Real-Time Drone Surveillance and Population Estimation of Marine Animals from Aerial Imagery

Saqib, M; Daud Khan, S; Sharma, N; Scully-Power, P; Butcher, P; Colefax, A; Blumenstein, M

Real-Time Drone Surveillance and Population Estimation of Marine Animals from Aerial Imagery

Saqib, M

Daud Khan, S Sharma, N

Scully-Power, P Butcher, P Colefax, A Blumenstein, M

Permalink

Publication Type:: Conference Proceeding
Citation:: International Conference Image and Vision Computing New Zealand, 2019, 2018-November
Issue Date:: 2019-02-04

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (552.58 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Saqib, M https://orcid.org/0000-0003-4374-0888	en_US
dc.contributor.author	Daud Khan, S	en_US
dc.contributor.author	Sharma, N https://orcid.org/0000-0003-0841-1245	en_US
dc.contributor.author	Scully-Power, P	en_US
dc.contributor.author	Butcher, P	en_US
dc.contributor.author	Colefax, A	en_US
dc.contributor.author	Blumenstein, M https://orcid.org/0000-0002-9908-3744	en_US
dc.date.available	2021-02-04T18:03:51Z
dc.date.issued	2019-02-04	en_US
dc.identifier.citation	International Conference Image and Vision Computing New Zealand, 2019, 2018-November	en_US
dc.identifier.isbn	9781728101255	en_US
dc.identifier.issn	2151-2191	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134579
dc.description.abstract	© 2018 IEEE. Video analysis is being rapidly adopted by marine biologists to asses the population and migration of marine animals. Manual analysis of videos by human observers is labor intensive and prone to error. The automatic analysis of videos using state-of-the-art deep learning object detectors provides a cost-effective way for the study of marine animals population and their ecosystem. However, there are many challenges associated with video analysis such as background clutter, illumination, occlusions, and deformation. Due to the high-density of objects in the images and sever occlusion, current state-of-the-art object often results in multiple detections. Therefore, customized Non-Maxima-Suppression is proposed after the detections to suppress false positives which significantly improves the counting and mean average precision of the detections. An end-to-end deep learning framework of Faster-RCNN [1] was adopted for detections with base architectures of VGG16 [2], VGGM [3] and ZF [4].	en_US
dc.relation.ispartof	International Conference Image and Vision Computing New Zealand	en_US
dc.relation.isbasedon	10.1109/IVCNZ.2018.8634661	en_US
dc.title	Real-Time Drone Surveillance and Population Estimation of Marine Animals from Aerial Imagery	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-November	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Strength - QSI - Centre for Quantum Software and Information
utslib.copyright.status	open_access	*
pubs.publication-status	Published	en_US
pubs.volume	2018-November	en_US

Abstract:

© 2018 IEEE. Video analysis is being rapidly adopted by marine biologists to asses the population and migration of marine animals. Manual analysis of videos by human observers is labor intensive and prone to error. The automatic analysis of videos using state-of-the-art deep learning object detectors provides a cost-effective way for the study of marine animals population and their ecosystem. However, there are many challenges associated with video analysis such as background clutter, illumination, occlusions, and deformation. Due to the high-density of objects in the images and sever occlusion, current state-of-the-art object often results in multiple detections. Therefore, customized Non-Maxima-Suppression is proposed after the detections to suppress false positives which significantly improves the counting and mean average precision of the detections. An end-to-end deep learning framework of Faster-RCNN [1] was adopted for detections with base architectures of VGG16 [2], VGGM [3] and ZF [4].

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/134579