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 published on a yearly basis
Papers
More filters
Patent•
16 May 1988TL;DR: In this article, a file of picture elements is generated which depicts the image with respect to the reference angle, and the picture elements are projected onto a plurality of contiguous segments of imaginary lines at selected angles across the file.
Abstract: A method and apparatus for determining a predominant angle of orientation of an image with respect to a reference angle. A file of picture elements is generated which depicts the image with respect to the reference angle. The picture elements are projected onto a plurality of contiguous segments of imaginary lines at selected angles across the file. Each imaginary line is perpendicular to its associated direction of projection. The number of picture elements that fall into the segments for each projection are counted. An enhancement function is applied to the segment counts of each projection. The projection that generates the largest value of the enhancement function defines the angle of orientation of the image. The position of a document scanner or the document itself may be rotated to compensate for the detected skew.
80 citations
TL;DR: In this article, a method is presented which indexes spots recorded on single oscillation images without any a priori knowledge of cell parameters, which is similar to that used in four-circle diffractometry and the method works in a fully automatic manner.
Abstract: A method is presented which indexes spots recorded on single oscillation images without any a priori knowledge of cell parameters. The strategy is similar to that used in four-circle diffractometry and the method works in a fully automatic manner. It is applicable to multiple oscillation images or multiple stills. A complementary method is also described to obtain orientation angles for the case where cell parameters have already been determined.
80 citations
Posted Content•
TL;DR: This work demonstrates its effectiveness on a continuous object orientation estimation task, which requires prediction of 0 to 360 degrees orientation of the objects, by proposing and comparing three continuous orientation prediction approaches designed for the DCNNs.
Abstract: Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of 0 to 360 degrees orientation of the objects. We do so by proposing and comparing three continuous orientation prediction approaches designed for the DCNNs. The first two approaches work by representing an orientation as a point on a unit circle and minimizing either L2 loss or angular difference loss. The third method works by first converting the continuous orientation estimation task into a set of discrete orientation estimation tasks and then converting the discrete orientation outputs back to the continuous orientation using a mean-shift algorithm. By evaluating on a vehicle orientation estimation task and a pedestrian orientation estimation task, we demonstrate that the discretization-based approach not only works better than the other two approaches but also achieves state-of-the-art performance. We also demonstrate that finding an appropriate feature representation is critical to achieve a good performance when adapting a DCNN trained for an image recognition task.
80 citations
Patent•
19 Jan 2006
TL;DR: In this article, the authors present a method for identifying, relocating, acquiring a first and/or subsequent image of the suspect area, and performing a comparative analysis of respective images, which can be used to assist a medical professional in treating or counseling the patient.
Abstract: A device for acquiring first and subsequent images of a suspect area on a patient and methods for monitoring or detecting changes of the suspect area over time and providing notification when the changes exceed a threshold. The device may be an imaging device, such as a digital camera, possibly augmented with physical or optical devices for arranging the orientation and/or distance of the imaging device with respect to the suspect area. In addition, methods for identifying, relocating, acquiring a first and/or subsequent image of the suspect area, and performing a comparative analysis of respective images are also described. Results of the comparative analysis can be used to notify and/or assist a medical professional in treating or counseling the patient.
80 citations
TL;DR: The authors propose to emphasise the analysis of such `non-stationary targets` using a 2D imaging space, using both the micro-Doppler and a high-range resolution analysis, to better discriminate the various effects caused by the time-varying reflectors.
Abstract: In radar imaging, it is well known that relative motion or deformations of parts of illuminated objects induce additional features in the Doppler frequency spectrum. These features are called micro-Doppler effect and appear as sidebands around the central Doppler frequency. They can provide valuable information about the structure of the moving parts and may be used for identification purposes. Previous papers have mostly focused on 1D micro-Doppler analysis. The authors propose to emphasise the analysis of such `non-stationary targets` using a 2D imaging space, using both the micro-Doppler and a high-range resolution analysis. As in 2D-ISAR imaging, range separation enables to better discriminate the various effects caused by the time-varying reflectors. The study is focused on two different common examples: rotating wheels and human motion. With the help of micro-Doppler signature, information on the geometrical features of wheels (position, orientation) and on the gait of pedestrians can be extracted. Examples will be shown with simulated and experimental data.
80 citations