Bounding overwatch

About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.

Universal Bounding Box Regression and Its Applications

Abstract: Bounding-box regression is a popular technique to refine or predict localization boxes in recent object detection approaches. Typically, bounding-box regressors are trained to regress from either region proposals or fixed anchor boxes to nearby bounding boxes of a pre-defined target object classes. This paper investigates whether the technique is generalizable to unseen classes and is transferable to other tasks beyond supervised object detection. To this end, we propose a class-agnostic and anchor-free box regressor, dubbed Universal Bounding-Box Regressor (UBBR), which predicts a bounding box of the nearest object from any given box. Trained on a relatively small set of annotated images, UBBR successfully generalizes to unseen classes, and can be used to improve localization in many vision problems. We demonstrate its effectiveness on weakly supervised object detection and object discovery.

Bounding plane-based techniques for improved sample test efficiency in image rendering

Abstract: A method for reducing the number of samples tested for rendering a screen space region of an image includes constructing a trajectory of a primitive in a three dimensional coordinate system, the coordinate system including a screen space dimension, a lens dimension and a time dimension. A bounding volume is constructed for a screen space region which is to be rendered, the bounding volume overlapping a portion of the screen space region. The bounding volume is defined according to a plurality of bounding planes which extend in the three dimensional coordinate system, whereby the bounding planes are determined as a function of the trajectory of the primitive. One or more sample points which are located within the screen space region, and which are not overlapped by the bounding volume are excluded from testing.

Lower And Upper Bounding Constraints of Model Parameters In Inversion of Geophysical Data

Abstract: Since many geophysical inverse problems are ill-posed, implementation of constraints is effective in reducing solution ambiguity. This paper presents a simple transform method for enforcing lower and upper bounding constraints about the solution to restrict model parameter updates during the inversion process such that non-realistic results are suppressed. The lower and upper bounding constraints are realized by a logarithmic or an inverse hyperbolic tangent transformation of model parameters. The width of the two bounds reflects the reliability of a priori information, which may be obtained through well logging and surface geological surveys. It is straightforward to recast the cost functional gradient in terms of the transformed variable.

On optimality of OBBs for visibility tests for frustum culling, ray shooting and collision detection

Abstract: Bounding volume hierarchies are widely employed in many areas of computer graphics. Usually they are used as crude approximations of the scene geometry to speed up some time-consuming computations, such as visibility tests for frustum culling, ray shooting, collision detection, etc. A number of bounding volume types have been discussed by various researchers. They include bounding spheres, axis-aligned and oriented bounding boxes, and others. Although it is practically possible to use any of these bounding volumes, some types prove to be particularly useful in certain applications, e.g. Gortschalk et al. (1996) used oriented bounding boxes to implement a very effective exact collision detection scheme. The authors address the problem of efficient bounding volume selection, the solution of which allows one to significantly accelerate such operations as visibility tests for frustum culling, collision detection and ray shooting. They prove that minimal surface area (perimeter in 2D) oriented bounding box is optimal among all the oriented bounding boxes with respect to the three operations stated above. Then, they develop a number of algorithms to create optimal oriented bounding boxes and their approximations and finally discuss the results of the practical implementation.