摘要 :
Since Qinghai is located in the high-altitude Qinghai-Tibet Plateau region, the geomorphological types are complex and diverse, and the distribution of ground precipitation observation stations is sparse, improving the accuracy of...
展开
Since Qinghai is located in the high-altitude Qinghai-Tibet Plateau region, the geomorphological types are complex and diverse, and the distribution of ground precipitation observation stations is sparse, improving the accuracy of precipitation data is critical for studying regional ecological change over time. In the paper, we study and construct a multi-source precipitation data fusion model based on neural networks, which consists of back propagation neural network (BPNN) and long short-term memory network (LSTM). The global precipitation measurement (GPM), fifth generation ECMWF atmospheric reanalysis (ERA5), digital elevation model (DEM), and normalized difference vegetation index (NDVI) data are selected as feature data and ground observation station data as label data for model training. The results show that the fused data generated by the BP-LSTM model reduces the root mean square error to 2.48mm and the overall relative bias to 0.25% compared with the original GPM, which is better than ERA5 on data accuracy. The precipitation event capture capability is improved, which is very close to the ERA5 data with strong precipitation event capture capability, and the probability of detection, false alarm rate, and missing event rate are 0.95, 0.53, and 0.04 respectively. Finally, the regional precipitation data is generated by the fusion model with resolution of 0.01°, lh. The model proposed in the paper incorporates topographic factors and seasonal characteristics to solve the temporal and spatial correlation of precipitation data in Qinghai Province improve the accuracy of precipitation data, and provide reliable data support for the study of regional hydro-ecological spatial and temporal variation patterns.
收起
摘要 :
This dissertation proposes a new approach for vehicular trajectory detecting. A radio-controlled quadcopter is used to shoot live traffic flow videos which can be flexible enough to meet the requirements of various road conditions...
展开
This dissertation proposes a new approach for vehicular trajectory detecting. A radio-controlled quadcopter is used to shoot live traffic flow videos which can be flexible enough to meet the requirements of various road conditions. A self-developed software is created to analyze traffic videos efficiently, which can extract the coordinate of each vehicle from the video and draw the trajectories of those vehicles automatically. The system only produces a relatively small bias, which is allowed in the practical field of traffic engineering. The proposed detection system can not only get the trajectory of vehicle conveniently, but also provide an easy way to collect the data on the velocity and the acceleration of vehicles and, even, set a foundation for driving behavior monitoring and analysis on the roads.
收起
摘要 :
This dissertation proposes a new approach for vehicular trajectory detecting. A radio-controlled quadcopter is used to shoot live traffic flow videos which can be flexible enough to meet the requirements of various road conditions...
展开
This dissertation proposes a new approach for vehicular trajectory detecting. A radio-controlled quadcopter is used to shoot live traffic flow videos which can be flexible enough to meet the requirements of various road conditions. A self-developed software is created to analyze traffic videos efficiently, which can extract the coordinate of each vehicle from the video and draw the trajectories of those vehicles automatically. The system only produces a relatively small bias, which is allowed in the practical field of traffic engineering. The proposed detection system can not only get the trajectory of vehicle conveniently, but also provide an easy way to collect the data on the velocity and the acceleration of vehicles and, even, set a foundation for driving behavior monitoring and analysis on the roads.
收起
摘要 :
An intelligent Synthetic Aperture Radar simulation system can be used to optimize SAR system parameters design and select optimum SAR data acquisition mode. Previous research has mainly focused on simulating geometric characterist...
展开
An intelligent Synthetic Aperture Radar simulation system can be used to optimize SAR system parameters design and select optimum SAR data acquisition mode. Previous research has mainly focused on simulating geometric characteristics of SAR image, lack of radiometric thinking in flat areas as it is a complicated problem. And the popular geometric model of Range Doppler Equations cannot apply to SAR sensor not launched as it relies on so many parameters contained in the original SAR data. In this paper we develop a new simulation system based on simplified geometric model and statistical radar scattering model for different thematic contents. It can generate simulated SAR image product at different band, polarization, incidence angle and resolution according to SAR user's need. As an experiment, a simulation example of ENVISAT ASAR is compared with the real data collected, to demonstrate the utility and correctness of the system.
收起
摘要 :
An intelligent Synthetic Aperture Radar simulation system can be used to optimize SAR system parameters design and select optimum SAR data acquisition mode. Previous research has mainly focused on simulating geometric characterist...
展开
An intelligent Synthetic Aperture Radar simulation system can be used to optimize SAR system parameters design and select optimum SAR data acquisition mode. Previous research has mainly focused on simulating geometric characteristics of SAR image, lack of radiometric thinking in flat areas as it is a complicated problem. And the popular geometric model of Range Doppler Equations cannot apply to SAR sensor not launched as it relies on so many parameters contained in the original SAR data. In this paper we develop a new simulation system based on simplified geometric model and statistical radar scattering model for different thematic contents. It can generate simulated SAR image product at different band, polarization, incidence angle and resolution according to SAR user's need. As an experiment, a simulation example of ENVISAT ASAR is compared with the real data collected, to demonstrate the utility and correctness of the system.
收起
摘要 :
In the society of PolSAR image segmentation, change detection and classification, the classical Wishart distribution has been used for a long time, but it especially suit to low-resolution SAR image, because in traditional sensors...
展开
In the society of PolSAR image segmentation, change detection and classification, the classical Wishart distribution has been used for a long time, but it especially suit to low-resolution SAR image, because in traditional sensors, only a small number of scatterers are present in each resolution cell. With the improving of SAR systems these years, the classical statistical models can therefore be reconsidered for high resolution and polarimetric information contained in the images acquired by these advanced systems. In this study, SAR image segmentation algorithm based on level-set method, added with distance regularized level-set evolution (DRLSE) is performed using Envisat/ASAR single-polarization data and Radarsat-2 polarimetric images, respectively. KummerU heterogeneous clutter model is used in the later to overcome the homogeneous hypothesis at high resolution cell. An enhanced distance regularized level-set evolution (DRLSE-E) is also applied in the later, to ensure accurate computation and stable level-set evolution. Finally, change detection based on four polarimetric Radarsat-2 time series images is carried out at Genhe area of Inner Mongolia Autonomous Region, NorthEastern of China, where a heavy flood disaster occurred during the summer of 2013, result shows the recommend segmentation method can detect the change of watershed effectively.
收起
摘要 :
In the society of PolSAR image segmentation, change detection and classification, the classical Wishart distribution has been used for a long time, but it especially suit to low-resolution SAR image, because in traditional sensors...
展开
In the society of PolSAR image segmentation, change detection and classification, the classical Wishart distribution has been used for a long time, but it especially suit to low-resolution SAR image, because in traditional sensors, only a small number of scatterers are present in each resolution cell. With the improving of SAR systems these years, the classical statistical models can therefore be reconsidered for high resolution and polarimetric information contained in the images acquired by these advanced systems. In this study, SAR image segmentation algorithm based on level-set method, added with distance regularized level-set evolution (DRLSE) is performed using Envisat/ASAR single-polarization data and Radarsat-2 polarimetric images, respectively. KummerU heterogeneous clutter model is used in the later to overcome the homogeneous hypothesis at high resolution cell. An enhanced distance regularized level-set evolution (DRLSE-E) is also applied in the later, to ensure accurate computation and stable level-set evolution. Finally, change detection based on four polarimetric Radarsat-2 time series images is carried out at Genhe area of Inner Mongolia Autonomous Region, NorthEastern of China, where a heavy flood disaster occurred during the summer of 2013, result shows the recommend segmentation method can detect the change of watershed effectively.
收起
摘要 :
With the development of agriculture, the protection of agricultural environment play s a critical role. Facing the status quo of unique environmental investment planning in our country's agriculture, through the existing theories ...
展开
With the development of agriculture, the protection of agricultural environment play s a critical role. Facing the status quo of unique environmental investment planning in our country's agriculture, through the existing theories and formulas, the functional model of the relationship between management investment and environmental loss is constructed, which is based on the monitoring data in many years. Then, the total optimized fund of environmental investment in agricultural projections will be determined from the aspect of optimization. In this paper, some useful help for optimizing investment structure are provided to solve the problems of environmental investment deficiency in our agriculture.
收起
摘要 :
This paper proposes a belief-updating scheme in a human-machine collaborative decision-making network to com-bat Byzantine attacks. A hierarchical framework is used to realize the network where local decisions from physical sensor...
展开
This paper proposes a belief-updating scheme in a human-machine collaborative decision-making network to com-bat Byzantine attacks. A hierarchical framework is used to realize the network where local decisions from physical sensors act as reference decisions to improve the quality of human sensor decisions. During the decision-making process, the belief that each physical sensor is malicious is updated. The case when humans have side information available is investigated, and its impact is analyzed. Simulation results substantiate that the proposed scheme can significantly improve the quality of human sensor decisions, even when most physical sensors are malicious. Moreover, the performance of the proposed method does not necessarily depend on the knowledge of the actual fraction of malicious physical sensors. Consequently, the proposed scheme can effectively defend against Byzantine attacks and improve the quality of human sensors' decisions so that the performance of the human-machine collaborative system is enhanced.
收起