360o Imaging

2018 ELE Engineering Design Project (LG01)


Faculty Lab Coordinator

Ling Guan

Topic Category

Digital Signal Processing

Preamble

A 360-degree photo is a controllable panoramic image that surrounds the original point from which the shot was taken. 360-degree photos simulate being in the shoes of a photographer and looking around to the left, right, up and down as desired as well as sometimes zooming. The viewer clicks any point on the image to drag it in the desired direction. The key for 360o imaging is panoramic image stitching (PIS) which can be regarded as the reconstruction of plenoptic function at a given viewpoint, which is one of the main problems of image based rendering. In this project, students are required to develop a PIS system using machine intelligence and image analysis techniques and apply to 360o imaging.

Objective

The objective of this project is to develop a software system to generate panoramic images, which are insensitive to the ordering, orientation, scale and illumination of the input images as well as noise images those are not part of a panorama.

Partial Specifications

The PIS system to be developed should: (i) deploy on PC platform; (ii) capture pictures and stitch them in real time or near real time; (iii) potable to iOS platform for iPhone or iPad.

Suggested Approach

 Study the literature on machine intelligence, image matching, panoramic image stitching, and graphics rendering;
 Build a prototype with a camera capable of taking multiple pictures in 360o.
 Develop a PIS prototype with Open Source Computer Vision (OpenCV) library and C++ language;
 Test the prototype for typical utility conditions.

Group Responsibilities

This project will be carried out by a group of three students. It is expected that all three students are involved in all aspects of the project. Study the techniques/algorithms in machine learning, image analysis, and graphics rendering. The students will learn practical programming skills in C++ and objective-C, and get familiar with Open Source Computer Vision (OpenCV) library, iOS software development. They will also integrate the software with the camera system. All students are responsible for the demo and project report.

Student A Responsibilities

Software development and testing

Student B Responsibilities

Software development and testing

Student C Responsibilities

Hardware/software integration and testing

Course Co-requisites

hardware/software co-design, intelligent systems, image analysis

 


LG01: 360o Imaging | Ling Guan | Tuesday September 18th 2018 at 01:35 PM