Search for dissertations about: "Video segmentation"
Showing result 11 - 15 of 20 swedish dissertations containing the words Video segmentation.
-
11. Reinforcement Learning for Active Visual Perception
Abstract : Visual perception refers to automatically recognizing, detecting, or otherwise sensing the content of an image, video or scene. The most common contemporary approach to tackle a visual perception task is by training a deep neural network on a pre-existing dataset which provides examples of task success and failure, respectively. READ MORE
-
12. Energy Efficient and Programmable Architecture for Wireless Vision Sensor Node
Abstract : Wireless Vision Sensor Networks (WVSNs) is an emerging field which has attracted a number of potential applications because of smaller per node cost, ease of deployment, scalability and low power stand alone solutions. WVSNs consist of a number of wireless Vision Sensor Nodes (VSNs). READ MORE
-
13. Action in Mind : A Neural Network Approach to Action Recognition and Segmentation
Abstract : Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry.This thesis presents a novel computational approach for human action recognition through different implementations of multi-layer architectures based on artificial neural networks. READ MORE
-
14. Discriminative correlation filters in robot vision
Abstract : In less than ten years, deep neural networks have evolved into all-encompassing tools in multiple areas of science and engineering, due to their almost unreasonable effectiveness in modeling complex real-world relationships. In computer vision in particular, they have taken tasks such as object recognition, that were previously considered very difficult, and transformed them into everyday practical tools. READ MORE
-
15. Multi-target Tracking Using on-line Viterbi Optimisation and Stochastic Modelling
Abstract : To study and compare the safety of intersection, traffic scientists today typically manually monitor the intersection during several days and count how often certain events such as evasive manoeuvres occur. This is a laboursome and costly procedure. READ MORE