Engineering Commons^™

Advanced Traffic Video Analytics For Robust Traffic Accident Detection, Hadi Ghahremannezhad

Dissertations

Automatic traffic accident detection is an important task in traffic video analysis due to its key applications in developing intelligent transportation systems. Reducing the time delay between the occurrence of an accident and the dispatch of the first responders to the scene may help lower the mortality rate and save lives. Since 1980, many approaches have been presented for the automatic detection of incidents in traffic videos. In this dissertation, some challenging problems for accident detection in traffic videos are discussed and a new framework is presented in order to automatically detect single-vehicle and intersection traffic accidents in real-time.

First, …

Investigating The Application Of Deep Convolutional Neural Networks In Semi-Supervised Video Object Segmentation, Jayadeep Sasikumar

Dissertations

This thesis investigates the different approaches to video object segmentation and the current state-of-the-art in the discipline, focusing on the different deep learning techniques used to solve the problem. The primary contribution of the thesis is the investigation of usefulness of Exponential Linear Units as activation functions for deep convolutional neural architectures trained to perform object semi-supervised segmentation in videos. Mask R-CNN was chosen as the base convolutional neural architecture, with the view of extending the image segmentation algorithm to videos. Two models were created, one with Rectified Linear Units and the other with Exponential Linear Units as the respective …

Investigating The Impact Of Unsupervised Feature-Extraction From Multi-Wavelength Image Data For Photometric Classification Of Stars, Galaxies And Qsos, Annika Lindh

Dissertations

This thesis reviews the current state of photometric classification in Astronomy and identifies two main gaps: a dependence on handcrafted rules, and a lack of interpretability in the more successful classifiers. To address this, Deep Learning and Computer Vision were used to create a more interpretable model, using unsupervised training to reduce human bias.

The main contribution is the investigation into the impact of using unsupervised feature-extraction from multi-wavelength image data for the classification task. The feature-extraction is achieved by implementing an unsupervised Deep Belief Network to extract lower-dimensionality features from the multi-wavelength image data captured by the Sloan Digital …