High-accuracy 3D sensing for mobile manipulation: Improving object detection and door opening

By Morgan Quigley, Siddharth Batra, Stephen Gould, E. Klingbeil, Quoc V. Le, A. Wellman, Andrew Y. Ng. 2009

112 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Voting for Voting in Online Point Cloud Object Detection (2015, background): “As examples serve [14, 15] who in addition also take into account appearance information from a regular camera image.”
Contextually Guided Semantic Labeling and Search for 3D Point Clouds (2011, background): “Some earlier works Gould et al. (2008); Rusu et al. (2008); Dima et al. (2004); Quigley et al. (2009) have tried to combine shape and color information from multiple sensors for tasks such as object and obstacle detection.”
Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks (2016, background): “Recently, CNNs have been shown to be successful in object recognition [17,18], object detection [19], scene parsing [20,21] and scene classification [22–24].”
Convolutional-Recursive Deep Learning for 3D Object Classification (2012, background): “The depth modality provides useful extra information to the complex problem of general object detection [1] since depth information is invariant to lighting or color variations, provides geometrical cues and allows better separation from the background.”
A search-classify approach for cluttered indoor scene understanding (2012, methodology): “In recent years, object recognition has been explored using scanned depth information combined with texture(RGB-D) [Quigley et al. 2009; Lai and Fox 2010; Lai et al. 2011].”
Multimodal deep learning for robust RGB-D object recognition (2015, background): “cts. However, they are often difﬁcult to use in scenarios were 3D pose information about the object is required [6]. On the other hand, purely shapebased approaches are often useful for large objects [20], although they sometimes fail for small objects, e.g., apple, All authors are with the Departme”
Learning the dynamics of doors for robotic manipulation (2013, background): “1) Detecting Doors: Several methods for detecting doors [5], [6] and handles [7], [8], [9], [10] have been proposed in the literature.”
Detection-based object labeling in 3D scenes (2012, background): “While image-only object matching can work very well for textured objects [4], recent works on RGB-D perception combine both shape and color and show promising results for generic object detection [26], [19], [20].”
Contextually guided semantic labeling and search for three-dimensional point clouds (2013, background): “Some earlier works (Dima et al., 2004; Gould et al., 2008; Rusu et al., 2008; Quigley et al., 2009) have tried to combine shape and color information from multiple sensors for tasks such as object and obstacle detection.”
Unsupervised feature learning for 3D scene labeling (2014, background): “There is a large body of literature on 3D scene labeling in indoor environments ([1], [2], [3], [4], [5]).”
Efficient grasping from RGBD images: Learning using a new rectangle representation (2011, background): “(Other sensors can also obtain such a depth map/disparity image, such as [27] or [28].”
Indoor scene segmentation using a structured light sensor (2011, methodology): “[16] use a laser-line scanner to recognize several classes and aid a robotic door-opening task.”
Semantic Labeling of 3D Point Clouds for Indoor Scenes (2011, background): “The recent availability of synchronized videos of both color and depth obtained from RGB-D (Kinect-style) depth cameras, shifted the focus to making use of both visual as well as shape features for object detection [9, 18, 19, 24, 26] and 3D segmentation (e.”