Feature-based camera pose estimation

The estimating of the relative orientation and position of a camera is one of the integral topics in the field of computer vision. The accuracy of a certain Finnish technology company’s traffic sign inventory and localization process can be improved by utilizing the aforementioned concept. The company’s localization process uses video data produced by a vehicle installed camera. The accuracy of estimated traffic sign locations depends on the relative orientation between the camera and the vehicle. This thesis proposes a computer vision based software solution which can estimate a camera’s orientation relative to the movement direction of the vehicle by utilizing video data. The task was solved by using feature-based methods and open source software. When using simulated data sets, the camera orientation estimates had an absolute error of 0.31 degrees on average. The software solution can be integrated to be a part of the traffic sign localization pipeline of the company in question.

This Is a Gorgeous-looking Movie”: Multimodal Interplay between Commentary and Subject Materials in Movie Review Entertainment

The present thesis is a study of movie review entertainment (MRE) which is a contemporary Internet-based genre of texts. MRE are movie reviews in video form which are published online, usually as episodes of an MRE web show. Characteristic to MRE is combining humor and honest opinions in varying degrees as well as the use of subject materials, i.e. clips of the movies, as a part of the review. The study approached MRE from a linguistic perspective aiming to discover 1) whether MRE is primarily text- or image-based and what the primary functions of the modes are, 2) how a reviewer linguistically combines subject footage to her/his commentary?, 3) whether there is any internal variation in MRE regarding the aforementioned questions, and 4) how suitable the selected models and theories are in the analysis of this type of contemporary multimodal data. To answer the aforementioned questions, the multimodal system of image—text relations by Martinec and Salway (2005) in combination with categories of cohesion by Halliday and Hasan (1976) were applied to four full MRE videos which were transcribed in their entirety for the study. The primary data represent varying types of MRE: a current movie review, an analytic essay, a riff review, and a humorous essay. The results demonstrated that image vs. text prioritization can vary between reviews and also within a review. The current movie review and the two essays were primarily commentary-focused whereas the riff review was significantly more dependent on the use of imagery as the clips are a major source of humor which is a prominent value in that type of a review. In addition to humor, clips are used to exemplify the commentary. A reviewer also relates new information to the imagery as well as uses two modes to present the information in a review. Linguistically, the most frequent case was that the reviewer names participants and processes lexically in the commentary. Grammatical relations (reference items such as pronouns and adverbs and conjunctive items in the riff review) were also encountered. There was internal variation to a considerable degree. The methods chosen were deemed appropriate to answer the research questions. Further study could go beyond linguistics to include, for instance, genre and media studies.