A novel three-dimensional（3D） imaging lidar system which is based on a virtual instrument technique is introduced in this paper. The main characteristics of the system include： the capability of modeling a 3D objec...A novel three-dimensional（3D） imaging lidar system which is based on a virtual instrument technique is introduced in this paper. The main characteristics of the system include： the capability of modeling a 3D object in accordance with the actual one by connecting to a geographic information system（GIS）, and building the scene for the lidar experiment including the simulation environment. The simulation environment consists of four parts： laser pulse, atmospheric transport,target interaction, and receiving unit. Besides, the system provides an interface for the on-site experiment. In order to process the full waveform, we adopt the combination of pulse accumulation and wavelet denoising for signal enhancement.We also propose an optimized algorithm for data decomposition： the V-L decomposition method, which combines Vondrak smoothing and laser-template based fitting. Compared with conventional Gaussian decomposition, the new method brings an improvement in both precision and resolution of data decomposition. After applying V-L decomposition to the lidar system, we present the 3D reconstructed model to demonstrate the decomposition method.展开更多
This novel method of Pedestrian Tracking using Support Vector (PTSV) proposed for a video surveillance instrument combines the Support Vector Machine (SVM) classifier into an optic-flow based tracker. The traditional ...This novel method of Pedestrian Tracking using Support Vector (PTSV) proposed for a video surveillance instrument combines the Support Vector Machine (SVM) classifier into an optic-flow based tracker. The traditional method using optical flow tracks objects by minimizing an intensity difference function between successive frames, while PTSV tracks objects by maximizing the SVM classification score. As the SVM classifier for object and non-object is pre-trained, there is need only to classify an image block as object or non-ob-ject without having to compare the pixel region of the tracked object in the previous frame. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine scan in the classification stage. To accelerate the training of SVM, a Sequential Minimal Optimization Method (SMO) is adopted. The results of using a kernel-PTSV for pedestrian tracking from real time video are shown at the end. Comparative experimental results showed that PTSV improves the reliability of tracking compared to that of traditional tracking method using optical flow.展开更多
This paper takes advantage of the depth camera of somatosensory kinect and sensors to implement gesture recognition and design a virtual instrument system. As long as the user waves his arm without the help of other e...This paper takes advantage of the depth camera of somatosensory kinect and sensors to implement gesture recognition and design a virtual instrument system. As long as the user waves his arm without the help of other equipments, our system can automatically recognize the hand gesture and make suitable sound. In order to achieve depth camera's detection of hands movement,this paper introduce the depth imaging technology Light Coding and bone tracking technology to obtain the actual position information and hand movement information of the human body. Feet movement detection uses sensor technology, different stampede strength outputs different digital number after AD conversion so that the intensity can be controlled. A series of experiments show that the system has good fluency and practicality and increased the fun of playing instruments.展开更多
提出了基于瞬时频率估计(Instantaneous frequency estimation,IFE)实现旋转机械阶比跟踪的新方法,其优点是简化了阶比分析对硬件的要求,用软件的方法实现了阶比跟踪,仿真与实际测试试验验证了本方法的正确性。本方法实现了旋转机械非...提出了基于瞬时频率估计(Instantaneous frequency estimation,IFE)实现旋转机械阶比跟踪的新方法,其优点是简化了阶比分析对硬件的要求,用软件的方法实现了阶比跟踪,仿真与实际测试试验验证了本方法的正确性。本方法实现了旋转机械非平稳振动信号中参考轴瞬时转速的跟踪、估计算法,为阶比分析的实际应用提供了一种新方法,是对原有阶比跟踪技术的有力补充,特别适合于虚拟仪器发展的要求。展开更多
基金Project supported by the National Natural Science Foundation of China(Grant No.608320036)
文摘A novel three-dimensional（3D） imaging lidar system which is based on a virtual instrument technique is introduced in this paper. The main characteristics of the system include： the capability of modeling a 3D object in accordance with the actual one by connecting to a geographic information system（GIS）, and building the scene for the lidar experiment including the simulation environment. The simulation environment consists of four parts： laser pulse, atmospheric transport,target interaction, and receiving unit. Besides, the system provides an interface for the on-site experiment. In order to process the full waveform, we adopt the combination of pulse accumulation and wavelet denoising for signal enhancement.We also propose an optimized algorithm for data decomposition： the V-L decomposition method, which combines Vondrak smoothing and laser-template based fitting. Compared with conventional Gaussian decomposition, the new method brings an improvement in both precision and resolution of data decomposition. After applying V-L decomposition to the lidar system, we present the 3D reconstructed model to demonstrate the decomposition method.
文摘This novel method of Pedestrian Tracking using Support Vector (PTSV) proposed for a video surveillance instrument combines the Support Vector Machine (SVM) classifier into an optic-flow based tracker. The traditional method using optical flow tracks objects by minimizing an intensity difference function between successive frames, while PTSV tracks objects by maximizing the SVM classification score. As the SVM classifier for object and non-object is pre-trained, there is need only to classify an image block as object or non-ob-ject without having to compare the pixel region of the tracked object in the previous frame. To account for large motions between successive frames we build pyramids from the support vectors and use a coarse-to-fine scan in the classification stage. To accelerate the training of SVM, a Sequential Minimal Optimization Method (SMO) is adopted. The results of using a kernel-PTSV for pedestrian tracking from real time video are shown at the end. Comparative experimental results showed that PTSV improves the reliability of tracking compared to that of traditional tracking method using optical flow.
文摘This paper takes advantage of the depth camera of somatosensory kinect and sensors to implement gesture recognition and design a virtual instrument system. As long as the user waves his arm without the help of other equipments, our system can automatically recognize the hand gesture and make suitable sound. In order to achieve depth camera's detection of hands movement,this paper introduce the depth imaging technology Light Coding and bone tracking technology to obtain the actual position information and hand movement information of the human body. Feet movement detection uses sensor technology, different stampede strength outputs different digital number after AD conversion so that the intensity can be controlled. A series of experiments show that the system has good fluency and practicality and increased the fun of playing instruments.
文摘提出了基于瞬时频率估计(Instantaneous frequency estimation,IFE)实现旋转机械阶比跟踪的新方法,其优点是简化了阶比分析对硬件的要求,用软件的方法实现了阶比跟踪,仿真与实际测试试验验证了本方法的正确性。本方法实现了旋转机械非平稳振动信号中参考轴瞬时转速的跟踪、估计算法,为阶比分析的实际应用提供了一种新方法,是对原有阶比跟踪技术的有力补充,特别适合于虚拟仪器发展的要求。
