You are here

Object Tracking, Geopositioning and Navigation

Object tracking is a typical computer vision problem defined in image space. Extending it to 3D can be achieved by 3D sensing of the environment. Our focus in PCVLab includes and goes beyond typical object tracking to geopositioning objects in an absolute coordinate system. This task can be realized  by using georeferenced data such as topological maps.

Contributors

  • Bing Zha (zha.44@osu)
  • Taha Koroglu
  • Jianli Wei
  • Akif Durdu
  • Mehmet Korkmaz
  • Media

Geopositioning and Navigation

Publications

  1. B. Zha and A. Yilmaz. January 2021. Map-Based Temporally Consistent Geolocalization through Learning Motion Trajectories. International Conf. on Computer Vision (ICPR). Milan Italy
  2. B. Zha and A. Yilmaz. Learning Maps for Object Localization using Visual-Inertial Odometry. 2020 ISPRS Annals of Photogrammetry and Remote Sensing Spatial Information Science. Nice, France. September 2020.
  3. B. Zha, M. T. Koroglu and A. Yilmaz, “Trajectory Mining for Localization using Re-current Neural Network,” 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, 2019, pp. 1-4.
  4. J. Wei, M. T. Koroglu, B. Zha and A. Yilmaz, “Pedestrian localization on topological maps with neural machine translation network,” 2019 IEEE SENSORS, Montreal, Canada, 2019, pp. 1-4.
  5. M. T. Koroglu, M. Korkmaz, A. Yilmaz and A. Durdu, “Multiple hypothesis testing approach to pedestrian inertial navigation,” 2019 IEEE Indoor Positioning Indoor Navigation Conference (IPIN), Pisa, Italy, 2019, pp. 1-8.
  6. M. T. Koroglu and A. Yilmaz, “Pedestrian inertial navigation via non-recursive Bayesian map-matching,” 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, 2018, pp. 1909-1914.
  7. M. T. Koroglu and A. Yilmaz, “Pedestrian inertial navigation with building floor plans for indoor environments via non-recursive Bayesian filtering,” 2017 IEEE SENSORS, Glasgow, Scotland, 2017, pp. 1-3.
  8. M. T. Koroglu and A. Yilmaz, “Pedestrian inertial navigation via non-recursive Bayesian map-matching,” 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, 2018, pp. 1909-1914.
  9. M. T. Koroglu and A. Yilmaz, “Pedestrian inertial navigation with building floor plans for indoor environments via non-recursive Bayesian filtering,” 2017 IEEE SENSORS, Glasgow, Scotland, 2017, pp. 1-3.

Object Tracking

Publications

  1. M. T. Koroglu, A. Yilmaz and C. J. Saul, “A deep learning strategy for stride detection,” 2018 IEEE SENSORS, New Delhi, India, 2018, pp. 1-4.
  2. N. Gard, J. Chen, P. Tang and Yilmaz. 10/2018. Deep Learning and Anthropometric Plane Based Workflow Monitoring by Detecting and Tracking Workers. ISPRS TC 1 Symposium on Innovative Sensing - From Sensors to Methods and Applications. Karlsruhe, Germany.
  3. C. Xiao and A. Yilmaz. 09/2017. A Unique Target Representation and Voting Mechanism For Visual Tracking. IEEE Int. Conf. Image Processing. Beijing, China.
  4. C. Xiao and A. Yilmaz. 06/2017. Visual Tracking Utilizing Object Concept from Deep Learning Network. ISPRS Annals of Photogrammetry and Remote Sensing Spatial Information Science, IV-1-W1, 125-132, https://doi.org/10.5194/isprs-annals-IV-1-W1-125-2017. Hannover, Germany
  5. C. Xiao and A. Yilmaz. 12/2016. Efficient Tracking with Distinctive Target Colors and Silhouette. International Conference On Pattern Recognition (ICPR). Cancun, Mexico.
  6. Hosseinyalamdary and A. Yilmaz. 2015. 3d Super-Resolution Approach For Sparse Laser Scanner Data. ISPRS Ann. Photogrammetry Remote Sensing Spatial Information Science, II-3/W5, 151-157, doi:10.5194/isprsannals-II-3-W5-151-2015, 2015
  7. S. HosseinyAlamdary and A. Yilmaz. 12/2015. Surface Recovery: Fusion of Image and Point Cloud. IEEE ICCV Multi-Sensor Fusion Workshop. Santiago, Chili.
  8. S. HosseinyAlamdary, P.-L. Lai, A. Yilmaz. 2014. Merging images, trajectory, and point clouds for 3D object tracking. ISPRS Photogrammetric Computer Vision TCIII Midterm Symposium. Zurich. Switzerland (September) (Second place award)
  9. Y. J. Lee and A. Yilmaz. Real-time object detection, tracking, and 3d positioning in a multiple camera setup. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. II-3/W2, pp. 31–35, 2013.
  10. F. Porikli and A. Yilmaz. 2012. Object Tracking. In Video Analytics for Business Intelligence. Edited by C. Shan, F. Porikli, T. Xiang and S. Gong. New York, NY: Springer Verlag. ISBN 978-3-642-28597-4
  11. A. Yilmaz. 2011. Detecting and Tracking the Action Content. In Computer Analysis of Human Behavior. Advances in Pattern Recognition. Edited by Theo Gevers and Albert Ali Salah. New York, NY: Springer Verlag. 41-68. ISBN 978-0-85729-993-2
  12. A. Yilmaz. March 2011. Kernel Based Object Tracking Using Asymmetric Kernels with Adaptive Scale and Orientation Selection.  Machine Vision and Applications Journal. Vol. 22, no. 2: 255-268. https://doi.org/10.1007/s00138-009-0237-4
  13. A. Yilmaz. 2007. Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). Minneapolis, MN, USA. (June): 1-6.
  14. A. Yilmaz, O. Javed and M. Shah. January 2006. Object Tracking: A Survey.  ACM Journal of Computing Surveys. Vol. 38, no. 4. https://doi.org/10.1145/1177352.1177355
  15. A. Yilmaz, K. Shafique and M. Shah. July 2003. Target Tracking in Airborne Forward Looking Infrared Imagery.  Image and Vision Computing. Vol. 21, no. 7: 623-635. https://doi.org/10.1016/S0262-8856(03)00059-3
  16. A. Yilmaz, K. Shafique, N. Lobo, T. Olson and M. Shah. 12/2001. Target Tracking in FLIR Imagery Using Mean-Shift and Global Motion Compensation. In: IEEE Workshop on Computer Vision Beyond Visible Spectrum. pp. 1-6