Filters








70,176 Hits in 8.4 sec

Abnormal Activity Detection and Notification Platform for Real-Time Ad Hoc Network

Suriya Pinitkan, Nawaporn Wisitpongphan
2020 International Journal of Online and Biomedical Engineering (iJOE)  
The proposed platform relies on human tracking using cameras that are installed in different rooms inside the house.  ...  AADN will take as input images from the cameras to process and output activity in the form of human pose and objects with their relative distant to the detected human.  ...  For example, if the prediction result at time t of a room with 4 cameras is {sit, sit, stand, idle} which means that the 1 st and 2 nd cameras predict that such person is in the sitting pose, 3 rd camera  ... 
doi:10.3991/ijoe.v16i15.16065 fatcat:xe6o3yxqr5dklncjrlyyb3wmxu

Steerable augmented reality with the beamatron

Andrew Wilson, Hrvoje Benko, Shahram Izadi, Otmar Hilliges
2012 Proceedings of the 25th annual ACM symposium on User interface software and technology - UIST '12  
Steerable displays use a motorized platform to orient a projector to display graphics at any point in the room.  ...  Often a camera is included to recognize markers and other objects, as well as user gestures in the display volume.  ...  Reasoning in Room Coordinates The computational strategies described above provide the ability to relate all sensing data to a room coordinate frame, find the real time 3D pose of the moving platform and  ... 
doi:10.1145/2380116.2380169 dblp:conf/uist/WilsonBIH12 fatcat:3qtmfeizcrhzxk7vftuguji5ra

Real-time Cloud Visual Simultaneous Localization And Mapping for Indoor Service Robots

Yali Zheng, Shinan Chen, Hong Cheng
2020 IEEE Access  
Based on recent excellent algorithms, our system is able to run a real-time sparse tracking on the client, and a real-time dense mapping on the cloud server, which outputs an explicit 3D dense map.  ...  However, as a fundamental intelligence function for mobile indoor robots, if a real-time visual Simultaneously Localization and Mapping (vSLAM) system is split into client and brain, it will be confronted  ...  Camera pose optimization based on keyframes runs on local computing servers in real time, then optimized camera poses are sent back to correct the tracking poses of robots via local optimization.  ... 
doi:10.1109/access.2020.2966757 fatcat:3lgvtyyaynfixixaufznlicxam

Online Reconstruction of Indoor Scenes from RGB-D Streams

Hao Wang, Jun Wang, Liang Wang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Our system is powered by a two-pass reconstruction scheme. The first pass tracks camera poses at video rate and simultaneously constructs a pose graph on-the-fly.  ...  The tracker operates in real-time, which allows the reconstruction results to be visualized during the scanning process. Live visual feedbacks makes the scanning operation fast and intuitive.  ...  Camera Tracking: We extends the voxel hashing based volumetric fusion [19] approach to achieve robust real-time camera tracking.  ... 
doi:10.1109/cvpr.2016.356 dblp:conf/cvpr/WangWW16 fatcat:bpokcmaapff3dkw7cjylkc5gce

Egocentric scene context for human-centric environment understanding from video [article]

Tushar Nagarajan, Santhosh Kumar Ramakrishnan, Ruta Desai, James Hillis, Kristen Grauman
2022 arXiv   pre-print
We show that by grounding videos in their physical environment, our models surpass traditional scene classification models at predicting which room a camera-wearer is in (where frame-level information  ...  First-person video highlights a camera-wearer's activities in the context of their persistent environment.  ...  of a camera-wearer at each time-step.  ... 
arXiv:2207.11365v1 fatcat:qhcezflvxzekdoagfzo2oyzpq4

A Precise Indoor Visual Positioning Approach Using a Built Image Feature Database and Single User Image from Smartphone Cameras

Ming Li, Ruizhi Chen, Xuan Liao, Bingxuan Guo, Weilong Zhang, Ge Guo
2020 Remote Sensing  
In addition, experiments show that the proposed method is more robust and efficient than the baseline method in a real scene.  ...  Indoor visual positioning is a key technology in a variety of indoor location services and applications.  ...  A large number of algorithms for continuous camera-pose estimation and global optimization in indoor environments have been studied, and visual-based indoor real-time 3D mapping and positioning technologies  ... 
doi:10.3390/rs12050869 fatcat:wxg2lrumkbaihhdojyrpz4e5r4

A projection-based mixed-reality display for exterior and interior of a building diorama

Ming Zhang, Itaru Kitahara, Yoshinari Kameda, Yuichi Ohta
2014 Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology - VRST '14  
The CG image corresponding to the user's viewpoint, gesture and the pose of the diorama is rendered by Dual Rendering algorithm in real time.  ...  Our system obtains both of the user's information (the viewpoint and the gesture) and the diorama model's information (the pose) in 3D space by using two RGB-D cameras.  ...  The projected CG image was generated by referring the user's viewpoint, gesture and the pose of the diorama in real time.  ... 
doi:10.1145/2671015.2671132 dblp:conf/vrst/ZhangKKO14 fatcat:gl2lvc5emne6hkgjnfhtbnmorq

Incremental 2D Grid Map Generation from RGB-D Images [chapter]

Tingfeng Ye, Juzhong Zhang, Yingcai Wan, Ze Cui, Hongbo Yang
2021 Frontiers in Artificial Intelligence and Applications  
Meanwhile, the pose information provided by RGB-D SLAM and scan matching respectively is fused to obtain a more accurate and robust pose, which improves the accuracy of map building.  ...  In this paper, we extend RGB-D SLAM to address the problem that sparse map-building RGB-D SLAM cannot directly generate maps for indoor navigation and propose a SLAM system for fast generation of indoor  ...  In this paper, we exploit the ability of RGB-D SLAM to output depth maps as well as camera poses in real time, combined with algorithms for navigation grid map building of 2D LiDAR SLAM, to design a robust  ... 
doi:10.3233/faia210433 fatcat:g5v3dsdmnzgy7nxt4rb44wcxh4

Estimating the Lecturer's Head Pose in Seminar Scenarios – A Multi-view Approach [chapter]

Michael Voit, Kai Nickel, Rainer Stiefelhagen
2006 Lecture Notes in Computer Science  
In this paper, we present a system to track the horizontal head orientation of a lecturer in a smart seminar room, which is equipped with several cameras.  ...  In 92% of the time, the correct pose class or a neighbouring pose class (i.e. a 45 degree error) were estimated.  ...  Overall, correct pose class detection was achieved in 48.4% of the time. In 82.9% of the time the estimated pose class fell in either the correct class or a neighbouring class (error < 45 • ).  ... 
doi:10.1007/11677482_20 fatcat:tm36uayqpzhq7e7mnvtrwie5vy

The CMU pose, illumination, and expression database

Terence Sim, S. Baker, M. Bsat
2003 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In the Fall of 2000 we collected a database of over 40,000 facial images of 68 people.  ...  Using the CMU 3D Room we imaged each person across 13 different poses, under 43 different illumination conditions, and with 4 different expressions.  ...  Sundar Vedula and German Cheung gave us great help using the CMU 3D Room. We would also like to thank Henry Schneiderman and Jeff Cohn for discussions on what  ... 
doi:10.1109/tpami.2003.1251154 fatcat:lqd4nmklwvcsnh22z3deyfvgje

SLAM++: Simultaneous Localisation and Mapping at the Level of Objects

Renato F. Salas-Moreno, Richard A. Newcombe, Hauke Strasdat, Paul H.J. Kelly, Andrew J. Davison
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We demonstrate real-time incremental SLAM in large, cluttered environments, including loop closure, relocalisation and the detection of moved objects, and of course the generation of an object level scene  ...  As a hand-held depth camera browses a cluttered scene, realtime 3D object recognition and tracking provides 6DoF camera-object constraints which feed into an explicit graph of objects, continually refined  ...  Acknowledgements Renato Salas-Moreno's research was supported by a PhD scholarship from AMD. We are grateful to Lee Howes for useful discussions.  ... 
doi:10.1109/cvpr.2013.178 dblp:conf/cvpr/Salas-MorenoNSKD13 fatcat:xgdykknqgrgvzkfb5pqqr4rkk4

Synthesis of Environment Maps for Mixed Reality

David R. Walton, Diego Thomas, Anthony Steed, Akihiro Sugimoto
2017 2017 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)  
virtual content in real time.  ...  We introduce a method using an RGBD camera and a small fisheye camera, contained in a single unit, to create environment maps at any location in an indoor scene.  ...  This work was also partly supported by Grant-in-Aid for Scientific Research (Grant No. 16H02851) of the Ministry of Education, Culture, Sports, Science and Technology of Japan.  ... 
doi:10.1109/ismar.2017.24 dblp:conf/ismar/WaltonTSS17 fatcat:wayheqhqnjckxhsgfij4s2km7i

Who do you want to be? Real-time face swap

Tim M. den Uyl, H. Emrah Tasli, Paul Ivan, Mariska Snijdewind
2015 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
This demonstration paper presents a face swap application where two people's faces are automatically exchanged in real-time without any calibration or training.  ...  This application is intended for gaming, shopping, educational or entertainment purposes and will be presented in a real-time setup during the demo session.  ...  DEMONSTRATION The proposed automatic face swap application presents a complete framework for changing the faces of two people in a real-time setting using an off-the-shelf web camera.  ... 
doi:10.1109/fg.2015.7163172 dblp:conf/fgr/UylTIS15 fatcat:2c3pjnpiljgrlllbdjphbfkfmy

iMAP: Implicit Mapping and Positioning in Real-Time [article]

Edgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. Davison
2021 arXiv   pre-print
We show for the first time that a multilayer perceptron (MLP) can serve as the only scene representation in a real-time SLAM system for a handheld RGB-D camera.  ...  Achieving real-time SLAM via continual training of a neural network against a live image stream requires significant innovation.  ...  real-time SLAM as online contin- jointly optimising a full 3D map and camera poses.  ... 
arXiv:2103.12352v2 fatcat:vsxdmgs3kbdztamcau3z46gsyi

Multi-pose Volume Reconstruction Across Arbitrary Trajectory from Multiple Fisheye Cameras [chapter]

Konstantina Kottari, Konstantinos Delibasis
2015 IFIP Advances in Information and Communication Technology  
Then we extend this algorithm in the case of a human moving along any trajectory a) assuming no pose change and b) considering pose change during motion.  ...  Volume reconstruction from silhouettes is a known subject in the case of projective cameras.  ...  Affective Computing for Biological Activity Recognition in Assistive Environments for financially supporting this work.  ... 
doi:10.1007/978-3-319-23868-5_3 fatcat:i4jo26mknfhuppod5tqkx7m6me
« Previous Showing results 1 — 15 out of 70,176 results