Robust and real-time pose tracking for augmented reality on mobile devices

Yang, Xin; Guo, Jiabin; Xue, Tangli; Cheng, Kwang-Ting

doi:10.1007/s11042-017-4575-3

Cited by 14 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of FAST and ORB decreases the amount of the processing time, but in the case of ORB, it is not as robust towards scale invariance [48]. It was also pointed out by Yang et al that the use of these faster feature descriptors lead to degraded robustness in their lightweight binary features [50].…”

Section: Marker or Markerless Trackingmentioning

confidence: 99%

“…The decision was made to use a marker-based tracking method because processing time can be greatly reduced, and it provides the operating room with reliable tracking features that can be consistently used from frame to frame. While Yang et al said that marker based methods are very fast even in mobile applications, there are certain drawbacks [50]. It could be inconvenient to users because a room must be set up beforehand in order to use marker-based tracking, such as markers being placed on the wall [50].…”

Section: Marker or Markerless Trackingmentioning

confidence: 99%

“…While Yang et al said that marker based methods are very fast even in mobile applications, there are certain drawbacks [50]. It could be inconvenient to users because a room must be set up beforehand in order to use marker-based tracking, such as markers being placed on the wall [50]. As the operating room is a controlled environment, this could be mitigated as markers could be placed once and remain in the room, negating the variation and setup between procedures using the HMD.…”

Section: Marker or Markerless Trackingmentioning

confidence: 99%

See 2 more Smart Citations

Design of a Spatially Anchoring Framework Using an Augmented Reality Head-Mounted Device and Fisheye Lens

Lai¹

2023

Preprint

View full text Add to dashboard Cite

<p>The development of improved Augmented Reality (AR) Head-Mounted Devices (HMDs) have led to many potential applications for augmented reality. In the case of surgery, an HMD could be used as an assistive tool to address some deficits that popular neuronavigation devices have, such as a disturbance to surgical workflow and surgeon comfort.</p> <p>This thesis aims to bring an HMD-based overlay framework that can be used in the operating room. Through a combination of Android Studio, OpenCV, and OpenGL, a method to localize an HMD (ODG R9s) was created. This framework used a fisheye lens and a marker-based tracking method to localize the headset and renders a spatially-anchored 3D model in real time. A “Focus” mode was also developed in stabilizing the camera pose estimation and translational and rotational errors were quantified.</p>

show abstract

Section: Marker or Markerless Trackingmentioning

confidence: 99%

Section: Marker or Markerless Trackingmentioning

confidence: 99%

Section: Marker or Markerless Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Design of a Spatially Anchoring Framework Using an Augmented Reality Head-Mounted Device and Fisheye Lens

Lai¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the beginning, these systems usually use camera as only sensors [146], [147]. In mobile devices, to improve accuracy and obtain absolute scale, the devices fuse data from other sensors such as IMU [148]- [151].…”

Section: Application Of Visual Odometry In Complicated and Emerging A...mentioning

confidence: 99%

Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas

Wang,

Ma,

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which is becoming increasingly mature and accurate, but it tends to be fragile under challenging environments. Comparing with classical geometrybased methods, deep learning-based methods can automatically learn effective and robust representations, such as depth, optical flow, feature, ego-motion, etc., from data without explicit computation. Nevertheless, there still lacks a thorough review of the recent advances of deep learning-based VO (Deep VO). Therefore, this paper aims to gain a deep insight on how deep learning can profit and optimize the VO systems. We first screen out a number of qualifications including accuracy, efficiency, scalability, dynamicity, practicability, and extensibility, and employ them as the criteria. Then, using the offered criteria as the uniform measurements, we detailedly evaluate and discuss how deep learning improves the performance of VO from the aspects of depth estimation, feature extraction and matching, pose estimation. We also summarize the complicated and emerging areas of Deep VO, such as mobile robots, medical robots, augmented reality and virtual reality, etc. Through the literature decomposition, analysis, and comparison, we finally put forward a number of open issues and raise some future research directions in this field.

show abstract

“…These robots are normally equipped with intelligent vision systems which not only detect parts in the working spaces but also estimate their poses before taking further actions such as grasping, rotating, moving, fitting, etc. Generally, object recognition and 6D pose estimation from images are the base of almost all kinds of robotic applications, such as robot manipulation (Tremblay et al, 2018 ), robot-human interaction (Svenstrup et al, 2009 ), and virtual reality (Yang et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

A Manufacturing-Oriented Intelligent Vision System Based on Deep Neural Network for Object Recognition and 6D Pose Estimation

et al. 2021

View full text Add to dashboard Cite

Nowadays, intelligent robots are widely applied in the manufacturing industry, in various working places or assembly lines. In most manufacturing tasks, determining the category and pose of parts is important, yet challenging, due to complex environments. This paper presents a new two-stage intelligent vision system based on a deep neural network with RGB-D image inputs for object recognition and 6D pose estimation. A dense-connected network fusing multi-scale features is first built to segment the objects from the background. The 2D pixels and 3D points in cropped object regions are then fed into a pose estimation network to make object pose predictions based on fusion of color and geometry features. By introducing the channel and position attention modules, the pose estimation network presents an effective feature extraction method, by stressing important features whilst suppressing unnecessary ones. Comparative experiments with several state-of-the-art networks conducted on two well-known benchmark datasets, YCB-Video and LineMOD, verified the effectiveness and superior performance of the proposed method. Moreover, we built a vision-guided robotic grasping system based on the proposed method using a Kinova Jaco2 manipulator with an RGB-D camera installed. Grasping experiments proved that the robot system can effectively implement common operations such as picking up and moving objects, thereby demonstrating its potential to be applied in all kinds of real-time manufacturing applications.

show abstract

Robust and real-time pose tracking for augmented reality on mobile devices

Cited by 14 publications

References 13 publications

Design of a Spatially Anchoring Framework Using an Augmented Reality Head-Mounted Device and Fisheye Lens

Design of a Spatially Anchoring Framework Using an Augmented Reality Head-Mounted Device and Fisheye Lens

Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas

A Manufacturing-Oriented Intelligent Vision System Based on Deep Neural Network for Object Recognition and 6D Pose Estimation

Contact Info

Product

Resources

About