Detection-based object labeling in 3D scenes

By Kevin Lai, Liefeng Bo, Xiaofeng Ren, Dieter Fox. 2012

210 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): “[10] detect objects in 3D point clouds generated from multiple views of RGB-D data by running a 2D sliding window detector on each view over both the RGB and the depth data.”
Real-time grasp detection using convolutional neural networks (2014, background): “Robotic systems increasingly leverage RGB-D sensors and data for tasks like object recognition [8], detection [9] [10], and mapping [11] [12].”
Latent-Class Hough Forests for 3D Object Detection and Pose Estimation (2014, methodology): “In fact many representations use a combination of both modalities to achieve superior results [34, 42, 60].”
Multimodal deep learning for robust RGB-D object recognition (2015, background): “We also show robust object recognition in real- world environments and prove that noiseaware training is effective and improves recognition accuracy on the RGB-D Scenes dataset [16].”
RGBD Datasets: Past, Present and Future (2016, background): “Turntable datasets have been exploited in ‘natural’ scenes for tasks such as object detection [63] and discovery [31].”
Unsupervised feature learning for 3D scene labeling (2014, methodology): “We found that the system performs similarly to the detectionbased object labeling approach of [18].”
Robots That Use Language (2020, background): “can be broken down by level of specificity; we roughly categorize language at these different levels of abstraction as (a) general language about object characteristics, such as color, shape, or size (32, 160, 161); (b) descriptions of objects at the type, or categorymembership, level,which encompas”
Monocular SLAM Supported Object Recognition (2015, methodology): “Experiment 3: Scalable recognition and run-time evaluation In this section, we investigate the run-time performance of computing VLAD with integral histograms (FLAIR) for our system and compare against previously proposed approaches [24, 34].”
Dense Reconstruction Using 3D Object Shape Priors (2013, methodology): “We thus require a detection in at least two key-frames before proceeding to estimate the pose [12].”
Modeling 4D Human-Object Interactions for Event and Object Recognition (2013, methodology): “We compare our method with method HOG [1] and RDH which uses the RGBD HOG feature [6] in a sliding window way to detect objects.”
Kinect and RGBD Images: Challenges and Applications (2012, methodology): “[17] use a sliding window detectors trained from object views to define a probabilities of the window’s pixels belongs to objects classes previously defined.”
Learning Visually Guided Latent Actions for Assistive Teleoperation (2021, background): “Additional work has shown progress in learning visual representations end-to-end using task reward signals (Lai et al., 2012; Levine et al., 2016; Zhu et al., 2017; Yu et al., 2019), or through self-supervised encoding of play behavior (Wang et al.”
Aligning 3D models to RGB-D images of cluttered scenes (2015, background): “There have been corresponding works for RGB-D images studying the problems of object detection [4, 13, 17, 20, 21, 22, 24, 34, 35, 36], semantic segmentation [3, 12, 13, 19, 25, 32, 33], and more recently instance segmentation [13, 33].”
Learning hierarchical sparse features for RGB-(D) object recognition (2014, methodology): “(Bo et al., 2011b; Lai et al., 2012b) 80.7 In this section we demonstrate the applicability of our hierarchical feature learning approach to object detection.”
FPM: Fine Pose Parts-Based Model with 3D CAD Models (2014, background): “The recent availability of affordable depth sensors has also led to an increase in the use of RGB-D data [21,11,3,30,26] to extract various types of 3D information from scenes such as depth, object pose, and intrinsic images.”
Inferring 3D Object Pose in RGB-D Images (2015, background): “There have been corresponding works for RGB-D images studying the problem of object detection [17, 34, 20, 21, 35, 13, 33, 19, 23, 4], semantic segmentation [3, 12, 18, 24, 31, 13, 32], and more recently instance segmentation [13, 32].”