Search Results for author: Roman Pflugfelder

Found 6 papers, 0 papers with code

An In-Depth Analysis of Visual Tracking with Siamese Neural Networks

no code implementations3 Jul 2017 Roman Pflugfelder

This survey presents a deep analysis of the learning and inference capabilities in nine popular trackers.

Visual Tracking

Clustering of Static-Adaptive Correspondences for Deformable Object Tracking

no code implementations CVPR 2015 Georg Nebehay, Roman Pflugfelder

We propose a novel method for establishing correspondences on deformable objects for single-target object tracking.

Clustering Object +1

On Learning Vehicle Detection in Satellite Video

no code implementations29 Jan 2020 Roman Pflugfelder, Axel Weissenfeld, Julian Wagner

Vehicle detection in aerial and satellite images is still challenging due to their tiny appearance in pixels compared to the overall size of remote sensing imagery.

Inductive Bias Object +2

The Problem of Fragmented Occlusion in Object Detection

no code implementations27 Apr 2020 Julian Pegoraro, Roman Pflugfelder

This paper presents an analysis of state-of-the-art detectors with imagery of green borders and proposes to train Mask R-CNN on new training data which captures explicitly the problem of fragmented occlusion.

Object object-detection +1

Deep Vehicle Detection in Satellite Video

no code implementations14 Apr 2022 Roman Pflugfelder, Axel Weissenfeld, Julian Wagner

In our experiment only five annotated images yield a $F_1$ score of 0. 81 on a new video showing more complex traffic patterns than the Las Vegas video.

Cannot find the paper you are looking for? You can Submit a new open access paper.