Computational Imaging & VisAnalysis

#357: D. K. Ufuktepe, J. Collins, E. Ufuktepe, J. Fraser, T. Krock, and K. Palaniappan

Learning-based shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds

IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI), 2021

Abstract, Bibtex, PlainText, Google Scholar

@inproceedings{2021a,
  author = "D. K. Ufuktepe and J. Collins and E. Ufuktepe and J. Fraser and T. Krock and K. Palaniappan",
  title = "Learning-based shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds",
  year = 2021,
  journal = "IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI)",
  month = "Oct"
}

D. K. Ufuktepe, J. Collins, E. Ufuktepe, J. Fraser, T. Krock, and K. Palaniappan. Learning-based shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds. IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI), October 2021.

#358: K. Nouduri, K. Gao, J. Fraser, S. Yao, H. AliAkbarpour, F. Bunyak, and K. Palaniappan

Deep realistic novel view generation for city-scale aerial images

IEEE International Conference on Pattern Recognition (ICPR), pgs. 7, 2021

3d voxel rendering, denoising, convolutional neural networks, synthetic aerial imagery, point cloud evaluation

Abstract, Bibtex, PlainText, PDF, DOI, Google Scholar

@inproceedings{Rohit2021:ICPR_deep-realistic-views,
  author = "K. Nouduri and K. Gao and J. Fraser and S. Yao and H. AliAkbarpour and F. Bunyak and K. Palaniappan",
  title = "Deep realistic novel view generation for city-scale aerial images",
  year = 2021,
  journal = "IEEE International Conference on Pattern Recognition (ICPR)",
  pages = "7",
  month = "Jan",
  keywords = "3d voxel rendering, denoising, convolutional neural networks, synthetic aerial imagery, point cloud evaluation",
  doi = "10.1109/ICPR48806.2021.9412844"
}

K. Nouduri, K. Gao, J. Fraser, S. Yao, H. AliAkbarpour, F. Bunyak, and K. Palaniappan. Deep realistic novel view generation for city-scale aerial images. IEEE International Conference on Pattern Recognition (ICPR), pages 7, January 2021.

#349: C. Davis, J. Collins, J. Fraser, H. Zhang, S. Yao, E. Lattanzio, B. Balakrishnan, Y. Duan, P. Calyam, and K. Palaniappan

3D Modeling of Cities for Virtual Environments

2021 IEEE International Conference on Big Data (Big Data), pgs. 5587--5596, 2021

Abstract, Bibtex, PlainText, PDF, Google Scholar

@inproceedings{davis20213d,
  author = "C. Davis and J. Collins and J. Fraser and H. Zhang and S. Yao and E. Lattanzio and B. Balakrishnan and Y. Duan and P. Calyam and K. Palaniappan",
  title = "3D Modeling of Cities for Virtual Environments",
  year = 2021,
  booktitle = "2021 IEEE International Conference on Big Data (Big Data)",
  pages = "5587--5596"
}

C. Davis, J. Collins, J. Fraser, H. Zhang, S. Yao, E. Lattanzio, B. Balakrishnan, Y. Duan, P. Calyam, and K. Palaniappan. 3D Modeling of Cities for Virtual Environments. 2021 IEEE International Conference on Big Data (Big Data), pages 5587--5596, 2021.

#331: K. Gao, H. Aliakbarpour, J. Fraser, K. Nouduri, F. Bunyak, R. Massaro, G. Seetharaman, and K. Palaniappan

Local feature performance evaluation for Structure-from-Motion and multi-view stereo using simulated city-scale aerial imagery

IEEE Sensors Journal, Volume 21, pgs. 11615 - 11627, 2020

local feature detector, sift, surf, orb, akaze binary feature, mser, lf-net, superpoint, image matching, photogrammetry, camera pose, bundle adjustment, simulation environments, virtual reality, augmented reality

Abstract, Bibtex, PlainText, PDF, URL, DOI, Google Scholar

@article{KeGao2020:Sensors_SfM_COLMAP,
  author = "K. Gao and H. Aliakbarpour and J. Fraser and K. Nouduri and F. Bunyak and R. Massaro and G. Seetharaman and K. Palaniappan",
  title = "Local feature performance evaluation for Structure-from-Motion and multi-view stereo using simulated city-scale aerial imagery",
  year = 2020,
  journal = "IEEE Sensors Journal",
  volume = 21,
  number = 10,
  pages = " 11615 - 11627",
  month = "Dec",
  keywords = "local feature detector, sift, surf, orb, akaze binary feature, mser, lf-net, superpoint, image matching, photogrammetry, camera pose, bundle adjustment, simulation environments, virtual reality, augmented reality",
  doi = "10.1109/JSEN.2020.3042810",
  url = "https://ieeexplore.ieee.org/abstract/document/9284524"
}

K. Gao, H. Aliakbarpour, J. Fraser, K. Nouduri, F. Bunyak, R. Massaro, G. Seetharaman, and K. Palaniappan. Local feature performance evaluation for Structure-from-Motion and multi-view stereo using simulated city-scale aerial imagery. IEEE Sensors Journal, volume 21, issue 10, pages  11615 - 11627, December 2020.

#336: E. Ufuktepe, V. Ramtekkar, K. Gao, N. Al-Shakarji, J. Fraser, H. AliAkbarpour, G. Seetharaman, and K. Palaniappan

pyTAG: Python-based interactive training data generation for visual tracking algorithms

Proc. SPIE Conf. Geospatial InfoFusion X (Defense + Commercial Sensing), Volume 11398, 2020

ground-truth generation, visual tracking, crowd sourcing, annotation, deep learning

Abstract, Bibtex, PlainText, Software, URL, DOI, Google Scholar

Visual object tracking has been always an important topic in the computer vision community due to its wide range of applications in many domains. While a considerable number of unsupervised and supervised visual tracking algorithms have been developed, the visual tracking field continues to explore improved algorithms and challenging new applications such as multispectral object tracking, multiobject tracking and tracking from moving platforms. Ground truth-based evaluation of tracking algorithms is an essential component for measuring tracker performance. However, manual ground-truth generation by tagging objects of interest in video sequences is an extremely tedious and error prone task that can be subjective especially in complex scenes. In visual tracking, some of the common challenges based on the environment characteristics and object movements are occlusion of the objects of interest, splitting or merging of groups of objects, id switches, and target drift due to model update errors during tracking. These problems can cause video object tracking algorithms to lose the object of interest or start tracking the wrong object due to id switches between objects of similar appearance or target drift due to model update errors. To improve longer, persistent, more accurate tracking for intelligent scene perception, the new generation of tracking algorithms incorporate machine learning based approaches. These supervised tracking algorithms require large training sets, especially deep convolution neural networks with millions of parameters. Therefore, it is important to generate accurate training data and ground truth for tracking. In this study, a training data and ground-truth generation tool called pyTAG is implemented for visual tracking. The proposed tool's plugin structure allows integration, testing, and validation of different trackers. The tracker can be paused, resumed, forwarded, rewound and re-initialized after it loses the object during training data generation. Most importantly pyTAG allows users to change the object tracking method during ground-truth generation. This feature provides the flexibility to adapt the challenges that occur in ground-truth generation by switching the object tracking method that performs better than the other object tracking methods. This tool has been implemented to assist researchers to rapidly generate ground-truth and training data, fix annotations, run and visualize custom or existing object tracking techniques.

@inproceedings{ufuktepe2020pytag,
  author = "E. Ufuktepe and V. Ramtekkar and K. Gao and N. Al-Shakarji and J. Fraser and H. AliAkbarpour and G. Seetharaman and K. Palaniappan",
  title = " pyTAG: Python-based interactive training data generation for visual tracking algorithms",
  year = 2020,
  journal = "Proc. SPIE Conf. Geospatial InfoFusion X (Defense + Commercial Sensing)",
  volume = 11398,
  keywords = "ground-truth generation, visual tracking, crowd sourcing, annotation, deep learning",
  doi = "10.1117/12.2561718",
  url = "https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11398/113980D/pyTAG--python-based-interactive-training-data-generation-for-visual/10.1117/12.2561718.full?SSO=1"
}

E. Ufuktepe, V. Ramtekkar, K. Gao, N. Al-Shakarji, J. Fraser, H. AliAkbarpour, G. Seetharaman, and K. Palaniappan.  pyTAG: Python-based interactive training data generation for visual tracking algorithms. Proc. SPIE Conf. Geospatial InfoFusion X (Defense + Commercial Sensing), volume 11398, 2020.

#230: K. Palaniappan, M. Poostchi, H. Aliakbarpour, R. Viguier, J. Fraser, F. Bunyak, A. Basharat, S. Suddarth, E. Blasch, R. Rao, and G. Seetharaman

Moving object detection for vehicle tracking in wide area motion imagery using 4D filtering

Proc. IEEE International Conference on Pattern Recognition (ICPR), 2016

wami, tracking

Abstract, Bibtex, PlainText, URL, Google Scholar

@inproceedings{Poostchi_2016_ICPR_Tracking,
  author = "K. Palaniappan and M. Poostchi and H. Aliakbarpour and R. Viguier and J. Fraser and F. Bunyak and A. Basharat and S. Suddarth and E. Blasch and R. Rao and G. Seetharaman",
  title = "Moving object detection for vehicle tracking in wide area motion imagery using 4D filtering",
  year = 2016,
  journal = "Proc. IEEE International Conference on Pattern Recognition (ICPR)",
  month = "Dec",
  keywords = "wami, tracking",
  url = "http://icpr2016.org/"
}

K. Palaniappan, M. Poostchi, H. Aliakbarpour, R. Viguier, J. Fraser, F. Bunyak, A. Basharat, S. Suddarth, E. Blasch, R. Rao, and G. Seetharaman. Moving object detection for vehicle tracking in wide area motion imagery using 4D filtering. Proc. IEEE International Conference on Pattern Recognition (ICPR), December 2016.

#168: J. Fraser, A. Haridas, G. Seetharaman, R. Rao, and K. Palaniappan

KOLAM: A cross-platform architecture for scalable visualization and tracking in wide-area motion imagery

Proc. SPIE Conf. Geospatial InfoFusion III (Defense, Security and Sensing: Sensor Data and Information Exploitation), Volume 8747, pgs. 87470N, 2013

visualization, big data, wami, tracking, fmv, features, motion, dod, biomedical

Abstract, Bibtex, PlainText, PDF, DOI, Google Scholar

KOLAM is an open, cross-platform, interoperable, scalable and extensible framework supporting a novel multi- scale spatiotemporal dual-cache data structure for big data visualization and visual analytics. This paper focuses on the use of KOLAM for target tracking in high-resolution, high throughput wide format video also known as wide-area motion imagery (WAMI). It was originally developed for the interactive visualization of extremely large geospatial imagery of high spatial and spectral resolution. KOLAM is platform, operating system and (graphics) hardware independent, and supports embedded datasets scalable from hundreds of gigabytes to feasibly petabytes in size on clusters, workstations, desktops and mobile computers. In addition to rapid roam, zoom and hyper- jump spatial operations, a large number of simultaneously viewable embedded pyramid layers (also referred to as multiscale or sparse imagery), interactive colormap and histogram enhancement, spherical projection and terrain maps are supported. The KOLAM software architecture was extended to support airborne wide-area motion imagery by organizing spatiotemporal tiles in very large format video frames using a temporal cache of tiled pyramid cached data structures. The current version supports WAMI animation, fast intelligent inspection, trajectory visualization and target tracking (digital tagging); the latter by interfacing with external automatic tracking software. One of the critical needs for working with WAMI is a supervised tracking and visualization tool that allows analysts to digitally tag multiple targets, quickly review and correct tracking results and apply geospatial visual analytic tools on the generated trajectories. One-click manual tracking combined with multiple automated tracking algorithms are available to assist the analyst and increase human effectiveness. Keywords: wide-area motion imagery, WAMI, digital tagging, assisted tracking, trajectory visualization, tra- jectory data mining, spatiotemporal cache, multiresolution tiled pyramid imagery

@inproceedings{Fraser:KOLAM_SPIE-2013,
  author = "J. Fraser and A. Haridas and G. Seetharaman and R. Rao and K. Palaniappan",
  title = "KOLAM: A cross-platform architecture for scalable visualization and tracking in wide-area motion imagery",
  year = 2013,
  booktitle = "Proc. SPIE Conf. Geospatial InfoFusion III (Defense, Security and Sensing: Sensor Data and Information Exploitation)",
  volume = 8747,
  pages = "87470N",
  keywords = "visualization, big data, wami, tracking, fmv, features, motion, dod, biomedical",
  doi = "10.1117/12.2018162"
}

J. Fraser, A. Haridas, G. Seetharaman, R. Rao, and K. Palaniappan. KOLAM: A cross-platform architecture for scalable visualization and tracking in wide-area motion imagery. Proc. SPIE Conf. Geospatial InfoFusion III (Defense, Security and Sensing: Sensor Data and Information Exploitation), volume 8747, pages 87470N, 2013.

#123: A. Haridas, R. Pelapur, J. Fraser, F. Bunyak, and K. Palaniappan

Visualization of automated and manual trajectories in wide-area motion imagery

15th Int. Conf. Information Visualization, pgs. 288--293, 2011

visualization, big data, wami, tracking, fmv, features, motion, dod

Abstract, Bibtex, PlainText, PDF, URL, DOI, Google Scholar

@inproceedings{Haridas:InfoVis-2011,
  author = "A. Haridas and R. Pelapur and J. Fraser and F. Bunyak and K. Palaniappan",
  title = "Visualization of automated and manual trajectories in wide-area motion imagery",
  year = 2011,
  booktitle = "15th Int. Conf. Information Visualization",
  pages = "288--293",
  keywords = "visualization, big data, wami, tracking, fmv, features, motion, dod",
  doi = "10.1109/IV.2011.67",
  url = "http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6004056"
}

A. Haridas, R. Pelapur, J. Fraser, F. Bunyak, and K. Palaniappan. Visualization of automated and manual trajectories in wide-area motion imagery. 15th Int. Conf. Information Visualization, pages 288--293, 2011.

#114: K. Palaniappan, F. Bunyak, P. Kumar, I. Ersoy, S. Jaeger, K. Ganguli, A. Haridas, J. Fraser, R. Rao, and G. Seetharaman

Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video

13th Int. Conf. Information Fusion, 2010

wami, tracking, fmv, motion, features, fusion, dod

Abstract, Bibtex, PlainText, PDF, URL, DOI, Google Scholar

@inproceedings{Pal:Fusion-2010,
  author = "K. Palaniappan and F. Bunyak and P. Kumar and I. Ersoy and S. Jaeger and K. Ganguli and A. Haridas and J. Fraser and R. Rao and G. Seetharaman",
  title = "Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video",
  year = 2010,
  booktitle = "13th Int. Conf. Information Fusion",
  keywords = "wami, tracking, fmv, motion, features, fusion, dod",
  doi = "10.1109/ICIF.2010.5711891",
  url = "http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5711891"
}

K. Palaniappan, F. Bunyak, P. Kumar, I. Ersoy, S. Jaeger, K. Ganguli, A. Haridas, J. Fraser, R. Rao, and G. Seetharaman. Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video. 13th Int. Conf. Information Fusion, 2010.

#37: K. Palaniappan and J. Fraser

Multiresolution tiling for interactive viewing of large datasets

17th Int. AMS Conf. on Interactive Information and Processing Systems (IIPS) for Meteorology, Oceanography and Hydrology, pgs. 338--342, 2001

visualization, big data, parallelization, cloud, remote sensing

Bibtex, PlainText, PDF, Google Scholar

@inproceedings{Palani:KolamAMS-2001,
  author = "K. Palaniappan and J. Fraser",
  title = "Multiresolution tiling for interactive viewing of large datasets",
  year = 2001,
  booktitle = "17th Int. AMS Conf. on Interactive Information and Processing Systems (IIPS) for Meteorology, Oceanography and Hydrology",
  pages = "338--342",
  keywords = "visualization, big data, parallelization, cloud, remote sensing"
}

#36: K. Palaniappan, A. Hasler, J. Fraser, and M. Manyin

Network-based visualization using the distributed image spreadsheet (DISS)

17th Int. AMS Conf. on Interactive Information and Processing Systems (IIPS) for Meteorology, Oceanography and Hydrology, pgs. 399--403, 2001

visualization, big data, parallelization, cloud, remote sensing

Bibtex, PlainText, PDF, Google Scholar

@inproceedings{Palani:Network-AMS-2001,
  author = "K. Palaniappan and A. Hasler and J. Fraser and M. Manyin",
  title = "Network-based visualization using the distributed image spreadsheet (DISS)",
  year = 2001,
  booktitle = "17th Int. AMS Conf. on Interactive Information and Processing Systems (IIPS) for Meteorology, Oceanography and Hydrology",
  pages = "399--403",
  keywords = "visualization, big data, parallelization, cloud, remote sensing"
}

11 Publications by "J. Fraser"

3d voxel rendering, denoising, convolutional neural networks, synthetic aerial imagery, point cloud evaluation

local feature detector, sift, surf, orb, akaze binary feature, mser, lf-net, superpoint, image matching, photogrammetry, camera pose, bundle adjustment, simulation environments, virtual reality, augmented reality

ground-truth generation, visual tracking, crowd sourcing, annotation, deep learning

wami, tracking

visualization, big data, wami, tracking, fmv, features, motion, dod, biomedical

visualization, big data, wami, tracking, fmv, features, motion, dod

wami, tracking, fmv, motion, features, fusion, dod

visualization, big data, parallelization, cloud, remote sensing

visualization, big data, parallelization, cloud, remote sensing