Authors:
Xiao Lin
1
;
Josep R. Casas
2
and
Montse Pardàs
2
Affiliations:
1
Industry and Advanced Manufacturing Department, Vicomtech, San Sebastian, Spain, Image Processing Group (GPI), Universitat Politécnica de Catalunya, Barcelona and Spain
;
2
Image Processing Group (GPI), Universitat Politécnica de Catalunya, Barcelona and Spain
Keyword(s):
Instance Segmentation, One Shot Learning, Convolutional Neural Network.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
Abstract:
Hand-crafted features employed in classical generic instance segmentation methods have limited discriminative power to distinguish different objects in the scene, while Convolutional Neural Networks (CNNs) based semantic segmentation is restricted to predefined semantics and not aware of object instances. In this paper, we combine the advantages of the two methodologies and apply the combined approach to solve a generic instance segmentation problem in RGBD video sequences. In practice, a classical generic instance segmentation method is employed to initially detect object instances and build temporal correspondences, whereas instance models are trained based on the few detected instance samples via CNNs to generate robust features for instance segmentation. We exploit the idea of one shot learning to deal with the small training sample size problem when training CNNs. Experiment results illustrate the promising performance of the proposed approach.