Registration algorithm based on image matching for outdoor AR system with fixed viewing position

This paper presents a new human recognition method based on features extracted from retinal images. The proposed method is composed of some steps including feature extraction, phase correlation technique, and feature matching for recognition. In the proposed method, Harris corner detector is used for feature extraction. Then, phase correlation technique is applied to estimate the rotation angle of head or eye movement in front of a retina fundus camera. Finally, a new similarity function is used to compute the similarity between features of different retina images. Experimental results on a database, including 480 retinal images obtained from 40 subjects of DRIVE dataset and 40 subjects from STARE dataset, demonstrated an average true recognition accuracy rate equal to 100% for the proposed method. The success rate and number of images used in the proposed method show the effectiveness of the proposed method in comparison to the counterpart methods.

show abstract

“…Therefore, a method based on the Fourier-Mellin transform is used to estimate the rotation angle of head or eye movement [26].…”

Section: Rotation Compensationmentioning

confidence: 99%

Human recognition based on retinal images and using new similarity function

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Category 1: single layer and point based. These algorithms match local independent features without explicit graph structures, such as Harris corners, KLT features [10], scale invariant features [5,13], local edge structure features [22] and geometric blur descriptors [19,25]. These features are often robust against certain geometric distortions and illumination changes, but carry little information about larger object structures.…”

Section: Introductionmentioning

confidence: 99%

Layered Graph Match with Graph Editing

Zhu

Wang

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Graph editing problems offer an interesting perspective on sub-and super-graph identification problems for a large variety of target properties. They have also attracted significant attention in recent years, particularly in the area of parameterized complexity as the problems have rich parameter ecolo-gies. In this paper we examine generalisations of the notion of editing a graph to obtain a regular subgraph. In particular we extend the notion of regularity to include two variants of edge-regularity along with the unifying constraint of strong regularity. We present a number of results, with the central observation that these problems retain the general complexity profile of their regularity-based inspiration: when the number of edits k and the maximum degree r are taken together as a combined parameter, the problems are tractable (i.e. in FPT), but are otherwise intractable. We also examine variants of the basic editing to obtain a regular subgraph problem from the perspective of parameterizing by the treewidth of the input graph. In this case the treewidth of the input graph essentially becomes a limiting parameter on the natural k + r parameterization.

show abstract

“…observe the augmented vision through see-through head-mounted displays (HMD) while moving his head around. At present, AR systems have been widely applied to the fields of entertainment game [6], medical surgery [15], protection of ancient relic [27], industrial assembly [16] and military training [24] etc.…”

mentioning

confidence: 99%

Sensor fusion based head pose tracking for lightweight flight cockpit systems

Luo

Wang

Liu

2010

Multimed Tools Appl

View full text Add to dashboard Cite

Flight cockpit head tracking systems (HTS) are one of the most important impetuses for head pose tracking in the field of augmented reality. For the purpose of implementing the natural interaction between pilot and the complete internal environment in our lightweight flight cockpit system, a head tracking system consisting of inside-out tracking (IOT) and outside-in tracking (OIT) is designed and a novel approach using sensor fusion is proposed to dynamically track pilot's head pose. The proposed approach utilizes a sensor fusion framework, composed of extended Kalman filters and fusion filter, to fuse the poses from complementary IOT and OIT. An experimental setup is established to simulate the cockpit HTS and verify the proposed approach. Experimental results show that the proposed tracking scheme based on sensor fusion is capable of achieving more accurate and stable pose outputs, extending tracking range as well as better robustness compared with single IOT or OIT. Keywords Sensor fusion . Head pose tracking . Lightweight flight cockpit system . Augmented reality IntroductionAugmented Reality (AR) [2,3] is a paradigm of the interaction technologies that uses accurate head pose to superpose computer-generated supplemental information onto the real video streams captured by the video device or the physical scene viewed by user. User can

show abstract

Registration algorithm based on image matching for outdoor AR system with fixed viewing position

Cited by 11 publications

References 16 publications

Human recognition based on retinal images and using new similarity function

Human recognition based on retinal images and using new similarity function

Layered Graph Match with Graph Editing

Sensor fusion based head pose tracking for lightweight flight cockpit systems

Contact Info

Product

Resources

About