No description available.

No description available.

No description available.

<p> In this thesis the problem of object recognition/pose estimation using active sensing is investigated. It is assumed that multiple cameras acquire images from different view angles of an object belonging to a set of a priori known objects. The eigenspace method is used to process the sensory observations and produce an abstract measurement vector. This step is necessary to avoid the manipulation of the original sensor data, i.e. large images, that can render the sensor modelling and matching process practically infeasible.</p> <p> The eigenspace representation is known to have shortcomings in dealing with structured noise such as occlusion. To overcome this problem, models of occlusions and sensor noise have been incorporated into the probabilistic model of sensor/object to increase robustness with respect to such uncertainties. The active recognition algorithm has also been modified to consider the possibility of occlusion, as well as variation in the occlusion levels due to camera movements.</p> <p> A recursive Bayesian state estimation problem is formulated to model the observation uncertainties through a probabilistic scheme. This enables us to identify the object and estimate its pose by fusing the information obtained from individual cameras. To this end, an extensive training step is performed, providing the system with the sensor model required for the Bayesian estimation. In order to enhance the quality of the estimates and to reduce the number of images taken, we employ active real-time viewpoint planning strategies to position cameras. For that purpose, the positions of cameras are controlled based on two different statistical performance criteria, namely the Mutual Information (MI) and Cramér-Rao Lower Bound (CRLB).</p> <p> A multi-camera active vision system has been developed in order to implement the ideas proposed in this thesis. Comparative Monte Carlo experiments conducted with the two-camera system demonstrate the effectiveness of the proposed methods in object classification/pose estimation in the presence of structured noise. Different concepts introduced in this work, i.e., the multi-camera data fusion, the occlusion modelling, and the active camera movement, all improve the recognition process significantly. Specifically, these approaches all increase the recognition rate, decrease the number of steps taken before recognition is completed, and enhance robustness with respect to partial occlusion considerably.</p> / Thesis / Master of Applied Science (MASc)

Remarkable advancements in the field of Computer Vision, Artificial Intelligence and Machine Learning have led to unprecedented breakthroughs in what machines are able to achieve. In many tasks such as in Image Classification in fact, they are now capable of even surpassing human performance. While this is truly outstanding, there are still many tasks in which machines lag far behind. Walking in a room, driving on an highway, grabbing some food for example. These are all actions that feel natural to us but can be quite unfeasible for them. Such actions require to identify and localize objects in the environment, effectively building a robust understanding of the scene. Humans easily gain this understanding thanks to their binocular vision, which provides an high-resolution and continuous stream of information to our brain that efficiently processes it. Unfortunately, things are much different for machines. With cameras instead of eyes and artificial neural networks instead of a brain, gaining this understanding is still an open problem. In this thesis we will not focus on solving this problem as a whole, but instead delve into a very relevant part of it. We will in fact analyze how to make ma- chines be able to identify and precisely localize objects in the 3D space by relying only on visual input i.e. 3D Object Detection from Images. One of the most complex aspects of Image-based 3D Object Detection is that it inherently requires the solution of many different sub-tasks e.g. the estimation of the object’s distance and its rotation. A first contribution of this thesis is an analysis of how these sub-tasks are usually learned, highlighting a destructivebehavior which limits the overall performance and the proposal of an alternative learning method that avoids it. A second contribution is the discovery of a flaw in the computation of the metric which is widely used in the field, affecting the re-computation of the performance of all published methods and the introduction of a novel un-flawed metric which has now become the official one. A third contribution is focused on one particular sub-task, i.e. estimation of the object’s distance, which is demonstrated to be the most challenging. Thanks to the introduction of a novel approach which normalizes the appearance of objects with respect to their distance, detection performances can be greatly improved. A last contribution of the thesis is the critical analysis of the recently proposed Pseudo-LiDAR methods. Two flaws in their training protocol have been identified and analyzed. On top of this, a novel method able to achieve state-of-the-art in Image-based 3D Object Detection has been developed.

Many real world datasets are characterized by having a long tailed distribution, with several samples for some classes and only a few samples for other classes. While many Deep Learning based solutions exist for object recognition when hundreds of samples are available, there are not many solutions for the case when there are only a few samples available per class. Recognition in the regime where the number of training samples available for each class are low, ranging from 1 to couple of tens of examples is called Lowshot Recognition. In this work, we attempt to solve this problem. Our framework is similar to [1]. We use a related dataset with sufficient number (a couple of hundred) of samples per class to learn representations using a Convolutional Neural Network (CNN). This CNN is used to extract features of the lowshot samples and learn a classifier . During representation learning, we enforce the learnt representations to obey certain property by using a custom loss function. We believe that when the lowshot sample obey this property the classification step becomes easier. We show that the proposed solution performs better than the softmax classifier by a good margin. / Master of Science

Recently, disaster scene description and indexing challenges attract the attention of researchers. In this dissertation, we solve a disaster-related multi-labeling task using a newly developed Low Altitude Disaster Imagery dataset. In the first task, we realize video content by selecting a set of summary key frames to represent the video sequence. Through inter-frame differences, the key frames are generated. The key frame extraction of disaster-related video clips is a powerful tool that can efficiently convert video data into image-level data, reduce the requirements for the extraction environment and improve the applicable environment. In the second, we propose a novel application of using deep learning methods on low altitude disaster video feature recognition. Supervised learning-based deep-learning approaches are effective in disaster-related features recognition via foreground object detection and background classification. Performed dataset validation, our model generalized well and improved performance by optimizing the YOLOv3 model and combining it with Resnet50. The comprehensive models showed more efficient and effective than those in prior published works. In the third task, we optimize the whole scene labeling classification by pruning the lightweight model MobileNetV3, which shows superior generalizability and can disaster features recognition from a disaster-related dataset be accomplished efficiently to assist disaster recovery.

Yes / Rationale: Dopamine dysregulation in the prefrontal cortex (PFC) plays an important role in cognitive dysfunction in schizophrenia. Sub-chronic phencyclidine (scPCP) treatment produces cognitive impairments in rodents and is a thoroughly validated animal model for cognitive deficits in schizophrenia. The aim of our study was to investigate the role of PFC dopamine in scPCP-induced deficits in a cognitive task of relevance to the disorder, novel object recognition (NOR). Methods: Twelve adult female Lister Hooded rats received scPCP (2 mg/kg) or vehicle via the intraperitoneal route twice daily for seven days, followed by seven days washout. In vivo microdialysis was carried out prior to, during and following the NOR task. Results: Vehicle rats successfully discriminated between novel and familiar objects and this was accompanied by a significant increase in dopamine in the PFC during the retention trial (P<0.01). scPCP produced a significant deficit in NOR (P<0.05 vs. control) and no PFC dopamine increase was observed. Conclusions: These data demonstrate an increase in dopamine during the retention trial in vehicle rats that was not observed in scPCP-treated rats accompanied by cognitive disruption in the scPCP group. This novel finding suggests a mechanism by which cognitive deficits are produced in this animal model and support its use for investigating disorders in which PFC dopamine is central to the pathophysiology.

Novel methods of object recognition that form a bridge between today&rsquo / s local feature frameworks and previous decade&rsquo / s strong but deserted geometric invariance field are presented in this dissertation. The rationale behind this effort is to complement the lowered discriminative capacity of local features, by the invariant geometric descriptions. Similar to our predecessors, we first start with constrained cases and then extend the applicability of our methods to more general scenarios. Local features approach, on which our methods are established, is reviewed in three parts / namely, detectors, descriptors and the methods of object recognition that employ them. Next, a novel planar object recognition framework that lifts the requirement for exact appearance-based local feature matching is presented. This method enables matching of groups of features by utilizing both appearance information and group geometric descriptions. An under investigated area, scene logo recognition, is selected for real life application of this method. Finally, we present a novel method for three-dimensional (3D) object recognition, which utilizes well-known local features in a more efficient way without any reliance on partial or global planarity. Geometrically consistent local features, which form the crucial basis for object recognition, are identified using affine 3D geometric invariants. The utilization of 3D geometric invariants replaces the classical 2D affine transform estimation /verification step, and provides the ability to directly verify 3D geometric consistency. The accuracy and robustness of the proposed method in highly cluttered scenes with no prior segmentation or post 3D reconstruction requirements, are presented during the experiments.

Today's smartphones are capable of accomplishing far more advanced tasks than reading emails. With the modern framework TensorFlow, visual object recognition becomes possible using smartphone resources. This thesis shows that the main challenge does not lie in developing an artifact which performs visual object recognition. Instead, the main challenge lies in developing an ecosystem which allows for continuous improvement of the system’s ability to accomplish the given task without laborious and inefficient data collection. This thesis presents four design principles which contribute to an efficient ecosystem with quick initiation of new object classes and efficient data collection which is used to continuously improve the system’s ability to recognize smart meters in varying environments in an automated fashion.