Effective Vehicle-Based Kangaroo Detection for Collision Warning Systems Using RCNN

https://www.ncbi.nlm.nih.gov/pubmed/29895804

Sensors (Basel). 2018 Jun 12;18(6). pii: E1913. doi: 10.3390/s18061913.

Effective Vehicle-Based Kangaroo Detection for Collision Warning Systems Using Region-Based Convolutional Networks.

Saleh K1, Hossny M2, Nahavandi S3.

Author information

1

Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, Victoria 3216, Australia. kaboufar@deakin.edu.au.

2

Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, Victoria 3216, Australia. mohammed.hossny@deakin.edu.au.

3

Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, Victoria 3216, Australia. saeid.nahavandi@deakin.edu.au.

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.

KEYWORDS:

collision avoidance; kangaroo collision; kangaroo dataset; kangaroo detection

PMID:

 

29895804

 

PMCID:

 

PMC6022154

 

DOI:

 

10.3390/s18061913

호주에서, 캥커루와 차량이랑 부딪히는 경우가 많으니까, RCNN ( region-based convolutional neural networks) 방법으로

캥커루를 미리 빨리 감지해서, 충돌 경고 시스템을 돌려서, 사고를 줄어보려고 하는 노력의 일환.

자율주행차도 같은 원리이고, 의학에도 응용할 수 있는 분야이기도 함. (실시간 동영상 분석 및 경고 시스템).

2018 Sensors _ Effective Vehicle-Based Kangaroo Detection (RCNN).pdf