Visual Subterranean Junction Recognition for MAVs based on Convolutional Neural Networks
作者： Sina Sharif Mansouri , Petros Karvelis , Christoforos Kanellakis , Anton Koval , George Nikolakopoulos
DOI: 10.1109/IECON.2019.8926916
关键词:
摘要: This article proposes a novel visual framework for detecting tunnel crossings/junctions in underground mine areas towards the autonomous navigation of Micro Aerial Vehicles (MAVs). Usually environments have complex geometries, including multiple crossings with different tunnels that challenge planning aerial robots. Towards envisioned scenario or semi-autonomous deployment MAVs limited Line-of-Sight subterranean environments, proposed module acknowledges existence junctions by providing crucial information to autonomy and layers vehicle. The capability junction detection is necessary majority mission scenarios, unknown area exploration, known inspection robot homing missions. method has ability feed image stream from vehicles on-board forward facing camera Convolutional Neural Network (CNN) classification architecture, expressed four categories: 1) left junction, 2) right 3) & 4) no local vicinity core contribution stems incorporation AlexNet transfer learning scheme branches environment. validity been validated through data-sets collected real demonstrating performance merits module.
sci-hub.se 参考文章(27)
Kevin P. Murphy, Machine Learning : A Probabilistic Perspective ,(2012)
Kristina Toutanova, Wen-tau Yih, John C. Platt, Christopher Meek, Learning Discriminative Projections for Text Similarity Measures conference on computational natural language learning. pp. 247- 256 ,(2011)
M.A. Hearst, S.T. Dumais, E. Osuna, J. Platt, B. Scholkopf, Support vector machines IEEE Intelligent Systems & Their Applications. ,vol. 13, pp. 18- 28 ,(1998) , 10.1109/5254.708428
M Sai Praneeth, Xudong Peng, Alice Li, Shahrzad Hosseini Vajargah, Going deeper with convolutions computer vision and pattern recognition. pp. 1- 9 ,(2015) , 10.1109/CVPR.2015.7298594
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, ImageNet: A large-scale hierarchical image database computer vision and pattern recognition. pp. 248- 255 ,(2009) , 10.1109/CVPR.2009.5206848
Ilya Sutskever, Geoffrey E. Hinton, Alex Krizhevsky, ImageNet Classification with Deep Convolutional Neural Networks neural information processing systems. ,vol. 25, pp. 1097- 1105 ,(2012)
Sinno Jialin Pan, Qiang Yang, A Survey on Transfer Learning IEEE Transactions on Knowledge and Data Engineering. ,vol. 22, pp. 1345- 1359 ,(2010) , 10.1109/TKDE.2009.191
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna, Rethinking the Inception Architecture for Computer Vision computer vision and pattern recognition. pp. 2818- 2826 ,(2016) , 10.1109/CVPR.2016.308
Hoo-Chang Shin, Holger R. Roth, Mingchen Gao, Le Lu, Ziyue Xu, Isabella Nogues, Jianhua Yao, Daniel Mollura, Ronald M. Summers, Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning IEEE Transactions on Medical Imaging. ,vol. 35, pp. 1285- 1298 ,(2016) , 10.1109/TMI.2016.2528162
Andreas Bircher, Mina Kamel, Kostas Alexis, Helen Oleynikova, Roland Siegwart, Receding horizon “next-best-view” planner for 3D exploration international conference on robotics and automation. pp. 1462- 1468 ,(2016) , 10.1109/ICRA.2016.7487281