This thesis tackles the challenge of registering modern to historic images in the context of urban rephotography. It aims at automatically identifying stable image features in scenes, which have been exposed to medium to tremendous changes across the years. Instead, the related field of location recognition mainly focuses on illumination and seasonal changes. This work illustrates that common feature descriptors are applicable in the context of historic and modern image matching, while local detectors are not, but most important is the choice of appropriate correspondence filters. It is verified that major structural changes are most challenging for traditional image matching approaches and the methods developed in this work are applicable to challenging image pairs beyond rephotography. Besides, features extracted from Convolutional Neural Networks (CNNs), originally trained for the task of location recognition, show high performance and should be further developed for the specific task of historic to modern image matching. At last, practical developments are presented, including an online portal for presenting and organizing rephotographs as well as an initial version of a mobile application, which supports recovering the original viewpoint of an image.

In 1976 two young photographers, Mark Klett and JoAnn Verburg, and a photo-historian named Ellen Manchester came together with an idea to rephotograph sites in the American West that had originally been documented by survey photographers such as William Henry Jackson and Timothy O'Sullivan. By the spring of 1977 and with the support of various organizations they began a project that spanned the next three years and would eventually become known as the Rephotographic Survey Project (RSP). In many ways, the RSP represents an important moment in the history of photography and the representation of the American West. Through analysis of their work, archival documents, contemporary sources, and interviews with the original members of the RSP and several others, this dissertation examines the activities of the project and its various members, which also included Gordon Bushaw and Rick Dingus. More than the RSP, this dissertation also focuses on the growing culture of photography that boomed in the 1970s. Photography was no longer seen as an outsider to the world of art but was benefiting from newfound opportunities and growth. Without such a culture, this work argues, it would not have been possible for the RSP to take place. By the end of their project, however, photography was undergoing another important transition as modernism was giving way to the more critical climate of postmodernism. When the RSP finally published their work In 1984, their project and the community of photography that fostered their ideas was undergoing profound changes. This study also closely examines the RSP's fieldwork in the American West and the various discourses that the project encountered in this meaningful space. Like photography, the West was undergoing significant changes that the RSP was able to observe and document. Through their process that matched images from the past with photographs of their present, the RSP was able to record diverse landscapes that had or had not changed over the subsequent century. Furthermore, it also provided insight into the ways in which the West had been represented and perceived over time and in a new history of the West.

No description available.

No description available.

This study reports on the quantitative evaluation of a set of state-of-the-art feature detectors and descriptors in the context of repeat photography. Unlike most related work, the proposed study assesses the performance of feature detectors when intra-pair variations are uncontrolled and due to a variety of factors (landscape change, weather conditions, different acquisition sensors). There is no systematic way to model the factors inducing image change. The proposed evaluation is performed in the context of image matching, i.e. in conjunction with a descriptor and matching strategy. Thus, beyond just comparing the performance of these detectors and descriptors, we also examine the feasibility of feature-based matching on repeat photography. Our dataset consists of a set of repeat and historic images pairs that are representative for the database created by the Mountain Legacy Project www.mountainlegacy.ca. / Graduate

Rephotography has been a popular research topic in the photography field for a long time. The purpose of rephotography itself is to repeatedly take photographs of the same scene at a different time. As a result, the sequence of rephotographs with the reference, often historical, the picture provides a compelling visualization of the evolution of the subject or capture its changes in time. However, the act of rephotography is difficult for the rephotographers as they have to cope with the ambiguous motions in six degrees of freedom and with the changes of the subject itself or its surrounding environment.        This thesis aims to create a mobile application that would help its users to capture a rephotograph more accurately and allow them to share the scenes amongst other users. The designed application uses available on-device sensors to navigate the user to the location and guide the user during the rephotography process to capture a precise rephotograph. Furthermore, the application contains user interface elements designed explicitly for rephotography. Moreover, the work describes topics about user interface design, iOS application development, and designing and deploying backend API for the mobile application.

The aim of this diploma thesis is to design and implement a web application focused on rephotography management. Analyze existing solutions, create list of features and simple graphical user interface. It also includes a design of API structure to communicate with the mobile application. Essential application requirements include adding photos on a map and combining different photos in a photo editor with enhanced auto-alignment features.