Abstract
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.
Highlights
The kangaroo detection problem on Australian traffic environments has received some attention from both research communities and car manufacturers—with the recent reports of the increased number of accidents happening on the Australian roads due to collision betweenKangaroos and human-driven vehicles [1]
In order to evaluate the performance of our proposed framework in real-life scenes of kangaroos and examine the feasibility our proposed framework to generalize to other real and live unseen scenes of kangaroo, we collected more than 250 real depth images of kangaroo in an urban traffic environment using the Microsoft Kinect sensor during night time
The first baseline is one of the most proposed approaches in the literature for the task of wild animal detection in general, and it is a combination between feature extractor, Histogram of Oriented Gradient (HOG) and the Support Vector Machines (SVM) classifier, which is pretty similar to the ones proposed in [9,18] for deer and moose detection, respectively
Summary
The kangaroo detection problem on Australian traffic environments has received some attention from both research communities and car manufacturers—with the recent reports of the increased number of accidents happening on the Australian roads due to collision betweenKangaroos and human-driven vehicles [1]. The kangaroo detection problem on Australian traffic environments has received some attention from both research communities and car manufacturers—with the recent reports of the increased number of accidents happening on the Australian roads due to collision between. The conflict exists between human-driven vehicles and kangaroos. The efforts that have been made to prevent or reduce the number of collisions happening between vehicles and other wild animals such as deer and moose could be categorized into two main categories, namely road-based techniques and vehicle-based techniques. Vehicle-based techniques rely either on passive sensors externally mounted on top of the vehicles or on the tremendous amount of active sensors that exist nowadays in most of the newly released vehicles in order to deter or detect wild animals. External passive sensors mounted on the vehicles that were used to keep wild animals away from the vehicles include high pitched
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
