The visual world can be a noisy and dynamic place. This poses problems for novice word learners who must map heard names to objects in scenes with their many potential referents. In this study, we consider how the visual stability and selectivity of scenes from the first-person perspective may simplify the learning problem. 12and 30-month-old children wore head cameras and played with a large s...

Combining active and passive imaging sensors enables creating a more detailed 3D model of the real world. Then, these 3D data can be used for various applications, such as city mapping, indoor navigation, autonomous vehicles, etc. Typically, LiDAR and camera as imaging sensors are installed on these systems. Both of these sensors have advantages and drawbacks. Thus, LiDAR sensor directly provid...

Master of Electrical Engineering Program Cornell University Design Project Report Project Title: 2D to 3D Video Conversion with Static Scene and Horizontal Camera Motion Author: Ling-Wei Lee Abstract: Four automate methods to convert two-dimensional (2D) video to three-dimensional (3D) for video with only static scene and horizontal camera motion have been proposed in this project. Our approach...

Hyperspectral remote sensing based on unmanned airborne vehicles is a field increasing in importance. The combined functionality of simultaneous hyperspectral and geometric modeling is less developed. A configuration has been developed that enables the reconstruction of the hyperspectral three-dimensional (3D) environment. The hyperspectral camera is based on a linear variable filter and a high...

Point based visual SLAM suffers from a trade off between map density and computational efficiency. With too few mapped points, tracking range is restricted and resistance to occlusion is reduced, whilst expanding the map to give dense representation significantly increases computation. We address this by introducing higher order structure into the map using planar features. The parameterisation...

This paper examines the process of tone mapping and blooming, and then discusses its real-time implementation on current graphics hardware (GPU). The main contribution of this paper is a fast Gaussian filtering algorithm that significantly reduces the number of texture fetches and thus runs at interactive frame rates on the GPU. The reduction of the number of texture fetches is made possible by...

It is too often that tracking algorithms lose track of interest points in image sequences. This persistent problem is difficult because the pixels around an interest point change in appearance or move in unpredictable ways. In this paper we explore how classifying videos into categories of camera motion improves the tracking of interest points, by selecting the right specialist motion model for...

In this paper we present a novel computer vision library called UAVision that provides support for different digital cameras technologies, from image acquisition to camera calibration, and all the necessary software for implementing an artificial vision system for the detection of color-coded objects. The algorithms behind the object detection focus on maintaining a low processing time, thus th...

for the nonlinear analysis of structures using the well known newton-raphson method, the tangent stiffness matrices of the elements must be constructed in each iteration. due to the high expense required to find the exact tangent stiffness matrices, researchers have developed novel innovations into the newton-raphson method to reduce the cost and time required by the analysis. in this paper, a ...

Abstract The novel approach to physical security based on visible light communication (VLC) using an informative object-pointing and simultaneous recognition by high-framerate (HFR) vision systems is presented in this study. In the proposed approach, a convolutional neural network (CNN) object detection method used detect environmental objects that assist spatiotemporal-modulated-pattern (SMP) ...