with previously published numerical results computed by means of the electromagnetic simulator “IE3D software”. Good agreement is found in all cases among all sets of results. For an isotropic substrate, it is confirmed that the bandwidth decreases with increasing of air-gap layer for high permittivity and low thickness of the substrate. Also, we show that the resonant frequencies and bandwidths are highly dependent on the permittivity variations alongside the optical axis. Other theoretical results attained display that the resonant frequencies downtrend monotonically with increasing substrate thickness, the diminution being larger for the uniaxial anisotropy of the substrate. Finally, numerical results for the effects of uniaxial anisotropy in the substrate on the radiation of the inverted rectangular microstrip structure are also presented.

The resonant frequencies and bandwidths of the inverted rectangular patch over anisotropic substrates are investigated in this paper. A rigorous analysis is performed using dyadic Green’s function formulation in the vector Fourier transform domain. The Galerkin’s technic is then used in the resolution of the integral equation; the complex resonance frequencies for the TM01 mode are studied with sinusoidal basis functions. The numerical results obtained are compared with previously published numerical results computed by means of the electromagnetic simulator “IE3D software”. Good agreement is found in all cases among all sets of results. For an isotropic substrate, it is confirmed that the bandwidth decreases with increasing of air-gap layer for high permittivity and low thickness of the substrate. Also, we show that the resonant frequencies and bandwidths are highly dependent on the permittivity variations alongside the optical axis. Other theoretical results attained display that the resonant frequencies downtrend monotonically with increasing substrate thickness, the diminution being larger for the uniaxial anisotropy of the substrate. Finally, numerical results for the effects of uniaxial anisotropy in the substrate on the radiation of the inverted rectangular microstrip structure are also presented.

The resonant frequencies and bandwidths of the inverted rectangular patch over anisotropic substrates are investigated in this paper. A rigorous analysis is performed using dyadic Green’s function formulation in the vector Fourier transform domain. The Galerkin’s technic is then used in the resolution of the integral equation; the complex resonance frequencies for the TM01 mode are studied with sinusoidal basis functions. The numerical results obtained are compared with previously published numerical results computed by means of the electromagnetic simulator “IE3D software”. Good agreement is found in all cases among all sets of results. For an isotropic substrate, it is confirmed that the bandwidth decreases with increasing of air-gap layer for high permittivity and low thickness of the substrate. Also, we show that the resonant frequencies and bandwidths are highly dependent on the permittivity variations alongside the optical axis. Other theoretical results attained display that the resonant frequencies downtrend monotonically with increasing substrate thickness, the diminution being larger for the uniaxial anisotropy of the substrate. Finally, numerical results for the effects of uniaxial anisotropy in the substrate on the radiation of the inverted rectangular microstrip structure are also presented.