通知公告
首页 > 通知公告

2017 SJTU Summer Research Internship

发布时间:2017-06-14 浏览次数:119

2017 SJTU Summer Research Internship

Research Project Title:

1. Smart UAVs for Complicate Tasks in Complex scenes

2. Location Information Processing and Spatial Behavior Analysis.

3. Designing and Testing Services for Navigation Terminals

4. Design of high performance antennas using novel microwave structures and materials

5. Superpixel Generation for SAR Images Based on Probability Models

6. Design of real-time information processing technique for optical remote sensing

7. Compressive Sensing Based Tomographic SAR Imaging in Urban Environment

Internship Dates:

6 weeks

 

Language of Instruction: English

 

Background Information (Description and Objectives):

1. In complex scenes such as indoor environments, woods, canyons, caves, UAVs are extremely difficult to be manually controlled to accomplish complicate tasks like scouting and mapping. To solve this problem, NLS is developing a Smart UAV system that is designed to achieve autonomous flight in complex scenes carrying out complicate tasks.

2. With the increasing popularity of mobile terminals, location-based services (LBS) and car networking application, big data of different kinds including GIS data, trajectory data and location-involved searching records have been one of important strategic resources. Application of big data technology will provide deep insight about social running laws and its trends. It can enhance the service level of social position, providing intelligence support to optimize the government’s planning, disaster prevention and emergency response.

3. To manage high-precision position calibration in complex environments, NLS has proposed a new method of classifying and representing typical scenes in navigation and developed a new approach to analyzing their properties.

4. Modern wireless communication requires design of novel antennas with high performance such as increased gain and high directivity. To that end, the application of novel concepts such as metamaterials and gradient surfaces offers a promising possibility to enhance the performance of antennas. The project offers a chance for students to apply cutting edge microwave concept in the design of practical antennas.

5. Superpixel generation is a widely accepted idea for synthetic aperture radar (SAR) image understanding, which uses the spatial context of images. The superpixel is the elementary unit in the following processes, and can provide additional information for image understanding. In the current state, superpixel generation for SAR images is still an open problem. In this project, the student will develop a superpixel generation method for SAR images, which exploits the inherent statistical information of SAR images. The method should be suitable for both homogeneous and heterogeneous areas in the image. Particularly, the method should provide competitive performance in the heterogeneous areas, considering specific applications.

6. The objective of this project is to develop an on-board real-time processing system for remote sensing. The satellite constellation contains about 200 small optical satellites. For different applications, we focus on the developing of the following algorithms: Algorithms for remote sensing image pre-processing; Algorithms for remote sensing data compression; Algorithms for extraction of target of interesting.

7. A conventional space- or airborne synthetic apertureradar (SAR) maps the 3-D reflectivity distribution of a scene to be imaged into the 2-D azimuth–range (x−r) plane. This can be seen as a projection along the third radar coordinate, namely, elevation (s). Synthetic aperture radar tomography (TomoSAR)extends the synthetic aperture principle into the elevation direction for 3-D imaging. It uses stacks of several acquisitions from slightly different viewing angles (the elevation aperture) to reconstruct the reflectivity function along the elevation direction by means of spectral analysis for every azimuth–range pixel. This research project aims to demonstrate the tomographic potential and the achievable imaging quality on the basis of TerraSAR-X spotlight data of urban environment.

Main Tasks during the Internship:

1. Learn framework of smart UAVs during your internship and try to build a platform for running the time-consuming integrated navigation algorithms.

2. Learn how to reduce the amount of data and make it easily for analysis and so strengthen the semantic of the involving location data.

3. Learn to provide complete data service for GNSS signal analysis, which is of high precision acquisition, high precision calibration.

4. Familiarize with CAD microwave design tools and learn to use the CAD tool to design antennas using metamaterial concepts.

5. Understanding statistical modelling for SAR images. Developing a superpixel generation method for SAR images based on the statistical information. Evaluating the performance of the developed superpixel generation method, especially in the heterogeneous areas.

6. Get familiar with the various remote sensing processing technologies; Design remote sensing algorithms in DSP/FPGA platform;

7. Three-dimensional reconstruction of urban buildings based on TomoSAR.

In-Lab Instructional Hours*: Number of hours of structured instruction.

40 hours.

Outside Lab Learning Hours*: 10-20

Weekly group meeting and discussion are arranged on every Friday. Every student in the group are required to give a brief report of their recent work and then discuss the problems or issues that remain to be settled.

At the end of the month, there will be a regular seminar. Some students in the lab are chosen randomly to give a presentation about what they have learn. Everyone is required to attend this seminar so as to share their work experience and academic perception. After the seminar, there will be some leisure activities such as birthday party.

(留发中心会配合实验室,提供中国语言与文化的课程,每周6学时,4.5个小时,共六周,合计27个小时)

Required Skills for the Internship: Are there prerequisites, or is the Internship only open to certain fields of study?

  1. Attended courses of Electromagnetic Fields and Waves, Or Microwave Engineering.

2. Matlab, Digital Image Processing, Statistical Modeling

3. Basic knowledge of coding in C++; basic knowledge about remote sensing and signal processing; enrolled in a computer science program or an electrical engineering program.

 

Textbooks: May be divided into “required” and “recommended”.

Recommended:

1. A Byte of Python. Swaroop, C. H. 2005

2. Paolo Giudici, Silvia Figini, Applied Data Mining for Business and Industry, 2nd Edition, 2009.

3. A Byte of Python. Swaroop, C. H. 2005

4. Microwave Engineering, David Pozar, 2012

5. Digital Image Processing, by Rafael C. Gonzalez and Richard E. Woods (required), Processing of Synthetic Aperture Radar Images, by Henri Maitre (recommended)

6. Introduction to Remote Sensing, Fifth Edition, by James B. Campbell and Randolph H. Wynne

7. Digital Processing of synthetic aperture radar Data: Algorithms and Implementation; Synthetic Aperture Radar Imaging Simulated in MATLAB.

Grade Distribution:

        Attendance 30%

        Mid term presentation 30%

        Final written report 40%

 

Grading: Are students given a % or a letter grade? How is the final grade assessed and assigned?

Letter grade

Course Credit:  3

 

Instructor Name and Contact Information:

  1. Prof. Zou Danping, dpzou@sjtu.edu.cn
  2. Prof. Pan Changchun, pan_cc@sjtu.edu.cn
  3. Prof. Chen Xin, xin.chen@sjtu.edu.cn
  4. Prof. Li Dongying, Dongying.li@sjtu.edu.cn
  5. Dr. Liu Bin, bliu.rsti@sjtu.edu.cn
  6. Prof. He Jin, jinhe@sjtu.edu.cn
  7. Prof. Zhang Zenghui, zenghui.zhang.@sjtu.edu.cn

Website:

实验室网址 nls@sjtu.edu.cn, ast.sjtu.edu.cn

学院网址 http://www.seiee.sjtu.edu.cn/