Nouranics

Nouranics

About this blog

Here you can find information about the things I work with, details of publications, projects, my resume, and software I have written as well slides from the subjects I used to teach.

On the use of Optical Flow for Scene Change Detection and Description

PublicationsPosted by navid nourani Thu, May 09, 2013 22:01:53

DOI: 10.1007/s10846-013-9840-8

Authors

N Nourani-Vatani, P VK Borges, J M Roberts, M V Srinivasan

Acceptance date

May 2013

Journal

Journal of Intelligent and Robotic Systems: Volume 74, Issue 3 (2014), Page 817-846

Abstract

We propose the use of optical flow information as a method for detecting and describing changes in the environment, from the perspective of a mobile camera. We analyze the characteristics of the optical flow signal and demonstrate how robust flow vectors can be generated and used for the detection of depth discontinuities and appearance changes at key locations. To successfully achieve this task, a full discussion on camera positioning, distortion compensation, noise filtering, and parameter estimation is presented. We then extract statistical attributes from the flow signal to describe the location of the scene changes. We also employ clustering and dominant shape of vectors to increase the descriptiveness. Once a database of nodes (where a node is a detected scene change) and their corresponding flow features is created, matching can be performed whenever nodes are encountered, such that topological localization can be achieved. We retrieve the most likely node according to the Mahalanobis and Chi-square distances between the current frame and the database. The results illustrate the applicability of the technique for detecting and describing scene changes in diverse lighting conditions, considering indoor and outdoor environments and different robot platforms.

Paper

The final publication is available at http://link.springer.com/article/10.1007%2Fs10846-013-9840-8

Videos

Scene change detection using optical flow, loop closure using SIFT, on a quad-copter:

Scene change detection and description using optical flow:



  • Comments(2)//robotics.nourani.dk/#post25

Euro Trip

NewsPosted by navid nourani Thu, May 09, 2013 21:52:21
ICRA is over, and it was great. So lovely to see and hang out with so many familiar faces.

Really enjoyed the fewer parallel track and massive poster sessions.

Btw, I'll be in Europe for a while visiting friends and colleagues so send me a line and we can potentially meet up! smiley

  • Comments(0)//robotics.nourani.dk/#post24

In the news

NewsPosted by navid nourani Wed, January 23, 2013 06:25:35
Our survey work at the Great Barrier Reef in December 2012 was featured in the national news on ABC smiley

http://www.abc.net.au/news/2012-12-21/robot-surveys-underwater-changes-on-the-great/4440952



  • Comments(0)//robotics.nourani.dk/#post23

Best student paper award

NewsPosted by navid nourani Tue, December 04, 2012 22:00:28
Our paper Automated species detection: An experimental approach to kelp detection from sea-floor AUV images won the best student paper award at ACRA 2012. Well done to Michael and the team smiley

  • Comments(0)//robotics.nourani.dk/#post22

Publish Or Perish

ResumePosted by navid nourani Tue, December 04, 2012 05:11:25

Navid Nourani-Vatani: all

Query date: 2012-12-04

Papers: 13
Citations: 75
Years: 8
Cites/year: 9.38
Cites/paper: 5.77/4.0/0 (mean/median/mode)
Cites/author: 27.91
Papers/author: 5.58
Authors/paper: 2.62/3.0/3 (mean/median/mode)
h-index: 5
g-index: 8
e-index: 6.08
hc-index: 5
hI-index: 1.67
hI,norm: 3
hm-index: 3.08
AW-index: 4.08
AWCR: 16.66
AWCRpA: 6.41
Hirsch a=3.00, m=0.63
Contemporary ac=2.68
1 paper(s) with 1 author(s)
4 paper(s) with 2 author(s)
7 paper(s) with 3 author(s)
1 paper(s) with 4 author(s)

  • Comments(0)//robotics.nourani.dk/#post21

ACRA 2012

NewsPosted by navid nourani Mon, December 03, 2012 23:57:25
At the Australasian Conference in Robotics and Automation (ACRA) in Wellington. There are some really interesting talks. Looking forward to reading the papers in detail.

HOWEVER, the most exciting part thus far is that Alberto Elfes, the father of occupancy grid maps, is charing a session with occupancy grid map papers!! How cool is that?

  • Comments(0)//robotics.nourani.dk/#post20

A Study of Feature Extraction Algorithms for Optical Flow Tracking

PublicationsPosted by navid nourani Tue, October 16, 2012 13:04:24

Authors

N. Nourani-Vatani, P. V.K. Borges, J. Roberts

Publication Date

Dec 2012

Conference

Australasian Conference of Robotics and Automation, Wellington, New Zealand

Abstract

Sparse optical flow algorithms, such as the Lucas-Kanade approach, provide more robustness to noise than dense optical flow algorithms and are the preferred approach in many scenarios. Sparse optical flow algorithms estimate the displacement for a selected number of pixels in the image. These pixels can be chosen randomly. However, pixels in regions with more variance between the neighbors will produce more reliable displacement estimates. The selected pixel locations should therefore be chosen wisely. In this study, the suitability of Harris corners, Shi-Tomasi’s “Good features to track”, SIFT and SURF interest point extractors, Canny edges, and random pixel selection for the purpose of frame-by-frame tracking using a pyramidical Lucas-Kanade algorithm is investigated. The evaluation considers the important factors of processing time, feature count, and feature trackability in indoor and outdoor scenarios using ground vehicles and unmanned areal vehicles, and for the purpose of visual odometry estimation.

Paper

Presentation

  • Comments(0)//robotics.nourani.dk/#post19

Automated species detection: An experimental approach to kelp detection from sea-floor AUV images

PublicationsPosted by navid nourani Tue, October 16, 2012 06:26:56

Authors

M.S. Bewley, B. Douillard, N. Nourani-Vatani, A. Friedman, O. Pizarro, S.B. Williams

Publication Date

Dec 2012

Conference

Australasian Conference of Robotics and Automation, Wellington, New Zealand

Abstract

This paper presents an experimental study of automated species detection systems suitable for use with Autonomous Underwater Vehicle (AUV) data. The automated detection systems presented in this paper use supervised learning; a support vector machine and local image features are used to predict the presence or ab- sence of Ecklonia Radiata (kelp) in sea floor images. A comparison study was done using a variety of descriptors (such as local binary patterns and principal component analysis) and image scales. The performance was tested on a large data set of images from 14 AUV missions, with more than 60,000 expert labelled points. The best performing model was then analysed in greater detail, to estimate performance on generalising to unseen AUV missions, and char- acterise errors that may impact the utility of the species detection system for marine scientists.

Paper

  • Comments(0)//robotics.nourani.dk/#post18
« PreviousNext »