Combined Holistic and Local Patches for Recovering 6D Object Pose

Haoruo Zhang, Qixin Cao; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2219-2227

Abstract


We present a novel method for recovering 6D object pose in RGB-D images. By contrast with recent holistic or local patch-based method, we combine holistic patches and local patches together to fulfil this task. Our method has three stages, including holistic patch classification, local patch regression and fine 6D pose estimation. Firstly, we apply a simple Convolutional Neural Network (CNN) to classify all the sampled holistic patches from the scene image. Then, the candidate region of target object can be segmented. Secondly, a Convolutional Autoencoder (CAE) is employed to extract condensed local patch feature, and coarse 6D object pose can be estimated by the regression of feature voting. Finally, we apply Particle Swarm Optimization (PSO) to refine 6D object pose. Our method is evaluated on the LINEMOD dataset and the Occlusion dataset. Experimental results show that our method has high precision and good performance under foreground occlusion and background clutter conditions.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhang_2017_ICCV,
author = {Zhang, Haoruo and Cao, Qixin},
title = {Combined Holistic and Local Patches for Recovering 6D Object Pose},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}