Garcia-Garcia, Alberto, Garcia-Rodriguez, Jose, Orts-Escolano, Sergio, Oprea, Sergiu, Gomez-Donoso, Francisco, Cazorla, Miguel
A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition
Computer Vision and Image Understanding. 2017, 164: 124-134. doi:10.1016/j.cviu.2017.06.006
URI: http://hdl.handle.net/10045/72633
DOI: 10.1016/j.cviu.2017.06.006
ISSN: 1077-3142 (Print)
Abstract: 
In this work, we carry out a study of the effect of adverse conditions, which characterize real-world scenes, on the accuracy of a Convolutional Neural Network applied to 3D object class recognition. Firstly, we discuss possible ways of representing 3D data to feed the network. In addition, we propose a set of representations to be tested. Those representations consist of a grid-like structure (fixed and adaptive) and a measure for the occupancy of each cell of the grid (binary and normalized point density). After that, we propose and implement a Convolutional Neural Network for 3D object recognition using Caffe. At last, we carry out an in-depth study of the performance of the network over a 3D CAD model dataset, the Princeton ModelNet project, synthetically simulating occlusions and noise models featured by common RGB-D sensors. The results show that the volumetric representations for 3D data play a key role on the recognition process and Convolutional Neural Network can be considerably robust to noise and occlusions if a proper representation is chosen.
Keywords:Deep learning, 3D object recognition, Convolutional neural networks, Noise, Occlusion, Caffe
Elsevier
info:eu-repo/semantics/article