ML p(r)ior | Latent-Class Hough Forests for 6 DoF Object Pose Estimation

Latent-Class Hough Forests for 6 DoF Object Pose Estimation

2016-02-03
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.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2018-01-16
1801.05365 | cs.CV

We propose a deep learning-based solution for the problem of feature learning in one-class classific… show more
PDF

Highlights - Most important sentences from the article

2017-12-05

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and cla… show more
PDF

Highlights - Most important sentences from the article

2017-11-01

Estimating the 6D pose of known objects is important for robots to interact with the real world. The… show more
PDF

Highlights - Most important sentences from the article

2017-04-22

Image semantic segmentation is more and more being of interest for computer vision and machine learn… show more
PDF

Highlights - Most important sentences from the article

2018-07-25

Object counting is an important task in computer vision due to its growing demand in applications su… show more
PDF

Highlights - Most important sentences from the article

2017-11-24

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predict… show more
PDF

Highlights - Most important sentences from the article

2014-08-04
1408.0814 | cs.CV

We present a foveated object detector (FOD) as a biologically-inspired alternative to the sliding wi… show more
PDF

Highlights - Most important sentences from the article

2016-02-24

This paper focuses on the problem of script identification in scene text images. Facing this problem… show more
PDF

Highlights - Most important sentences from the article

2016-11-17

With the increasing performance of machine learning techniques in the last few years, the computer v… show more
PDF

Highlights - Most important sentences from the article

2015-04-07
1504.01639 | cs.CV

Lifelogging devices are spreading faster everyday. This growth can represent great benefits to devel… show more
PDF

Highlights - Most important sentences from the article

2019-04-29

We address the problem of finding a set of images containing a common, but unknown, object category … show more
PDF

Highlights - Most important sentences from the article

2018-03-19

As we move towards large-scale object detection, it is unrealistic to expect annotated training data… show more
PDF

Highlights - Most important sentences from the article

2018-12-06

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to … show more
PDF

Highlights - Most important sentences from the article

2017-11-27

We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB da… show more
PDF

Highlights - Most important sentences from the article

2018-05-28
1805.10917 | cs.LG

We consider the problem of anomaly detection in images, and present a new detection technique. Given… show more
PDF

Highlights - Most important sentences from the article