Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Theses/Dissertations

Open Access Dissertations

Image processing

Purdue University

Articles 1 - 2 of 2

Full-Text Articles in Engineering

Visual Clutter Study For Pedestrian Using Large Scale Naturalistic Driving Data, Kai Yang Aug 2016

Visual Clutter Study For Pedestrian Using Large Scale Naturalistic Driving Data, Kai Yang

Open Access Dissertations

Some of the pedestrian crashes are due to driver’s late or difficult perception of pedestrian’s appearance. Recognition of pedestrians during driving is a complex cognitive activity. Visual clutter analysis can be used to study the factors that affect human visual search efficiency and help design advanced driver assistant system for better decision making and user experience. In this thesis, we propose the pedestrian perception evaluation model which can quantitatively analyze the pedestrian perception difficulty using naturalistic driving data. An efficient detection framework was developed to locate pedestrians within large scale naturalistic driving data. Visual clutter analysis was used ...


Error Resilient Video Coding Using Bitstream Syntax And Iterative Microscopy Image Segmentation, Neeraj Jayant Gadgil Aug 2016

Error Resilient Video Coding Using Bitstream Syntax And Iterative Microscopy Image Segmentation, Neeraj Jayant Gadgil

Open Access Dissertations

There has been a dramatic increase in the amount of video traffic over the Internet in past several years. For applications like real-time video streaming and video conferencing, retransmission of lost packets is often not permitted. Popular video coding standards such as H.26x and VPx make use of spatial-temporal correlations for compression, typically making compressed bitstreams vulnerable to errors. We propose several adaptive spatial-temporal error concealment approaches for subsampling-based multiple description video coding. These adaptive methods are based on motion and mode information extracted from the H.26x video bitstreams. We also present an error resilience method using data ...