Effective vehicle-based kangaroo detection for collision warning systems using region-based convolutional networks Saleh, Khaled, Hossny, Mohammed and Nahavandi, Saeid 2018, Effective vehicle-based kangaroo detection for collision warning systems using region-based convolutional networks, Sensors, vol. 18, no. 6, pp. 1-15, doi: 10.3390/s18061913. Attached Files Name Description MIMEType Size Downloads nahavandi-effectivevehicle-2018.pdf Published version application/pdf 2.35MB 9 Title Effective vehicle-based kangaroo detection for collision warning systems using region-based convolutional networks Author(s) Saleh, Khaled Hossny, Mohammed orcid.org/0000-0002-1593-6296 Nahavandi, Saeid orcid.org/0000-0002-0360-5270 Journal name Sensors Volume number 18 Issue number 6 Article ID 1913 Start page 1 End page 15 Total pages 15 Publisher MDPI Place of publication Basel, Switzerland Publication date 2018-06-12 ISSN 1424-8220 Keyword(s) kangaroo collision kangaroo detection collision avoidance kangaroo dataset Accidents, Traffic Animals Macropodidae Neural Networks (Computer) Support Vector Machine Science & Technology Physical Sciences Technology Chemistry, Analytical Electrochemistry Instruments & Instrumentation Chemistry Summary Traffic collisions between kangaroos and motorists are on the rise on Australian roads. According to a recent report, it was estimated that there were more than 20,000 kangaroo vehicle collisions that occurred only during the year 2015 in Australia. In this work, we are proposing a vehicle-based framework for kangaroo detection in urban and highway traffic environment that could be used for collision warning systems. Our proposed framework is based on region-based convolutional neural networks (RCNN). Given the scarcity of labeled data of kangaroos in traffic environments, we utilized our state-of-the-art data generation pipeline to generate 17,000 synthetic depth images of traffic scenes with kangaroo instances annotated in them. We trained our proposed RCNN-based framework on a subset of the generated synthetic depth images dataset. The proposed framework achieved a higher average precision (AP) score of 92% over all the testing synthetic depth image datasets. We compared our proposed framework against other baseline approaches and we outperformed it with more than 37% in AP score over all the testing datasets. Additionally, we evaluated the generalization performance of the proposed framework on real live data and we achieved a resilient detection accuracy without any further fine-tuning of our proposed RCNN-based framework. Language eng DOI 10.3390/s18061913 Indigenous content off Field of Research 080106 Image Processing 0906 Electrical and Electronic Engineering Socio Economic Objective 880109 Road Safety HERDC Research category C1 Refereed article in a scholarly journal Copyright notice ©2018, The Authors Free to Read? Yes Use Rights Persistent URL http://hdl.handle.net/10536/DRO/DU:30110956 Document type: Journal Article Collections: Centre for Intelligent Systems Research Open Access Collection Related Links Link Description Connect to published version (open access) Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au. Versions Version Filter Type Thu, 12 Jul 2018, 09:48:16 EST Fri, 13 Jul 2018, 05:01:00 EST Fri, 13 Jul 2018, 08:15:38 EST Sat, 18 Aug 2018, 02:31:23 EST Wed, 17 Oct 2018, 07:36:14 EST Wed, 17 Oct 2018, 07:45:39 EST Mon, 04 Mar 2019, 13:47:41 EST Mon, 04 Mar 2019, 13:48:38 EST Mon, 04 Mar 2019, 13:50:35 EST Wed, 19 Jun 2019, 06:02:30 EST Tue, 25 Jun 2019, 16:07:32 EST Tue, 25 Jun 2019, 16:09:26 EST Tue, 25 Jun 2019, 16:10:00 EST Thu, 05 Sep 2019, 10:04:18 EST Filtered Full Citation counts:   Cited 1 times in TR Web of Science Cited 1 times in Scopus Search Google Scholar Access Statistics: 62 Abstract Views, 11 File Downloads  -  Detailed Statistics Created: Mon, 04 Mar 2019, 13:50:35 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.