Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Klaus McDonald-Maier

SwitchHit: A Probabilistic, Complementarity-Based Switching System for Improved Visual Place Recognition in Changing Environments


Mar 01, 2022
Maria Waheed, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan


  Access Paper or Ask Questions

Using Machine Learning for Anomaly Detection on a System-on-Chip under Gamma Radiation


Jan 05, 2022
Eduardo Weber Wachter, Server Kasap, Sefki Kolozali, Xiaojun Zhai, Shoaib Ehsan, Klaus McDonald-Maier


  Access Paper or Ask Questions

A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms


Sep 22, 2021
Rose Power, Mubariz Zaffar, Bruno Ferrarini, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan


  Access Paper or Ask Questions

Sequence-Based Filtering for Visual Route-Based Navigation: Analysing the Benefits, Trade-offs and Design Choices


Mar 02, 2021
Mihnea-Alexandru Tomită, Mubariz Zaffar, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan

* 7 pages, currently under-review 

  Access Paper or Ask Questions

ConvSequential-SLAM: A Sequence-based, Training-less Visual Place Recognition Technique for Changing Environments


Sep 28, 2020
Mihnea-Alexandru Tomită, Mubariz Zaffar, Michael Milford, Klaus McDonald-Maier, Shoaib Ehsan

* 10 pages, currently under-review 

  Access Paper or Ask Questions

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change


May 17, 2020
Mubariz Zaffar, Shoaib Ehsan, Michael Milford, David Flynn, Klaus McDonald-Maier

* Currently under-review, 25 pages, 16 figures 

  Access Paper or Ask Questions

CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition


Sep 18, 2019
Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Klaus McDonald-Maier

* Submitted in ICRA 2020 

  Access Paper or Ask Questions

Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?


May 22, 2019
Mubariz Zaffar, Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Kostas Alexis, Klaus McDonald-Maier

* IEEE ICRA 2019 Workshop on Aerial Robotics 8 pages, 7 figures 

  Access Paper or Ask Questions

DisplaceNet: Recognising Displaced People from Images by Exploiting Dominance Level


May 03, 2019
Grigorios Kalliatakis, Shoaib Ehsan, Maria Fasli, Klaus McDonald-Maier

* To be published in CVPR Workshop on Computer Vision for Global Challenges (CV4GC). arXiv admin note: substantial text overlap with arXiv:1902.03817 

  Access Paper or Ask Questions

Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions


Mar 21, 2019
Mubariz Zaffar, Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Klaus McDonald-Maier

* 8 pages, 11 figures 

  Access Paper or Ask Questions

A Holistic Visual Place Recognition Approach using Lightweight CNNs for Severe ViewPoint and Appearance Changes


Nov 14, 2018
Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Klaus McDonald-Maier

* Under review at IEEE Transactions on Robotics (T-RO) 

  Access Paper or Ask Questions

MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip


Aug 14, 2018
Somdip Dey, Grigorios Kalliatakis, Sangeet Saha, Amit Kumar Singh, Shoaib Ehsan, Klaus McDonald-Maier

* 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2018) 
* 6 pages, 3 figures, 2 tables 

  Access Paper or Ask Questions

Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks


Aug 01, 2018
Jose Carlos Villarreal Guerra, Zeba Khanam, Shoaib Ehsan, Rustam Stolkin, Klaus McDonald-Maier


  Access Paper or Ask Questions

Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in images


May 12, 2018
Grigorios Kalliatakis, Shoaib Ehsan, Ales Leonardis, Klaus McDonald-Maier

* 19 pages, 13 figures; Submitted to PLOS ONE 

  Access Paper or Ask Questions