Failure Detection in Pedestrian Detection : A Fully Convolutional Neural Network approach
Translated title
Author
Term
4. term
Publication year
2016
Submitted on
2016-06-02
Pages
85
Abstract
Pedestrian detection forms a key prob- lem in computer vision, with applica- tions that can greatly affect every day life. In this project, failures in pedes- trian detectors are attempted to be re- fined by re-evaluating their results via a fully convolutional neural network. The network is trained on a number of datasets which include a custom par- tial occluded pedestrian dataset. The networks efficiency was evaluated by examining the loss through train- ing (iterations) and by measuring the mean intersection union across classes. As a detector, accuracy was measured by comparing the network given a detectors result against state-of-the-art but also by measuring the networks re- fined result against the detector with- out the network. It was found that although results vary, the proposed network shows promising results.
Documents