19,906 Hits in 6.6 sec

Detecting planar surface using a light-field camera with application to distinguishing real scenes from printed photos

Alireza Ghasemi, Martin Vetterli
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We propose a novel approach for detecting printed photos from natural scenes using a light-field camera.  ...  Our approach exploits the extra information captured by a light-field camera and the multiple views of scene in order to infer a compact feature vector from the variance in the distribution of the depth  ...  Detecting Flat Surfaces Using the EPI Information Suppose we capture two images using a light-field camera from the two seces in the Figure 1 .  ... 
doi:10.1109/icassp.2014.6854471 dblp:conf/icassp/GhasemiV14 fatcat:65hksunyojbe5jour3byywh32m

Applications of Human Motion Tracking: Smart Lighting Control

Sung Yong Chun, Chan-Su Lee
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
Multiple depth cameras were used to detect human subject motion in a large area.  ...  The activity modes can be estimated using the human motion tracking results from depth cameras and from thermal cameras.  ...  Human detection and location estimation from a thermal camera: Thermal information is used to detect human subject similar to the depth information.  ... 
doi:10.1109/cvprw.2013.65 dblp:conf/cvpr/ChunL13 fatcat:uu3l3gejejax5bwp5iygfbxqim

Globally Consistent Indoor Mapping via a Decoupling Rotation and Translation Algorithm Applied to RGB-D Camera Output

Yuan Liu, Jun Wang, Jingwei Song, Zihui Song
2017 ISPRS International Journal of Geo-Information  
As the consumer RGB-D camera provides a noisy depth image, the proposed algorithm decouples the rotation and translation for a more robust camera pose estimation, which makes full use of the information  ...  The uncertainty in the image depth is not only related to the camera device, but also the environment; hence, a novel uncertainty model for depth measurements was developed using Gaussian mixture applied  ...  (a) An RGB image from the camera; (b) a depth image from the camera; (c) a result from the uncertainty model using independent pixel methods; (d) a result from the uncertainty model using our method.  ... 
doi:10.3390/ijgi6110323 fatcat:mzarwvhtojgybezildnmwsqzhq

Depth image-based plane detection

Zhi Jin, Tammam Tillo, Wenbin Zou, Xia Li, Eng Gee Lim
2018 Big Data Analytics  
In this paper, we propose a robust Depth Image-based Plane Detection (DIPD) algorithm.  ...  The proposed approach starts from the highest planarity seed patch, and uses the estimated equation of the growing plane and a dynamic threshold function to steer the growing process.  ...  Cang Ye from the Department of Systems Engineering, University of Arkansas for their helpful technical support.  ... 
doi:10.1186/s41044-018-0035-y fatcat:4kkcooj5ovct7a656k5ugeso6y

Automatic Detection of Emotion Valence on Faces Using Consumer Depth Cameras

Arman Savran, Ruben Gur, Ragini Verma
2013 2013 IEEE International Conference on Computer Vision Workshops  
In this paper, we present the first practical 3D expression recognition using cheap consumer depth cameras.  ...  Experiments show that using only low fidelity 3D data of consumer cameras, we get 77.4% accuracy in emotion valence detection.  ...  Conclusion We have established the use of 3D data from consumer depth cameras for automated recognition of facial expressions, by demonstrating their applicability on the affect valence detection problem  ... 
doi:10.1109/iccvw.2013.17 dblp:conf/iccvw/SavranGV13 fatcat:ff6c6k3mcfea7m7eh64qnzxfca

A real-time system for object detection and location reminding with RGB-D camera

I-Kuei Chen, Chung-Yu Chi, Szu-Lu Hsu, Liang-Gee Chen
2014 2014 IEEE International Conference on Consumer Electronics (ICCE)  
The introduced method uses RGB-D information as input and has high detection rate in messy indoor environments.  ...  This paper presents a helpful application with a real-time detection system that can automatically capture the last scene where the user-defined important objects appear.  ...  INTRODUCTION In recent years, there has been increasing interests in using RGB-D information from video sequences for object detection.  ... 
doi:10.1109/icce.2014.6776063 dblp:conf/iccel/ChenCHC14 fatcat:ag4ih6jai5dcbigynfyzjvphje

Real-Time Multiple Human Perception With Color-Depth Cameras on a Mobile Robot

Hao Zhang, Christopher Reardon, Lynne E. Parker
2013 IEEE Transactions on Cybernetics  
Here we present a system for 3-D multiple human perception in real time from a moving robot equipped with a color-depth camera and a consumer-grade computer.  ...  Index Terms-3-D vision, depth of interest, human detection and tracking, human perception, RGB-D camera application.  ...  Our results showed that through use of depth information and modern techniques in some new ways, it is possible to use a color-depth camera to create an accurate, robust system of real-time, 3-D perception  ... 
doi:10.1109/tcyb.2013.2275291 pmid:23974672 fatcat:lxvhndn7ljaejm252pkex4dvo4

High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review

Jianwei Li, Wei Gao, Yihong Wu, Yangdong Liu, Yanfei Shen
2022 Computational Visual Media  
As depth images produced by consumer RGB-D cameras are noisy and incomplete when surfaces are shiny, bright, transparent, or far from the camera, obtaining high-quality 3D scene models is still a challenge  ...  The advent of consumer RGB-D cameras has made a profound advance in indoor scene reconstruction.  ...  Sparse-to-dense [77] first introduced a robust and accurate depth estimation method from RGB images with additional sparse depth samples acquired from a low-resolution depth sensor; it was used in a  ... 
doi:10.1007/s41095-021-0250-8 fatcat:z6ywcn4zujbptjaqrwkwhoyquu

Automatic registration of LiDAR and optical imagery using depth map stereo

Hyojin Kim, Carlos D. Correa, Nelson Max
2014 2014 IEEE International Conference on Computational Photography (ICCP)  
A number of algorithms are based on 2D-3D registration using feature detection from both 3D LiDAR and 2D optical imagery. The features are collected by detecting specific  ...  The proposed algorithm is based on feature correspondence between a LiDAR depth map and a depth map from an optical image.  ...  In order to generate a ground-based stereo depth map, we perform ground plane estimation and alignment by finding a dominant plane of the reconstructed scene using RANSAC-based plane fitting.  ... 
doi:10.1109/iccphot.2014.6831821 dblp:conf/iccp/KimCM14 fatcat:w2gegbxbc5egzhnxuklhhmkwte

Depth image enhancement using local tangent plane approximations

Kiyoshi Matsuo, Yoshimitsu Aoki
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper describes a depth image enhancement method for consumer RGB-D cameras. Most existing methods use the pixel-coordinates of the aligned color image.  ...  To improve enhancement accuracy, we use local tangent planes as local coordinates for the measured surfaces.  ...  In this work, to detect surface regions, local tangent planes were estimated from a pair comprising a low-resolution depth image and aligned color image. Our work is an improvement of this work.  ... 
doi:10.1109/cvpr.2015.7298980 dblp:conf/cvpr/MatsuoA15 fatcat:l5727hw4wfcl7gnxn2daheg4xq

Capture and Dewarping of Page Spreads with a Handheld Compact 3D Camera

Michael P. Cutter, Patrick Chiu
2012 2012 10th IAPR International Workshop on Document Analysis Systems  
A Fujifilm consumer grade 3D camera provides a highly mobile and low-cost 3D capture device.  ...  We address this problem by computing curve profiles of the depth map and using them to build a cylinder model of the pages.  ...  These methods require highly accurate 3D information and are difficult to use with low-cost consumer grade stereo cameras.  ... 
doi:10.1109/das.2012.24 dblp:conf/das/CutterC12 fatcat:k74albh4xnfn5jlwnxtacqy4hy

Cluster tracking with Time-of-Flight cameras

Dan Witzner, Hansen Mads, Syska Hansen, Martin Kirschmeyer, Rasmus Larsen, Davide Silvestre
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
A background model is built by fusing information from intensity and depth images.  ...  We describe a method for tracking people using a Timeof-Flight camera and apply the method for persistent authentication in a smart-environment.  ...  This publication reflects the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained therein.  ... 
doi:10.1109/cvprw.2008.4563156 dblp:conf/cvpr/HansenHKLS08 fatcat:b37muigbjref5onb2nh5fegn2e

Beyond Silhouettes: Surface Reconstruction Using Multi-Flash Photography

Daniel Crispell, Douglas Lanman, Peter G. Sibley, Yong Zhao, Gabriel Taubin
2006 Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)  
This paper introduces a novel method for surface reconstruction using the depth discontinuity information captured by a multi-flash camera while the object moves along a known trajectory.  ...  The method extends well-established differential and global shape-from-silhouette surface reconstruction techniques by incorporating the significant additional information encoded in the depth discontinuities  ...  using only local information from a relatively small number of viewpoints.  ... 
doi:10.1109/3dpvt.2006.37 dblp:conf/3dpvt/CrispellLSZT06 fatcat:6wceq3cvefgdll2ntre5prz5se

Expanding the Detection of Traversable Area with RealSense for the Visually Impaired

Kailun Yang, Kaiwei Wang, Weijian Hu, Jian Bai
2016 Sensors  
As a result, stereo cameras return sparse depth images in textureless indoor scenes, such as a blank wall.  ...  in Henderson, NV, USA) estimates the depth map through stereo matching of images from two or more lenses.  ...  By using the plane model, the RANSAC algorithm provides a robust estimation of the dominant plane parameters, performing a random search to detect short-range ground preliminarily, which is assumed to  ... 
doi:10.3390/s16111954 pmid:27879634 pmcid:PMC5134613 fatcat:n26mttjp7naotding53yi6n52y

Improving CNN-based Planar Object Detection with Geometric Prior Knowledge [article]

Jianxiong Cai, Jiawei Hou, Yiren Lu, Hongyu Chen, Laurent Kneip, Sören Schwertfeger
2020 arXiv   pre-print
large-scale training sets. 2) It usually needs a long training time. 3) CNN-based object detection shows significant weakness in predicting location.  ...  , typically a CNN-based detector like YOLO or MASK RCNN.  ...  This approach also features a high robustness towards noisy depth information input (noisy point cloud), as the depth is just used to estimate the plane parameters, where RANSAC is effective even with  ... 
arXiv:1909.10245v2 fatcat:pd2osmnq55extbj6quhrrrnxcu
« Previous Showing results 1 — 15 out of 19,906 results