SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels

Xiao, Jianxiong; Owens, Andrew; Torralba, Antonio

doi:10.1109/iccv.2013.458

Cited by 680 publications

(475 citation statements)

References 20 publications

Supporting

Mentioning

473

Contrasting

Unclassified

Order By: Relevance

“…For more comprehensive comparisons, besides these 20 14 , from top left to bottom right is the chronological order from the video. The curves under the images are the accelerometer data at 50 Hz of devices attached to the knife, the mixing spoon, the small spoon, the peeler, the glass, the oil bottle, and the pepper dispenser mentioned datasets above, another 26 extra RGB-D datasets for different applications are also added into the tables: Birmingham University Objects, Category Modeling RGB-D [104], Cornell Activity [47,92], Cornell RGB-D [48], DGait [12], Daily Activities with occlusions [1], Heidelberg University Scenes [63], Microsoft 7-scenes [78], MobileRGBD [96], MPII Multi-Kinect [93], MSR Action3D Dataset [97], MSR 3D Online Action [103], MSRGesture3D [50], DAFT [31], Paper Kinect [70], RGBD-HuDaAct [68], Stanford Scene Object [44], Stanford 3D Scene [105], Sun3D [101], SUN RGB-D [82], TST Fall Detection [28], UTD-MHAD [14], Vienna University Technology Object [2], Willow Garage [99], Workout SU-10 exercise [67] and 3D-Mask [24]. In addition, we name those datasets without original names by means of creation place or applications.…”

Section: Discussionmentioning

confidence: 99%

RGB-D datasets using microsoft kinect or similar sensors: a survey

Cai

Han

Liu

et al. 2016

Multimed Tools Appl

123

View full text Add to dashboard Cite

RGB-D data has turned out to be a very useful representation of an indoor scene for solving fundamental computer vision problems. It takes the advantages of the color image that provides appearance information of an object and also the depth image that is immune to the variations in color, illumination, rotation angle and scale. With the invention of the low-cost Microsoft Kinect sensor, which was initially used for gaming and later became a popular device for computer vision, high quality RGB-D data can be acquired easily. In recent years, more and more RGB-D image/video datasets dedicated to various applications have become available, which are of great importance to benchmark the stateof-the-art. In this paper, we systematically survey popular RGB-D datasets for different applications including object recognition, scene classification, hand gesture recognition, 3D-simultaneous localization and mapping, and pose estimation. We provide the insights into the characteristics of each important dataset, and compare the popularity and the difficulty of those datasets. Overall, the main goal of this survey is to give a comprehensive description about the available RGB-D datasets and thus to guide researchers in the selection of suitable datasets for evaluating their algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

RGB-D datasets using microsoft kinect or similar sensors: a survey

Cai

Han

Liu

et al. 2016

Multimed Tools Appl

123

View full text Add to dashboard Cite

show abstract

“…Data must be combined and registered in the same coordinate system to obtain the complete model of the scene. On the other hand, the use of mobile mapping systems enables the collection of 3D data continuously [20,21]. These systems are based on the 3D positioning of the sensor together with 2D laser scanning.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Point Cloud Acquisition of Unknown Indoor Scenes

González-deSantos

Díaz-Vilariño

Balado

et al. 2018

IJGI

View full text Add to dashboard Cite

This paper presents a methodology for the automatic selection of heuristic scanning positions in unknown indoor environments. The surveying is carried out by a robotic system following a stop-and-go procedure. Starting with a random scan position in the room, the point cloud is discretized in voxels and they are submitted to a two-step classification and are labelled as occupied, occluded, empty, window, door, or exterior based on a visibility analysis. The main objective of the methodology is to obtain a complete point cloud of the indoor space and accordingly, the next best position is the scan position minimizing occluded voxels. Because the method locates doors and windows, the room can be delimited and the scan can continue for adjacent rooms. This approach has been tested in a real case study, in which three scans were developed.

show abstract

“…Recent approaches to 3D reconstruction have either used semantic information in a qualitative manner [1], or have only proposed to reconstruct indoor scenes using such information [5]. Only Yuan et al [7] propose to add semantic constraints for reconstruction.…”

Section: Semantic Constraints For Reconstructionmentioning

confidence: 99%

“…For example, reconstructing dynamic urban traffic scenes are useful since traffic patterns can be studied to produce autonomous vehicles that can better navigate such situations. Reconstructing dynamic objects are also useful in indoor environments when robots need to identify and avoid moving obstacles in their path [5].…”

Section: Introductionmentioning

confidence: 99%

Dynamic body VSLAM with semantic constraints

Reddy

Singhal

Chari

et al. 2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Image based reconstruction of urban environments is a challenging problem that deals with optimization of large number of variables, and has several sources of errors like the presence of dynamic objects. Since most large scale approaches make the assumption of observing static scenes, dynamic objects are relegated to the noise modeling section of such systems. This is an approach of convenience since the RANSAC based framework used to compute most multiview geometric quantities for static scenes naturally confine dynamic objects to the class of outlier measurements. However, reconstructing dynamic objects along with the static environment helps us get a complete picture of an urban environment. Such understanding can then be used for important robotic tasks like path planning for autonomous navigation, obstacle tracking and avoidance, and other areas.In this paper, we propose a system for robust SLAM that works in both static and dynamic environments. To overcome the challenge of dynamic objects in the scene, we propose a new model to incorporate semantic constraints into the reconstruction algorithm. While some of these constraints are based on multi-layered dense CRFs trained over appearance as well as motion cues, other proposed constraints can be expressed as additional terms in the bundle adjustment optimization process that does iterative refinement of 3D structure and camera / object motion trajectories. We show results on the challenging KITTI urban dataset for accuracy of motion segmentation and reconstruction of the trajectory and shape of moving objects relative to ground truth. We are able to show average relative error reduction by a significant amount for moving object trajectory reconstruction relative to state-ofthe-art methods like VISO 2[16], as well as standard bundle adjustment algorithms.

show abstract

SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels

Cited by 680 publications

References 20 publications

RGB-D datasets using microsoft kinect or similar sensors: a survey

RGB-D datasets using microsoft kinect or similar sensors: a survey

Autonomous Point Cloud Acquisition of Unknown Indoor Scenes

Dynamic body VSLAM with semantic constraints

Contact Info

Product

Resources

About