A5100672417- Advanced SAR Imaging Techniques
- CCD and CMOS Imaging Sensors
- Advanced Manufacturing and Logistics Optimization
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- UAV Applications and Optimization
- Assembly Line Balancing Optimization
- Environmental remediation with nanomaterials
- Image Retrieval and Classification Techniques
- Advanced Malware Detection Techniques
- Web Application Security Vulnerabilities
- Advanced Image Fusion Techniques
- Direction-of-Arrival Estimation Techniques
- Peer-to-Peer Network Technologies
- Remote Sensing in Agriculture
- AI in cancer detection
- Underwater Acoustics Research
- Heavy metals in environment
- Advanced Wireless Network Optimization
- Remote-Sensing Image Classification
- Advanced Photocatalysis Techniques
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Infrared Target Detection Methodologies
- Adsorption and biosorption for pollutant removal
- Urban and Freight Transport Logistics
Massachusetts General Hospital
2024
Harvard University
2024
Harbin Engineering University
2020-2024
National University of Defense Technology
2023-2024
Guangdong University of Technology
2011-2020
Ministry of Industry and Information Technology
2020
Xiangnan University
2020
Anhui Institute of Information Technology
2019
Beijing University of Chemical Technology
2018
Hunan University of Technology
2017
In this work, we report our solutions to the problems given in 2014 International Micro Aerial Vehicle Competition, held Delft, Netherlands, August 2014, which involves using micro air vehicles urban post-disaster search and rescue missions. Solutions all key mission elements of competition, including real-time map stitching, indoor navigation roof-top perching, are documented highlighted manuscript. The proposed successfully demonstrated competition help us win championship.
The method proposed in this letter for synthetic aperture radar (SAR) image classification has two main stages. In the first stage, a convolutional neural network (CNN) is trained normal SAR task. After training, sample features can be obtained by extracting output of middle layer forward propagation process CNN. second an end-to-end metric to measure relations between features. tested with some larger targets OpenSARShip data set which collected from Sentinel-1 satellite, and it also MSTAR...
We present the development and application of multiple autonomous aerial vehicles in urban search rescue missions. The missions are designed by 2014 International Micro Aerial Vehicle Competition, held Delft, Netherlands, August 2014. Different mission tasks identified for missions, such as photography, low altitude flight environment, indoor navigation rooftop landing. These all paramount importance rescuers a disaster-hit place. have team micro with specific configurations to meet...
In many manufacturing contexts, performance modelling of an integrated production and material handling system is a complex problem. Existing research lacks in-depth consideration the integration these two areas. A flexible flow shop with random state-dependent batch transport, where size depends on number jobs in buffers capacity automated guided vehicles, considered modelled as open queueing network blocking. decomposition method state space proposed for computing measures. The accuracy...
Currently, how to efficiently exploit useful information from multi-source remote sensing data for better Earth observation becomes an interesting but challenging problem. In this paper, we propose collaborative classification framework hyperspectral image (HSI) and Light Detection Ranging (LIDAR) via image-to-image convolutional neural network (CNN). There is mapping, learning a representation input source (i.e., HSI) output LIDAR). Then, the extracted features are expected own...
In this paper, we consider the problem of bistatic multiple- input multiple-output (MIMO) radar systems design for parameters estimation. Maximum channel capacity is used as criterion optimal under transmitted power constraint and constraint. We obtain that system based on maximum can be expressed a joint optimization problem. Given number transmit antenna, receive antenna signal-noise ratio (SNR), determined. This obtained from unique appropriate allocation placement strategy, which very...
Weak feature enhancement is an important and intractable issue in machine vision fields. In this paper, effective complex-scene inverse synthetic aperture radar (ISAR) image method proposed based on spatial neighborhood sparse constraint hybrid clustering oversegmentation (SNSC-HCOS). A superpixel concept first developed considering the consistency of pixel labels discrimination perturbations. The scattering characteristic similarity, proximity, information, sparsity bias, overall features...
Through the needs of Loading-Machine storage scheduling in forestry-pulp-paper production logistics intelligent distribution system, analysis model problems and improvement measures, put forward algorithm, based on ensuring feasibility scheduling, to rationalization, equalization, execute only, process optimization, realize through computer programming.
An retrieval algorithm based on dimensionality reduction is proposed to effectively extract the features improve performance of image retrieval. Firstly, most important properties subspaces with respect captured by intelligently utilizing similarity and dissimilarity information semantic geometric structure in database. Secondly, We propose Semi-supervised Orthogonal Discriminant Embedding Label Propagation method (SODELP) for The experimental results show that our has discrimination power...
A novel multi-object detection and tracking technology based on hexagonal opto-electronic detector is proposed, in which (1) a new detector, composed of 6 linear CCDs, has been firstly developed to achieve the field view 360 degree, (2) with high speed, object recognition criterions Object Signal Width Criterion (OSWC) Horizontal Scale Ratio (HSRC) are proposed. In this paper, Simulated Experiments have carried out verify validity proposed technology, show that can be achieved speed by using...
This paper describes the development status and key technologies of IPTV, discusses advantages video multicast basic theory multicast. Based on analysis idea stream scheduling strategy behavior characteristics user demand, mathematical model is established, performance evaluation parameters algorithm are proposed. The patch elaborated in detail. Two improved algorithms patching proposed, their analyzed through experiments.