Filtered-x least mean square(Fx-LMS) algorithm is popular in many adaptive processes. As its contradiction between convergence speed and stead-state error, the improvements of Fx-LMS algorithm with variable step size(...Filtered-x least mean square(Fx-LMS) algorithm is popular in many adaptive processes. As its contradiction between convergence speed and stead-state error, the improvements of Fx-LMS algorithm with variable step size(VSS) have been developed. To strengthen the robustness of variable step size least mean square(VSSLMS) algorithms to noise disturbance in active vibration control(AVC) application, nine VSSLMS algorithms are introduced in detail. Then an improved VSSLMS algorithm is proposed for better performance. At last, the performance of these VSSLMS algorithms are compared in AVC experimental system with different noise level. The experimental results verifies the effectiveness and robustness of the proposed VSSLMS algorithm in AVC application.展开更多
Curb detection provides road boundary information and is important to road detection.However,curb detection is challenging due to the problems such as various curb shapes,colour,discontinuity.In this work,a novel lear...Curb detection provides road boundary information and is important to road detection.However,curb detection is challenging due to the problems such as various curb shapes,colour,discontinuity.In this work,a novel learning-based method for curb detection is proposed using Lidar point clouds,considering that Lidars are not sensitive to illumination and are relatively stable to weather conditions.A deep neural network,named EdgeNet,is constructed and trained,which handles point clouds in an end-to-end way.After EdgeNet is properly trained,curb points are then segmented in the neural network output.In order to train,a curb point annotation algorithm is also designed to generate training dataset.The curb detection method works well with different road scenarios including intersections.The experimental results validate the effectiveness and robustness of this curb detection method.展开更多
基金Supported by the National Natural Science Foundation of China(No.51575328,61503232)the Shanghai Municipal Education Commission and Shanghai Education Development Foundation(No.15CG44)。
文摘Filtered-x least mean square(Fx-LMS) algorithm is popular in many adaptive processes. As its contradiction between convergence speed and stead-state error, the improvements of Fx-LMS algorithm with variable step size(VSS) have been developed. To strengthen the robustness of variable step size least mean square(VSSLMS) algorithms to noise disturbance in active vibration control(AVC) application, nine VSSLMS algorithms are introduced in detail. Then an improved VSSLMS algorithm is proposed for better performance. At last, the performance of these VSSLMS algorithms are compared in AVC experimental system with different noise level. The experimental results verifies the effectiveness and robustness of the proposed VSSLMS algorithm in AVC application.
基金Supported by the National Natural Science Foundation of China (No.51875331)。
文摘Curb detection provides road boundary information and is important to road detection.However,curb detection is challenging due to the problems such as various curb shapes,colour,discontinuity.In this work,a novel learning-based method for curb detection is proposed using Lidar point clouds,considering that Lidars are not sensitive to illumination and are relatively stable to weather conditions.A deep neural network,named EdgeNet,is constructed and trained,which handles point clouds in an end-to-end way.After EdgeNet is properly trained,curb points are then segmented in the neural network output.In order to train,a curb point annotation algorithm is also designed to generate training dataset.The curb detection method works well with different road scenarios including intersections.The experimental results validate the effectiveness and robustness of this curb detection method.
