Imperial College London
Alternate

DrTae-KyunKim

Faculty of Engineering, Department of Electrical and Electronic Engineering

Visiting Reader
 
 
 
//

Contact

 

+44 (0)20 7594 6317tk.kim Website

 
 
//

Location

 

1017Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Tejani:2018:10.1109/TPAMI.2017.2665623,
author = {Tejani, A and Kouskouridas, R and Doumanoglou, A and Tang, D and Kim, T-K},
doi = {10.1109/TPAMI.2017.2665623},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {119--132},
title = {Latent-Class Hough Forests for 6 DoF object pose estimation},
url = {http://dx.doi.org/10.1109/TPAMI.2017.2665623},
volume = {40},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - In this paper we present Latent-Class Hough Forests, a method for object detection and 6 DoF pose estimation in heavily cluttered and occluded scenarios. We adapt a state of the art template matching feature into a scale-invariant patch descriptor and integrate it into a regression forest using a novel template-based split function. We train with positive samples only and we treat class distributions at the leaf nodes as latent variables. During testing we infer by iteratively updating these distributions, providing accurate estimation of background clutter and foreground occlusions and, thus, better detection rate. Furthermore, as a by-product, our Latent-Class Hough Forests can provide accurate occlusion aware segmentation masks, even in the multi-instance scenario. In addition to an existing public dataset, which contains only single-instance sequences with large amounts of clutter, we have collected two, more challenging, datasets for multiple-instance detection containing heavy 2D and 3D clutter as well as foreground occlusions. We provide extensive experiments on the various parameters of the framework such as patch size, number of trees and number of iterations to infer class distributions at test time. We also evaluate the Latent-Class Hough Forests on all datasets where we outperform state of the art methods.
AU  - Tejani,A
AU  - Kouskouridas,R
AU  - Doumanoglou,A
AU  - Tang,D
AU  - Kim,T-K
DO  - 10.1109/TPAMI.2017.2665623
EP  - 132
PY  - 2018///
SN  - 0162-8828
SP  - 119
TI  - Latent-Class Hough Forests for 6 DoF object pose estimation
T2  - IEEE Transactions on Pattern Analysis and Machine Intelligence
UR  - http://dx.doi.org/10.1109/TPAMI.2017.2665623
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000417806000010&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/7845723
VL  - 40
ER  -
Download