scispace - formally typeset
Search or ask a question
Topic

Orientation (computer vision)

About: Orientation (computer vision) is a research topic. Over the lifetime, 17196 publications have been published within this topic receiving 358181 citations.


Papers
More filters
Proceedings ArticleDOI
12 May 1992
TL;DR: A vision-based position sensing system which provides three-dimensional relative position and orientation (pose) of an arbitrary moving object with respect to a camera for a real-time tracking control is studied.
Abstract: A vision-based position sensing system which provides three-dimensional relative position and orientation (pose) of an arbitrary moving object with respect to a camera for a real-time tracking control is studied. Kalman filtering was applied to vision measurements for the implicit solution of the photogrametric equations and to provide significant temporal filtering of the resulting motion parameters resulting in optimal pose estimation. Both computer simulation and real-time experimental results are presented to verify the effectiveness of the Kalman filter approach with large vision measurement noise. >

103 citations

Patent
30 Jan 1995
TL;DR: In this paper, a flat display can display an image corresponding to text, data and graphic information in several orientations, and a plurality of switches enable the user to select an orientation for the image relative to the orientation of the flat display.
Abstract: A pen-based computer including a housing and a flat display integral therewith. The flat display can display an image corresponding to text, data and graphic information in several orientations. A plurality of switches enables the user to select an orientation for the image relative to the orientation of the flat display. In one embodiment the switches are mercury switches positioned to automatically align the orientation of the image relative to motion of the flat panel display relative to the force of gravity. An optional additional switch resets the orientation of the image to a predetermined orientation or prevents the reorientation of the image responsive to the mercury switches.

103 citations

Patent
25 Jul 2006
TL;DR: In this paper, the authors propose a method for generating an image sequence using an image capture device. But the method is limited to images generated by the device and representative of an existing image of a sequence to assist a user of the device to capture one or more subsequent images for the sequence.
Abstract: A method for generating an image sequence using an image capture device, the method comprising using image data generated using the device and representative of an existing image of a sequence to assist a user of the device to capture one or more subsequent images for the sequence in order that said existing and the or each subsequent image are captured at substantially the same location and device orientation, and an image capture device operable to assist a user in generating an image sequence.

103 citations

Journal ArticleDOI
TL;DR: A supervised retinal vessel segmentation by incorporating vessel filtering and wavelet transform features from orientation scores (OSs), and green intensity achieves a competitive segmentation, and better vessel preservation with less false detections compared with the state-of-the-art methods.

103 citations

Book ChapterDOI
13 Jan 2006
TL;DR: A bottom-up approach that uses local image features to estimate human upper body pose from single images in cluttered backgrounds, and shows that it estimates pose with similar performance levels to current example-based methods, but unlike them it works in the presence of natural backgrounds, without any prior segmentation.
Abstract: Recovering the pose of a person from single images is a challenging problem. This paper discusses a bottom-up approach that uses local image features to estimate human upper body pose from single images in cluttered backgrounds. The method takes the image window with a dense grid of local gradient orientation histograms, followed by non negative matrix factorization to learn a set of bases that correspond to local features on the human body, enabling selective encoding of human-like features in the presence of background clutter. Pose is then recovered by direct regression. This approach allows us to key on gradient patterns such as shoulder contours and bent elbows that are characteristic of humans and carry important pose information, unlike current regressive methods that either use weak limb detectors or require prior segmentation to work. The system is trained on a database of images with labelled poses. We show that it estimates pose with similar performance levels to current example-based methods, but unlike them it works in the presence of natural backgrounds, without any prior segmentation.

103 citations


Network Information
Related Topics (5)
Segmentation
63.2K papers, 1.2M citations
82% related
Pixel
136.5K papers, 1.5M citations
79% related
Image segmentation
79.6K papers, 1.8M citations
78% related
Image processing
229.9K papers, 3.5M citations
77% related
Feature (computer vision)
128.2K papers, 1.7M citations
76% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202212
2021535
2020771
2019830
2018727
2017691