Building occupancy estimation has become an important topic for sustainable buildings that has attracted more attention during the pandemics. Estimating building occupancy is a considerable problem in computer vision, while computer vision has achieved breakthroughs in recent years. But, machine learning algorithms for computer vision demand large datasets that may contain users’ private information to train reliable models. As privacy issues pose a severe challenge in the field of machine learning, this work aims to develop a privacypreserved machine learningbased method for people counting using a lowresolution thermal camera with 32 × 24 pixels. The method is applicable for counting people in different scenarios, concretely, counting people in spaces smaller than the field of view (FoV) of the camera, as well as large spaces over the FoV of the camera. In the first scenario, counting people in small spaces, we directly count people within the FoV of the camera by Multiple Object Detection (MOD) techniques. Our MOD method achieves up to 56.8% mean average precision (mAP). In the second scenario, we use Multiple Object Tracking (MOT) techniques to track people entering and exiting the space. We record the number of people who entered and exited, and then calculate the number of people based on the tracking results. The MOT method reaches 47.4% multiple object tracking accuracy (MOTA), 78.2% multiple object tracking precision (MOTP), and 59.6% identification F-Score (IDF1). Apart from the method, we create a novel thermal images dataset containing 1770 thermal images with proper annotation. / Uppskattning av hur många personer som vistas i en byggnad har blivit ett viktigt ämne för hållbara byggnader och har fått mer uppmärksamhet under pandemierna. Uppskattningen av byggnaders beläggning är ett stort problem inom datorseende, samtidigt som datorseende har fått ett genombrott under de senaste åren. Algoritmer för maskininlärning för datorseende kräver dock stora datamängder som kan innehålla användarnas privata information för att träna tillförlitliga modeller. Eftersom integritetsfrågor utgör en allvarlig utmaning inom maskininlärning syftar detta arbete till att utveckla en integritetsbevarande maskininlärningsbaserad metod för personräkning med hjälp av en värmekamera med låg upplösning med 32 x 24 pixlar. Metoden kan användas för att räkna människor i olika scenarier, dvs. att räkna människor i utrymmen som är mindre än kamerans FoV och i stora utrymmen som är större än kamerans FoV. I det första scenariot, att räkna människor i små utrymmen, räknar vi direkt människor inom kamerans FoV med MOD teknik. Vår MOD-metod uppnår upp till 56,8% av den totala procentuella fördelningen. I det andra scenariot använder vi MOT-teknik för att spåra personer som går in i och ut ur rummet. Vi registrerar antalet personer som går in och ut och beräknar sedan antalet personer utifrån spårningsresultaten. MOT-metoden ger 47,4% MOTA, 78,2% MOTP och 59,6% IDF1. Förutom metoden skapar vi ett nytt dataset för värmebilder som innehåller 1770 värmebilder med korrekt annotering.

This paper seeks to find whether the spectrum auctions in Sweden have been conducted efficiently and if there is a de facto model that suits all auctions. The efficiency is conditions that emphasise truthful bidding, price discovery and limits collusive behaviour. The paper compares three different auction models used in Sweden, a beauty contest used in the allocation of 3G spectrums, and the auction model selected for the upcoming 5G spectrum auction. The auction models are as follows: first and second-price sealed-bid auction, SMRA and CCA. We found that beauty contests should not be used in any spectrum allocation as it did not meet the criteria of efficiency outlined in this paper. The first-price sealed-bid auction is not a suitable format for spectrum auctions. According to the theory, it generates equivalent revenues on average as the second-price format, which shows a higher degree of efficient allocation. We found that depending on the blocks sold, both SMRA and CCA can result in somewhat efficient results, but they are not suitable for a single object auction. We found that no de facto auction format is suitable for every spectrum auction to be conducted in the future, but instead that the auction format is dependent on the characteristics of the individual auctions.

abstract: The problem of multiple object tracking seeks to jointly estimate the time-varying cardinality and trajectory of each object. There are numerous challenges that are encountered in tracking multiple objects including a time-varying number of measurements, under varying constraints, and environmental conditions. In this thesis, the proposed statistical methods integrate the use of physical-based models with Bayesian nonparametric methods to address the main challenges in a tracking problem. In particular, Bayesian nonparametric methods are exploited to efficiently and robustly infer object identity and learn time-dependent cardinality; together with Bayesian inference methods, they are also used to associate measurements to objects and estimate the trajectory of objects. These methods differ from the current methods to the core as the existing methods are mainly based on random finite set theory. The first contribution proposes dependent nonparametric models such as the dependent Dirichlet process and the dependent Pitman-Yor process to capture the inherent time-dependency in the problem at hand. These processes are used as priors for object state distributions to learn dependent information between previous and current time steps. Markov chain Monte Carlo sampling methods exploit the learned information to sample from posterior distributions and update the estimated object parameters. The second contribution proposes a novel, robust, and fast nonparametric approach based on a diffusion process over infinite random trees to infer information on object cardinality and trajectory. This method follows the hierarchy induced by objects entering and leaving a scene and the time-dependency between unknown object parameters. Markov chain Monte Carlo sampling methods integrate the prior distributions over the infinite random trees with time-dependent diffusion processes to update object states. The third contribution develops the use of hierarchical models to form a prior for statistically dependent measurements in a single object tracking setup. Dependency among the sensor measurements provides extra information which is incorporated to achieve the optimal tracking performance. The hierarchical Dirichlet process as a prior provides the required flexibility to do inference. Bayesian tracker is integrated with the hierarchical Dirichlet process prior to accurately estimate the object trajectory. The fourth contribution proposes an approach to model both the multiple dependent objects and multiple dependent measurements. This approach integrates the dependent Dirichlet process modeling over the dependent object with the hierarchical Dirichlet process modeling of the measurements to fully capture the dependency among both object and measurements. Bayesian nonparametric models can successfully associate each measurement to the corresponding object and exploit dependency among them to more accurately infer the trajectory of objects. Markov chain Monte Carlo methods amalgamate the dependent Dirichlet process with the hierarchical Dirichlet process to infer the object identity and object cardinality. Simulations are exploited to demonstrate the improvement in multiple object tracking performance when compared to approaches that are developed based on random finite set theory. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2019

Yes / The Atkinson-Shiffrin modal model forms the foundation of our understanding of human memory. It consists of three stores (Sensory Memory (SM), also called iconic memory, Short-Term Memory (STM), and Long-Term Memory (LTM)), each tuned to a different time-scale. Since its inception, the STM and LTM components of the modal model have undergone significant modifications, while SM has remained largely unchanged, representing a large capacity system funneling information into STM. In the laboratory, visual memory is usually tested by presenting a brief static stimulus and, after a delay, asking observers to report some aspect of the stimulus. However, under ecological viewing conditions, our visual system receives a continuous stream of inputs, which is segmented into distinct spatio-temporal segments, called events. Events are further segmented into event-segments. Here we show that SM is not an unspecific general funnel to STM but is allocated exclusively to the current event-segment. We used a Multiple-Object Tracking (MOT) paradigm in which observers were presented with disks moving in different directions, along bi-linear trajectories, i.e., linear trajectories, with a single deviation in direction at the mid-point of each trajectory. The synchronized deviation of all of the trajectories produced an event stimulus consisting of two event-segments. Observers reported the pre-deviation or the post-deviation directions of the trajectories. By analyzing observers' responses in partial- and full-report conditions, we investigated the involvement of SM for the two event-segments. The hallmarks of SM hold only for the current event segment. As the large capacity SM stores only items involved in the current event-segment, the need for event-tagging in SM is eliminated, speeding up processing in active vision. By characterizing how memory systems are interfaced with ecological events, this new model extends the Atkinson-Shiffrin model by specifying how events are stored in the first stage of multi-store memory systems.

This project aims at using deep learning to solve the pedestrian tracking problem for Autonomous driving usage. The research area is in the domain of computer vision and deep learning. Multi-Object Tracking (MOT) aims at tracking multiple targets simultaneously in a video data. The main application scenarios of MOT are security monitoring and autonomous driving. In these scenarios, we often need to track many targets at the same time which is not possible with only object detection or single object tracking algorithms for their lack of stability and usability. Therefore we need to explore the area of multiple object tracking. The proposed method breaks the MOT into different stages and utilizes the motion and appearance information of targets to track them in the video data. We used three different object detectors to detect the pedestrians in frames, a person re-identification model as appearance feature extractor and Kalman filter as motion predictor. Our proposed model achieves 47.6% MOT accuracy and 53.2% in IDF1 score while the results obtained by the model without person re-identification module is only 44.8% and 45.8% respectively. Our experiment results indicate the fact that a robust multiple object tracking algorithm can be achieved by splitted tasks and improved by the representative DNN based appearance features. / Detta projekt syftar till att använda djupinlärning för att lösa problemet med att följa fotgängare för autonom körning. For ligger inom datorseende och djupinlärning. Multi-Objekt-följning (MOT) syftar till att följa flera mål samtidigt i videodata. de viktigaste applikationsscenarierna för MOT är säkerhetsövervakning och autonom körning. I dessa scenarier behöver vi ofta följa många mål samtidigt, vilket inte är möjligt med endast objektdetektering eller algoritmer för enkel följning av objekt för deras bristande stabilitet och användbarhet, därför måste utforska området för multipel objektspårning. Vår metod bryter MOT i olika steg och använder rörelse- och utseendinformation för mål för att spåra dem i videodata, vi använde tre olika objektdetektorer för att upptäcka fotgängare i ramar en personidentifieringsmodell som utseendefunktionsavskiljare och Kalmanfilter som rörelsesprediktor. Vår föreslagna modell uppnår 47,6 % MOT-noggrannhet och 53,2 % i IDF1 medan resultaten som erhållits av modellen utan personåteridentifieringsmodul är endast 44,8%respektive 45,8 %. Våra experimentresultat visade att den robusta algoritmen för multipel objektspårning kan uppnås genom delade uppgifter och förbättras av de representativa DNN-baserade utseendefunktionerna.

Emergency landing is a critical safety mechanism for aerial vehicles. Commercial aircraft have triply-redundant systems that greatly increase the probability that the pilot will be able to land the aircraft at a designated airfield in the event of an emergency. In general aviation, the chances of always reaching a designated airfield are lower, but the successful pilot might use landmarks and other visual information to safely land in unprepared locations. For small unmanned aircraft systems (sUAS), triply- or even doubly-redundant systems are unlikely due to size, weight, and power constraints. Additionally, there is a growing demand for beyond visual line of sight (BVLOS) operations, where an sUAS operator would be unable to guide the vehicle safely to the ground. This thesis presents a machine vision-based approach to emergency landing for small unmanned aircraft systems. In the event of an emergency, the vehicle uses a pre-compiled database of potential landing sites to select the most accessible location to land based on vehicle health. Because it is impossible to know the current state of any ground environment, a camera is used for real-time visual feedback. Using the recently developed Recursive-RANSAC algorithm, an arbitrary number of moving ground obstacles can be visually detected and tracked. If obstacles are present in the selected ditch site, the emergency landing system chooses a new ditch site to mitigate risk. This system is called Safe2Ditch.

This thesis concerns the interdisciplinary field of combinatorial auctions, combining the fields of computer science, optimization and economics. A combinatorial auction is an auction where many items are sold simultaneously and where bidders may submit indivisible combinatorial bids on groups of items. It is commonly believed that good solutions to the allocation problem can be achieved by allowing combinatorial bidding. Determining who wins in a combinatorial auction is fundamentally different from a traditional single-item auction because we are faced with a hard and potentially intractable optimization problem. Also, unless we are limited to truthful mechanisms, game theoretic analysis of the strategic behavior of bidders is still an open problem. We have chosen primarily to study the first-price combinatorial auction, a natural auction widely used in practice. Theoretical analysis of this type of auction is difficult and little has been done previously. In this thesis we investigate and discuss three fundamental questions with significant practical implications for combinatorial auctions. First, because the number of possible bids grows exponentially with the number of items, limitations on the number of bids are typically required. This gives rise to a problem since bidders are unlikely to choose the "correct" bids that make up the globally optimal solution. We provide evidence that an expressive and compact bidding language can be more important than finding the optimal solution. Second, given a first-price (sealed-bid) combinatorial auction, the question of equilibrium bidding strategies remains an open problem. We propose a heuristic for finding such strategies and also present feasible strategies. And finally, is a first-price combinatorial auction worth pursuing compared to the simpler simultaneous (single-item) auction? We prove, through a model capturing many fundamental properties of multiple items scenarios with synergies, that the first-price combinatorial auction produces higher revenue than simultaneous single-item auctions. We provide bounds on revenue, given a significantly more general model, in contrast to previous work.

Video surveillance has long been in use to monitor security sensitive areas such as banks, department stores, crowded public places and borders. The rise in computer speed, availability of cheap large-capacity storage devices and high speed network infrastructure enabled the way for cheaper, multi sensor video surveillance systems. In this thesis, the problem of tracking multiple targets with multiple cameras has been discussed. Cameras have been located so that they have overlapping fields of vision. A dynamic background-modeling algorithm is described for segmenting moving objects from the background, which is capable of adapting to dynamic scene changes and periodic motion, such as illumination change and swaying of trees. After segmentation of foreground scene, the objects to be tracked have been acquired by morphological operations and connected component analysis. For the purpose of tracking the moving objects, an active contour model (snakes) is one of the approaches, in addition to a Kalman tracker. As the main tracking algorithm, a rule based tracker has been developed first for a single camera, and then extended to multiple cameras. Results of used and proposed methods are given in detail.

Individual tracking of objects in the video such as people and the luggages they carry is important for surveillance applications as it would enable deduction of higher level information and timely detection of potential threats. However, this is a challenging problem and many studies in the literature track people and the belongings as a single object. In this thesis, we propose using thermal band video data in addition to the visible band video data for tracking people and their belongings separately for indoor applications using their heat signatures. For object tracking step, an adaptive, fully automatic multi object tracking system based on mean-shift tracking method is proposed. Trackers are refreshed using foreground information to overcome possible problems which may occur due to the changes in object&rsquo / s size, shape and to handle occlusion, split and to detect newly emerging objects as well as objects that leave the scene. By using the trajectories of objects, owners of the objects are found and abandoned objects are detected to generate an alarm. Better tracking performance is also achieved compared a single modality as the thermal reflection and halo effect which adversely affect tracking are eliminated by the complementing visible band data.

This thesis is concerned with modeling geometric patterns. Specifically, a clear and practical definition for regular patterns is proposed. Based on this definition, this thesis proposes the following modeling setting to describe the semantic transfer of a model between various forms of pattern regularity: (1) recognition or identification of patterns in digital models of 3D assemblies and scenes, (2) pattern regularization, (3) pattern modification and editing by varying the repetition parameters, and (4) establishing exceptions (designed irregularities) in regular patterns. In line with this setting, this thesis describes a representation and approach for designing and editing hierarchical assemblies based on grouped, nested, and recursively nested patterns. Based on this representation, this thesis presents the OCTOR approach for specifying, recording, and producing exceptions in regular patterns. To support editing of free-form shape patterns on surfaces, this thesis also presents the imprint-mapping approach which can be used to identify, extract, process, and apply relief features on surfaces. Pattern regularization, modification, and exceptions are addressed for the case of relief features on surfaces.