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 20 of 21 for “"scene recognition"”.
-
Visual features for scene recognition and reorientation
In this thesis, I investigate how scenes are represented by the human visual system and how observers use visual information to reorient themselves within a space. Scenes, like objects, are three-dimensional spaces that are experienced through twodimensional views and must be recognized from many …
-
Local, Semi-Local and Global Models for Texture, Object and Scene Recognition
… problems of recognizing textures, objects, and scenes in photographs. We present approaches to these recognition tasks that combine salient local image features with spatial relations and effective discriminative learning techniques. First, we introduce a bag of features image model for …
-
Indoor navigation efficiency improvement in intelligent assistive systems (IAS) using neural networks
… in IAS because of the inefficient indoor home scene and object recognition. The problem is therefore addressed by developing different novel methods using neural networks in this thesis. Apart from addressing the mentioned problem, the developed novel methods also focus on addressing the …
-
Features identification and tracking for an autonomous ground vehicle
… tasks: Motion detection, object tracking, scene recognition, and object detection and recognition. For motion detection, we combined the background subtraction method using the mixture of Gaussian models and the optical flow to highlight any moving objects or new entering objects which …
-
Simulating an Optical Neural Network for Deep Learning in Edge Computing
… applications: MNIST digit classification and scene recognition. The netcast ONN enables large DNNs to run on SWaP-limited edge devices with significantly less energy needed to run inference compared to digital models. Software simulations are used to assess netcast’s performance on MNIST …
-
The role of sleep in consolidation of multi-item bound representations
… bound memory representations, focusing on object-scene and action-scene pairings. It was observed that culture was not a factor for actionscene pairings but Western participants were significantly more accurate than East Asian participants for object-scene pairings. Furthermore, object-scene …
-
Examining the Effects of Real-World Experience on Lab-Based Scene Memory
Boundary extension (BE) is as an error in scene memory, such that participants retrieve details beyond the given boundaries of a scene image. Boundary contraction (BC) is the opposite effect, whereby participants retrieve less context within the boundaries of a given scene image. Some research …
-
Visualization of Deep Convolutional Neural Networks
… accuracy in large scale image classification and scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a classification result is achieved. The …
-
Deep Learning Models for Context-Aware Object Detection
… object detection exploit state-of-the-art image recognition networks for classifying the given region-of-interest (ROI) to predefined classes and regressing a bounding-box around it without using any information about the corresponding scene. ContextNet is based on an intuitive idea of having …
-
The SUN Action database : collecting and analyzing typical actions for visual scene types
… has increasingly focused on the problem of scene recognition. Scene types are largely defined by the actions one might typically do there: an office is a place someone would typically "work". I introduce the SUN Action database (short for "Scene UNderstanding - Action"): the first effort to …
-
An fMRI dataset of 1,102 natural videos for visual event understanding
… utilizes many visual processes, from object recognition to motion perception. Thus, studying the neural correlates of visual event understanding requires brain responses that capture the entire transformation from video-based stimuli to high-level conceptual understanding. However, despite …
-
Gaze selection in the real world : finding evidence for a preferential selection of eyes
… that when observers are shown complex natural scenes, they look at the eyes more frequently than any other region. This selection preference is enhanced when the social content and activity in the scene is high, and when the task is to report on the attentional states in the scene. Chapters 4 …
-
Development of Resource-Constrained Computer Vision Algorithms: From Conventional Machine Learning to Deep Learning
… compared to existing methods. The LVNet enables scene recognition in televisions and event recognition in Blu-ray recorders while securing a US patent. This adoption demonstrates the successful commercialisation of AI capabilities in resource-constrained consumer devices.<br/><br/>The thesis …
-
Investigation of new learning methods for visual recognition
Visual recognition is one of the most difficult and prevailing problems in computer vision and pattern recognition due to the challenges in understanding the semantics and contents of digital images. Two major components of a visual recognition system are discriminatory feature representation and …
-
Large databases of real and synthetic images for feature evaluation and prediction
… matching to panorama stitching to object and scene recognition. They exploit image regularities to capture structure in images both locally, using a patch around an interest point, and globally, over the entire image. Image features need to be distinctive and robust toward variations in scene …
-
The robot's vista space : a computational 3D scene analysis
… structures they are talking about, and what scene elements they are going to manipulate. This thesis focuses on the analysis of a robot's vista space. Mechanisms for extracting relevant spatial information are developed which enable the robot to recognize in which place it is, to detect the …
-
Canonical views of objects and scenes
… encounter and interact with objects and scenes from various vantage points in everyday life. The present set of studies explored canonical viewpoints in objects and scenes. Three themes were focused on: First, what the actual preferred views are for objects verses scenes; second, whether …
-
The neural correlates of Human Spatial Memory and Representation
… for task difficulty, mental rotation, scene recognition and other ecological confounds. In addition to interactions within the cognitive map, we assessed how, when and where in the brain spatial information is integrated with object information. Our investigations used implicit and …
-
Deep neural network models for image classification and regression
… in computer vision, and particularly in object recognition and detection, deep learning is yet to find its way into other research areas. Furthermore, the performance of deep learning models has a strong dependency on the way in which these latter are designed/tailored to the problem at hand. …
-
The mechanisms of reliable coding in mouse visual cortex
… for reliably coding (Chapter 3). Natural scenes contain unique statistical properties that could be leveraged by the visual cortex for efficient coding. Thus, the first aim is to elucidate how image statistics modulate reliable coding in V1. To this end, I developed a novel noise masking …
Page 1 of 2