Authors:
Marlon Marcon
1
;
Olga Regina Pereira Bellon
2
and
Luciano Silva
2
Affiliations:
1
Dapartment of Software Engineering, Federal University of Technology - Paraná, Dois Vizinhos, Brazil
;
2
Department of Computer Science, Federal University of Paraná, Curitiba, Brazil
Keyword(s):
Transfer Learning, 3D Computer Vision, Feature-based Registration, ICP Dense Registration, RGB-D Images.
Abstract:
Object recognition and 6DoF pose estimation are quite challenging tasks in computer vision applications. Despite efficiency in such tasks, standard methods deliver far from real-time processing rates. This paper presents a novel pipeline to estimate a fine 6DoF pose of objects, applied to realistic scenarios in real-time. We split our proposal into three main parts. Firstly, a Color feature classification leverages the use of pre-trained CNN color features trained on the ImageNet for object detection. A Feature-based registration module conducts a coarse pose estimation, and finally, a Fine-adjustment step performs an ICP-based dense registration. Our proposal achieves, in the best case, an accuracy performance of almost 83% on the RGB-D Scenes dataset. Regarding processing time, the object detection task is done at a frame processing rate up to 90 FPS, and the pose estimation at almost 14 FPS in a full execution strategy. We discuss that due to the proposal’s modularity, we could le
t the full execution occurs only when necessary and perform a scheduled execution that unlocks real-time processing, even for multitask situations.
(More)