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.

Image processing system with ease of operation

Abstract: When a shot is taken by a portable terminal, the position and orientation at the time of shooting is transmitted to an information processing apparatus. The information processing apparatus, which stores information including the position of equipment, detects the equipment included in the shot image by the portable terminal, based on the position and orientation of the portable terminal and the position of the equipment, and transmits information about the equipment to the portable terminal. The portable terminal obtains an operation history on an image processing apparatus in the equipment based on the received information, and displays an operation screen presenting the operation history in a selectable manner on a display unit. Then, when a selection of operation history is accepted, a control signal for allowing the image processing apparatus to execute image processing indicated by the operation history is transmitted to the image processing apparatus.

Monitoring Crack Changes in Concrete Structures

Abstract: This study proposes a crack-monitoring sys- tem to quantify the change of cracks from multitempo- ral images during the monitoring period. A series of images were taken from an off-the-shelf digital camera. Concrete cracks were extracted from the digital images by employing a series of image-processing techniques. The image coordinates and orientation of same cracks can be changed since the position and direction of the portable camera vary at every exposure time. To moni- tor the crack changes (width and length), it is critical to transform the image coordinates of cracks extracted from each image into the same object coordinates of the con- crete surface. In this study, such a geometric relationship was automatically recovered using the two-dimensional (2D) projective transformation based on the modified it- erated Hough transform (MIHT) algorithm, the result of which solved the transformation parameters. To improve the computational operation of MIHT, regions of param- eter estimation were also investigated. The developed al- gorithms were applied to monitor the crack of the concrete specimen. As a result, the change of cracks on the concrete specimen was successfully detected and accurately quan- tified.

Learning Hybrid Image Templates (HIT) by Information Projection

Abstract: This paper presents a novel framework for learning a generative image representation-the hybrid image template (HIT) from a small number (i.e., 3 \sim 20) of image examples. Each learned template is composed of, typically, 50 \sim 500 image patches whose geometric attributes (location, scale, orientation) may adapt in a local neighborhood for deformation, and whose appearances are characterized, respectively, by four types of descriptors: local sketch (edge or bar), texture gradients with orientations, flatness regions, and colors. These heterogeneous patches are automatically ranked and selected from a large pool according to their information gains using an information projection framework. Intuitively, a patch has a higher information gain if 1) its feature statistics are consistent within the training examples and are distinctive from the statistics of negative examples (i.e., generic images or examples from other categories); and 2) its feature statistics have less intraclass variations. The learning process pursues the most informative (for either generative or discriminative purpose) patches one at a time and stops when the information gain is within statistical fluctuation. The template is associated with a well-normalized probability model that integrates the heterogeneous feature statistics. This automated feature selection procedure allows our algorithm to scale up to a wide range of image categories, from those with regular shapes to those with stochastic texture. The learned representation captures the intrinsic characteristics of the object or scene categories. We evaluate the hybrid image templates on several public benchmarks, and demonstrate classification performances on par with state-of-the-art methods like HoG+SVM, and when small training sample sizes are used, the proposed system shows a clear advantage.

System and method for displaying anatomy and devices on a movable display

Abstract: An image display system is provided comprised of a virtual window system that creates a visual coherency between the patient's anatomical images and the actual patient by aligning the image on the display to the patient and then presenting the image to the user in a way that feels as if the user is looking directly into the patient through the display. The image shown within the image display system is dependent upon the position of the image display apparatus and the position of the user so that the display orientation of the image may be biased slightly toward the user to improve ergonomics and usability.

Discrete element textures

Abstract: A variety of phenomena can be characterized by repetitive small scale elements within a large scale domain. Examples include a stack of fresh produce, a plate of spaghetti, or a mosaic pattern. Although certain results can be produced via manual placement or procedural/physical simulation, these methods can be labor intensive, difficult to control, or limited to specific phenomena.We present discrete element textures, a data-driven method for synthesizing repetitive elements according to a small input exemplar and a large output domain. Our method preserves both individual element properties and their aggregate distributions. It is also general and applicable to a variety of phenomena, including different dimensionalities, different element properties and distributions, and different effects including both artistic and physically realistic ones. We represent each element by one or multiple samples whose positions encode relevant element attributes including position, size, shape, and orientation. We propose a sample-based neighborhood similarity metric and an energy optimization solver to synthesize desired outputs that observe not only input exemplars and output domains but also optional constraints such as physics, orientation fields, and boundary conditions. As a further benefit, our method can also be applied for editing existing element distributions.