Human faces have been a subject of study in computer science for decades. The rich of set features from human faces have been used in solving various problems in computer vision, including person identification, facial expression analysis, and attribute classification. In this work, I explore the human facial features that depend on the geo-location using a data- driven approach. I analyze millions of public domain images to extract the geo-dependent human facial features and explore their applications. Using various machine learning and statistical techniques, I show that the geo-dependent features of human faces can be used to solve the image geo-localization task of given an image, predict where it was taken. Deep Convolutional Neural Networks (CNN) have been recently shown to excel at the image classification task; I have used CNNs to geo-localize images using the human face as a cue. I also show that the facial features used in image localization can be used to solve other problems, such as ethnicity, gender, and age estimation.

Visual surveillance of human crowds in a dynamic environment has attracted a great amount of computer vision research efforts in recent years. Moving object detection, which conventionally includes motion segmentation and optionally, object classification, is the first major task for any visual surveillance application. After detecting the targets, estimation of their geo-locations is needed to create the same reference coordinate system for them for higher-level decision-making. Depending on the required fidelity of decision, multi-target data association may be also needed at higher levels to differentiate multiple targets in a series of frames. Applying all these vision-based algorithms to a crowd surveillance system (a major application studied in this dissertation) using a team of cooperative unmanned vehicles (UVs), introduces new challenges to the problem. Since the visual sensors move with the UVs, and thus the targets and the environment are dynamic, it adds to the complexity and uncertainty of the video processing. Moreover, the limited onboard computation resources require more efficient algorithms to be proposed. Responding to these challenges, the goal of this dissertation is to design and develop an effective and efficient visual surveillance system based on dynamic data driven application system (DDDAS) paradigm to be used by the cooperative UVs for autonomous crowd control and border patrol. The proposed visual surveillance system includes different modules: 1) a motion detection module, in which a new method for detecting multiple moving objects, based on sliding window is proposed to segment the moving foreground using the moving camera onboard the unmanned aerial vehicle (UAV); 2) a target recognition module, in which a customized method based on histogram-of-oriented-gradients is applied to classify the human targets using the onboard camera of unmanned ground vehicle (UGV); 3) a target geo-localization module, in which a new moving-landmark-based method is proposed for estimating the geo-location of the detected crowd from the UAV, while a heuristic method based on triangulation is applied for geo-locating the detected individuals via the UGV; and 4) a multi-target data association module, in which the affinity score is dynamically adjusted to comply with the changing dispersion of the detected targets over successive frames. In this dissertation, a cooperative team of one UAV and multiple UGVs with onboard visual sensors is used to take advantage of the complementary characteristics (e.g. different fidelities and view perspectives) of these UVs for crowd surveillance. The DDDAS paradigm is also applied toward these vision-based modules, where the computational and instrumentation aspects of the application system are unified for more accurate or efficient analysis according to the scenario. To illustrate and demonstrate the proposed visual surveillance system, aerial and ground video sequences from the UVs, as well as simulation models are developed, and experiments are conducted using them. The experimental results on both developed videos and literature datasets reveal the effectiveness and efficiency of the proposed modules and their promising performance in the considered crowd surveillance application.

No description available.

E-handeln inom Europa växer explosionsartat och tillgång till varor och tjänster är i dagsläget endast några få knapptryck bort. Eftersom åtkomsten till internet är global kan hemsidor och webbshoppar få en enorm internationell spridning. Näringsidkare som bedriver fysisk handel kan enkelt anpassa sig till lagar, språk, valuta mm. i landet där deras verksamhet är placerad, men anpassningen på internet, i cybervärlden, är svårare. Geolokalisering är en teknik som gör det möjligt för näringsidkare att kunna anpassa sig, genom att lokalisera och fastställa var internetanvändare befinner sig. När en internetanvändares geografiska placering är fastställd, kan näringsidkaren anpassa utbud, reklam, språk och valuta på hemsidan som denne bedriver. Möjligheten att kunna lokalisera internetanvändare på detta sätt, är ur ett affärsmässigt perspektiv mycket lönsamt för en näringsidkare. Geolokaliseringen ger även näringsidkaren en möjlighet till att geoblockera internetanvändare från dennes hemsida, genom att exempelvis helt blockera åtkomst, anpassa vilka produkter internetanvändaren får åtkomst till eller omdirigera internetanvändare från en version av hemsidan till en annan. Geoblockering kan därför underlätta det för en näringsidkare att följa regler och lagar i de olika länderna där dennes hemsida är tillgänglig. Immaterialrätter är i regel skyddade inom olika territorium. Med immaterialrätter följer ensamrätt till användande av rättigheten inom skyddsområdet. En näringsidkare som säljer varor på sin e-handels hemsida, som är eller kan vara omfattade av andra innehavares rättighetsskydd, kan använda geoblockering som ett verktyg för att helt undvika eller anpassa sig till de olika immaterialrättsliga skyddsområdena. Kommissionen har meddelat att ett av EU:s mål är att skapa en digital inre marknad och förhindra diskriminering mot konsumenter baserat på nationalitet, bostadsort eller geografisk placering. Diskrimineringen kan utgöras av exempelvis olika begränsningar för en konsument som vill få tillgång till ett innehåll eller köpa varor på internet. En sådan begränsning kan vara geoblockering. Den 25 maj 2016 lade Kommissionen fram ett förordningsförslag, som syftar till att förbjuda omotiverad geoblockering. I november 2016 enades Rådet om ett utkast till förordningen. Förordningsförhandlingarna förväntas påbörja så snart som Europaparlamentet enats om sin ståndpunkt. Frågan är hur ett förbud mot geoblockering kan komma att påverka näringsidkare inom e-handeln, ur ett immaterialrättsligt perspektiv.

The goal of this master thesis is creation of an online system serving as a performing application for presentation results of visual geo-localization in nature and mountain environment. The system offers the users to choose one of the pre-defined photographs or~to~upload one's own photography while choosing a file or inserting an URL address. The~system will localizate a camera of a given image based on a visual geo-localization. The~geo-localization uses the mountain horizon as a key characteristic when searching for similar horizons. The~curve line of the horizon is extracted by a fully automatic algorithm based on supervised learning and dynamic programming. Visual geo-localization running on the server which using new inversed index with cache politic. This allows further scaling of the system. The server processing detected horizon curve and respond with set of the best candidates on results. Results are visualised to the user in form of classic map, detailed sattelite view and rendering of found panorama.

The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. Two networks were trained so that satellite and aerial images taken from different views of the same location had feature vectors that were similar. The networks were also trained so that images taken from different locations had different feature vectors. After training, the position of a given aerial image can then be estimated by finding the satellite image with a feature vector that is the most similar to that of the aerial image.  A previous method called Where-CNN was used as a baseline model. Batch-Hard triplet loss, the Adam optimizer, and a different CNN backbone were tested as possible augmentations to this method. The models were trained on 2640 different locations in Linköping and Norrköping. The models were then tested on a sequence of 4411 query images along a path in Jönköping. The search region had 1449 different locations constituting a total area of 24km2.  In Top-1% accuracy, there was a significant improvement over the baseline, increasing from 61.62% accuracy to 88.62%. The environment was modeled as a Hidden Markov Model to filter the sequence of guesses. The Viterbi algorithm was then used to find the most probable path. This filtering procedure reduced the average error along the path from 2328.0 m to just 264.4 m for the best model. Here the baseline had an average error of 563.0 m after filtering.  A few different 3D methods were also tested. One drawback was that no pretrained weights existed for these models, as opposed to the 2D models, which were pretrained on the ImageNet dataset. The best 3D model achieved a Top-1% accuracy of 70.41%. It should be noted that the best 2D model without using any pretraining achieved a lower Top-1% accuracy of 49.38%. In addition, a 3D method for efficiently doing convolution on sparse 3D data was presented. Compared to the straight-forward method, it was almost 2.5 times faster while still having comparable accuracy at individual query prediction.  While there was a significant improvement over the baseline, it was not significant enough to provide reliable and accurate localization for individual images. For global navigation, using the entire Earth as search space, the information in a 2D image might not be enough to be uniquely identifiable. However, the 3D CNN techniques tested did not improve the results of the pretrained 2D models. The use of more data and experimentation with different 3D CNN architectures is a direction in which further research would be exciting.