Region Proposal Based Object Detectors Integrated With an Extended Kalman Filter for a Robust Detect-Tracking Algorithm
In this thesis we present a detect-tracking algorithm (see figure 3.1) that combines the detection robustness of static region proposal based object detectors, like the faster region convolutional neural network (R-CNN) and the region-based fully convolutional networks (R-FCN) model, with the tracki...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)
2019
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-72698 |