A robust lane detection and tracking system based on monocular vision is presented in this paper.First,the lane detection algorithm can transform raw images into top view images by inverse perspective mapping(IPM),and...A robust lane detection and tracking system based on monocular vision is presented in this paper.First,the lane detection algorithm can transform raw images into top view images by inverse perspective mapping(IPM),and detect both inner sides of the lane accurately from the top view images.Then the system will turn to lane tracking procedures to extract the lane according to the information of last frame.If it fails to track the lane,lane detection will be triggered again until the true lane is found.In this system,θ-oriented Hough transform is applied to extract candidate lane markers,and a geometrical analysis of the lane candidates is proposed to remove the outliers.Additionally,vanishing point and region of interest(ROI)dynamically planning are used to enhance the accuracy and efficiency.The system was tested under various road conditions,and the result turned out to be robust and reliable.展开更多
Low dynamic range(LDR)images captured by consumer cameras have a limited luminance range.As the conventional method for generating high dynamic range(HDR)images involves merging multiple-exposure LDR images of the sam...Low dynamic range(LDR)images captured by consumer cameras have a limited luminance range.As the conventional method for generating high dynamic range(HDR)images involves merging multiple-exposure LDR images of the same scene(assuming a stationary scene),we introduce a learning-based model for single-image HDR reconstruction.An input LDR image is sequentially segmented into the local region maps based on the cumulative histogram of the input brightness distribution.Using the local region maps,SParam-Net estimates the parameters of an inverse tone mapping function to generate a pseudo-HDR image.We process the segmented region maps as the input sequences on long short-term memory.Finally,a fast super-resolution convolutional neural network is used for HDR image reconstruction.The proposed method was trained and tested on datasets including HDR-Real,LDR-HDR-pair,and HDR-Eye.The experimental results revealed that HDR images can be generated more reliably than using contemporary end-to-end approaches.展开更多
The inverse problem of determining two convection coefficients of an elliptic partial differential equation by Dirichlet to Neumann map is discussed.It is well known that this is a severely ill-posed problem with high...The inverse problem of determining two convection coefficients of an elliptic partial differential equation by Dirichlet to Neumann map is discussed.It is well known that this is a severely ill-posed problem with high nonlinearity.By the inverse scattering technique for first order elliptic system in the plane and the theory of generalized analytic functions,we give a constructive method for this inverse problem.展开更多
基金Supported by the National Natural Science Foundation of China(51005019)
文摘A robust lane detection and tracking system based on monocular vision is presented in this paper.First,the lane detection algorithm can transform raw images into top view images by inverse perspective mapping(IPM),and detect both inner sides of the lane accurately from the top view images.Then the system will turn to lane tracking procedures to extract the lane according to the information of last frame.If it fails to track the lane,lane detection will be triggered again until the true lane is found.In this system,θ-oriented Hough transform is applied to extract candidate lane markers,and a geometrical analysis of the lane candidates is proposed to remove the outliers.Additionally,vanishing point and region of interest(ROI)dynamically planning are used to enhance the accuracy and efficiency.The system was tested under various road conditions,and the result turned out to be robust and reliable.
基金This study was supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2018R1D1A1B07049932).
文摘Low dynamic range(LDR)images captured by consumer cameras have a limited luminance range.As the conventional method for generating high dynamic range(HDR)images involves merging multiple-exposure LDR images of the same scene(assuming a stationary scene),we introduce a learning-based model for single-image HDR reconstruction.An input LDR image is sequentially segmented into the local region maps based on the cumulative histogram of the input brightness distribution.Using the local region maps,SParam-Net estimates the parameters of an inverse tone mapping function to generate a pseudo-HDR image.We process the segmented region maps as the input sequences on long short-term memory.Finally,a fast super-resolution convolutional neural network is used for HDR image reconstruction.The proposed method was trained and tested on datasets including HDR-Real,LDR-HDR-pair,and HDR-Eye.The experimental results revealed that HDR images can be generated more reliably than using contemporary end-to-end approaches.
基金partly supported by the National Natural Science Foundation of China(Grant No.10271032)Shuguang Project and E-Institute of Shanghai Municipal Education Commission(N.E03004).
文摘The inverse problem of determining two convection coefficients of an elliptic partial differential equation by Dirichlet to Neumann map is discussed.It is well known that this is a severely ill-posed problem with high nonlinearity.By the inverse scattering technique for first order elliptic system in the plane and the theory of generalized analytic functions,we give a constructive method for this inverse problem.