Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 10 of 10 for “"lighting change"”.

  1. Recognition and matching in the presence of deformation and lighting change

    … of variability due to different factors like lighting and viewpoint change, occlusion, articulation and non-rigid deformation. There are certain cases like recognition of specular objects and images with arbitrary deformations where existing techniques do not perform well. For image …

    maryland Repository record for Recognition and matching in the presence of deformation and lighting change (opens in a new tab)

  2. Measuring Deformations and Illumination Changes in Images with Applications to Face Recognition

    This thesis explores object deformation and lighting change in images, proposing methods that account for both variabilities within a single framework. We construct a deformation- and lighting-insensitive metric that assigns a cost to a pair of images based on their similarity. The primary …

    maryland Repository record for Measuring Deformations and Illumination Changes in Images with Applications to Face Recognition (opens in a new tab)

  3. INSTITUTE OF CONTEMPORARY ART: EMERGING FROM THE EVERYDAY LANDSCAPE

    … art we see today and excludes possibility of change. The museum that invites the visitor’s contemplation of serene freestanding works of sculpture and smooth succession of pictures aligned along its walls cannot serve as the model for the new Institute of Contemporary Art. A new space for …

    nus Repository record for INSTITUTE OF CONTEMPORARY ART: EMERGING FROM THE EVERYDAY LANDSCAPE (opens in a new tab) Download file for INSTITUTE OF CONTEMPORARY ART: EMERGING FROM THE EVERYDAY LANDSCAPE (opens in a new tab)

  4. Towards Deep Learning for Long-term Visual Localization in Visual Teach and Repeat

    … long-term operation, the camera is affected by lighting changes, and the appearance of the environment changes. This poses a challenge for localizing to the visual map that was built when teaching the path. VT&R can operate across large appearance change by using multi-experience localization. …

    toronto-retro Repository record for Towards Deep Learning for Long-term Visual Localization in Visual Teach and Repeat (opens in a new tab)

  5. Expanding the Limits of Vision-Based Autonomous Path Following

    … perform localization across extreme appearance change, most are not suitable or untested for vision-in-the-loop systems such as autonomous path following, which requires continuous metric localization to keep the robot driving. This thesis extends the performance of vision-based autonomous path …

    toronto-retro Repository record for Expanding the Limits of Vision-Based Autonomous Path Following (opens in a new tab)

  6. ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE

    … at that pixel. As the scene illumination changes, a pixel's color is predicted using a linear model of the codeword and the codeword, in turn, is updated using the new observation. We carried out a number of experiments on sequences that have extensive lighting change and compare with …

    maryland Repository record for ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE (opens in a new tab)

  7. Counting of Mostly Static People in Indoor Conditions

    … The background scene is uncontrolled. Lighting is complex and varying. And, image resolution, both in terms of spatial and temporal is usually poor, especially in pre-stored surveillance videos. Passive counting of people from video has many practical applications such as in monitoring …

    usf Repository record for Counting of Mostly Static People in Indoor Conditions (opens in a new tab)

  8. Model-driven and Data-driven Approaches for some Object Recognition Problems

    … for the problem of face recognition under lighting change, and show that the direction of image gradient largely preserves object properties across varying lighting conditions. The second part of the dissertation utilizes information conveyed by large quantity of data to learn contextual …

    maryland Repository record for Model-driven and Data-driven Approaches for some Object Recognition Problems (opens in a new tab)

  9. Towards open-world image recognition

    … the input distribution of a particular category changes from the training time. Deep models can easily make mistakes with a small change in the input, such as small noise addition, lighting change, or changes in the object pose. On the other hand, unseen classes - classes that are absent in the …

    bu Repository record for Towards open-world image recognition (opens in a new tab)

  10. Vision-Based Observation Models for Lower Limb 3D Tracking with a Moving Platform

    … are also investigated for handling appearance change of tracking target: increasing number of templates and using different representations of colors. For the depth camera, two observation likelihoods are developed: the first one works directly in the 3D space, while the second one works in the …

    waterloo Repository record for Vision-Based Observation Models for Lower Limb 3D Tracking with a Moving Platform (opens in a new tab)