Please use this identifier to cite or link to this item:
Title: Rain removal for object tracking in image sequence
Authors: Campbell, Calina Dionne Xiu Ping
Keywords: DRNTU::Engineering
Issue Date: 2013
Abstract: In this report, we will explore the various methods of rain detection with a number of real life motion images. With the use of Matlab’s Computer Vision Tool Box, algorithms are developed to apply different techniques of rain detection and subsequently rain removal on motion pictures. The objective of the project is to come out with a program which can detect rain apart from various objects in the video. The detection must have minimal false positives and negatives. Subsequently, the detected rain particles will be removed from the video, hence leaving the viewers with a clearer and sharper image. The main software used in the project was Matlab’s Computer Vision. It was used to write out algorithms for the various methods of rain detection such as the chromatic constraint, dynamic model constraint, and k-means constraint. The program was successful in telling apart rain particles from other objects in the video and subsequently removing it. A combination of the chromatic constraint and k-means constraint algorithm was developed and it improved the detection of rain.  
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
8.43 MBAdobe PDFView/Open

Page view(s) 20

Updated on Jun 14, 2024

Download(s) 50

Updated on Jun 14, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.