Avancerad sökning

Visar resultat 1 - 5 av 21 avhandlingar som matchar ovanstående sökkriterier.

1. 1. Data-Efficient Learning of Semantic Segmentation

   Författare :David Nilsson; Mathematical Imaging Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; semantic segmentation; embodied learning; active learning; semantic video segmentation; computer vision; deep learning;

   Sammanfattning : Semantic segmentation is a fundamental problem in visual perception with a wide range of applications ranging from robotics to autonomous vehicles, and recent approaches based on deep learning have achieved excellent performance. However, to train such systems there is in general a need for very large datasets of annotated images. LÄS MER

3. 2. Learning Representations for Segmentation and Registration

   Författare :Felix Järemo Lawin; Per-Erik Forssén; Michael Felsberg; Radu Patrice Horaud; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computer Vision; point set registration; video object segmentation; time-of-flight; point set segmentation; deep learning; expectation maximization;

   Sammanfattning : In computer vision, the aim is to model and extract high-level information from visual sensor measurements such as images, videos and 3D points. Since visual data is often high-dimensional, noisy and irregular, achieving robust data modeling is challenging. LÄS MER

4. 3. Video Signal Processing: Compression Segmentation and Tracking

   Författare :Andrew Backhouse; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

   Sammanfattning : This thesis considers three separate research problems within the field of video processing.The first is concerned with segmenting an image, the second with tracking an object and the third with the communication of video across an unreliable network.Segmentation is an application-specific problem. LÄS MER

5. 4. Audio-video synthesis methods for improving performance of biometric systems

   Författare :Dereje Teferi Lemma; Josef Bigun; Högskolan i Halmstad; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Biometrics; Audio-Video synthesis; Image segmentation; XM2VTS; DXM2VTS; TECHNOLOGY; TEKNIKVETENSKAP;

   Sammanfattning : System security is important for any automation. It is even more so in the case of biometric systems due to the sensitive nature of the data it uses for enrollment and authentication - the subjects physical or biological trait. LÄS MER

7. 5. Spatio-Temporal Estimation for Mixture Models and Gaussian Markov Random Fields - Applications to Video Analysis and Environmental Modelling

   Författare :Johan Lindström; Matematisk statistik; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; vegetation; time series analysis; video segmentation; spatio-temporal modelling; precipitation; Markov chain Monte Carlo; Gaussian Markov random fields; expectation maximisation; change point detection; Bayesian recursive estimation; African Sahel; adaptive Gaussian mixtures;

   Sammanfattning : In this thesis computationally intensive methods are used to estimate models and to make inference for large, spatio-temporal data sets. The thesis is divided into two parts: the first two papers are concerned with video analysis, while the last three papers model and investigate environmental data from the Sahel area in northern Africa. LÄS MER