Realtime tracking and grasping of a moving object from range video

2014 22nd International Conference on Pattern Recognition

Dellen

Torras

2014

Self Cite

Abstract-Detecting objects in cluttered scenes is a necessary step for many robotic tasks and facilitates the interaction of the robot with its environment. Because of the availability of efficient 3D sensing devices as the Kinect, methods for the recognition of objects in 3D point clouds have gained importance during the last years. In this paper, we propose a new supervised learning approach for the recognition of objects from 3D point clouds using Conditional Random Fields, a type of discriminative, undirected probabilistic graphical model. The various features and contextual relations of the objects are described by the potential functions in the graph. Our method allows for learning and inference from unorganized point clouds of arbitrary sizes and shows significant benefit in terms of computational speed during prediction when compared to a state-of-the-art approach based on constrained optimization.

Section: Results For Opcdmentioning

confidence: 99%

Recognizing Point Clouds Using Conditional Random Fields

2014 22nd International Conference on Pattern Recognition

Dellen

Torras

2014

Self Cite

“…To serve this purpose, the usage of RGB-D cameras is becoming ubiquitous, as they provide color images and dense depth maps of the scene. Tasks such as "picking up objects" and "planning manipulation actions" [1][2][3] are simplified once the precise location of objects in the scene is identified. One way to facilitate object localization is to perform pixelwise semantic labeling of the scene [4].…”

Section: Introductionmentioning

confidence: 99%

Combining Semantic and Geometric Features for Object Class Segmentation of Indoor Scenes

IEEE Robot. Autom. Lett.

Schulz

Dellen

et al. 2017

Self Cite

Abstract-Scene understanding is a necessary prerequisite for robots acting autonomously in complex environments. Low-cost RGB-D cameras such as Microsoft Kinect enabled new methods for analyzing indoor scenes and are now ubiquitously used in indoor robotics. We investigate strategies for efficient pixelwise object class labeling of indoor scenes that combine both pretrained semantic features transferred from a large color image dataset and geometric features, computed relative to the room structures, including a novel distance-from-wall feature, which encodes the proximity of scene points to a detected major wall of the room. We evaluate our approach on the popular NYU v2 dataset. Several deep learning models are tested, which are designed to exploit different characteristics of the data. This includes feature learning with two different pooling sizes. Our results indicate that combining semantic and geometric features yields significantly improved results for the task of object class segmentation.

“…One possible application for fast object discovery methods is robotic manipulation [1]. For complex indoor scenarios, object discovery still presents a challenge to current methods [2,3].…”

Section: Introductionmentioning

confidence: 99%

Semantic segmentation priors for object discovery

García

2016 23rd International Conference on Pattern Recognition (ICPR)

Schulz

et al. 2016

Self Cite

Abstract-Reliable object discovery in realistic indoor scenes is a necessity for many computer vision and service robot applications. In these scenes, semantic segmentation methods have made huge advances in recent years. Such methods can provide useful prior information for object discovery by removing false positives and by delineating object boundaries. We propose a novel method that combines bottom-up object discovery and semantic priors for producing generic object candidates in RGB-D images. We use a deep learning method for semantic segmentation to classify colour and depth superpixels into meaningful categories. Separately for each category, we use saliency to estimate the location and scale of objects, and superpixels to find their precise boundaries. Finally, object candidates of all categories are combined and ranked. We evaluate our approach on the NYU Depth V2 dataset and show that we outperform other state-of-the-art object discovery methods in terms of recall.