The Applied Imagery Pattern Recognition (AIPR) workshop aims ‘to bring together researchers from government, industry, and academia in an elegant setting conducive to technical interchange across a broad range of disciplines.’ Presentations at the workshop will cover areas including research and fielded systems, providing a broad vision of the applicability of image analysis technologies.
Kitware’s participation in AIPR workshop includes:
- Presenting on KWiver
- Presenting on multi-target tracking in video
- Presenting on visual analysis of unconstrained images in social forums
Multi-Target Tracking in Video with Adaptive Integration of Appearance and Motion Models
By Arslan Basharat, Ilker Ersoy, Kannappan Palaniappan, Anthony Hoogs, Gunasekaran Seetharaman
Abstract
In the recent years various appearance-based single target trackers have been proposed with high accuracy in FMV and WAMI. CSURF and LOFT trackers are two such examples that are able to continue tracking targets under difficult conditions but require manual initialization and additional computational cost. Tracking at urban scale is challenging when the goal is to automatically track hundreds to thousands of targets in real-time in WAMI or dozens of multiple high-resolution targets in FMV.
Here we propose a hybrid tracking architecture that utilizes motion detections to robustly initialize multiple tracks, uses a blended approach to integrate appearance-based trackers, provides a generalized API for interfacing such trackers, and adaptively uses motion detection or appearance match to update a track. High quality motion detections are evaluated prior to appearance-based track update due to lower computational complexity. On the other hand appearance-based tracker updates are preferred under difficult conditions like temporary slowing and stopping, low contrast, partial occlusion, complex backgrounds and clutter. Independent of the approach used to update the track, the system allows for the appearance-based trackers to update the model on every frame a track has been updated. Moreover, this architecture also includes time-reverse backward tracking over a limited period of time to exploit asymmetric temporal information for increased target coverage and tracking success.
We demonstrate the proposed approach by interfacing CSURF and LOFT appearance-based trackers into the proposed architecture. This was achieved by implementing the interface API from the Matlab library implementation of these trackers into the overall C++ system. We present quantitative evaluation of the proposed system with four different approaches for appearance modeling, CSURF and LOFT being the two recently demonstrated trackers and for baseline comparison sum-of-squared differences (SSD) template matching and normalized cross-correlation. The results show that combining CSURF appearance-based tracking with motion-based detect-and-track framework produces the best track quality when interfaced in this system.
KWiver: A Open-Source Cross-Platform Video Exploitation Framework
By Keith Fieldhouse, Matthew J. Leotta, Arslan Basharat, Russell Blue, David Stoup, Charles Atkins, Linus Sherrill, Benjamin Boeckel, Paul Tunison, Jacob Becker, Matthew Dawkins, Matthew Woehlke, Roderic Collins, Matt Turek, Anthony Hoogs
Abstract
We introduce KWiver, a cross-platform video exploitation framework that Kitware has begun releasing as open source. Kitware is utilizing a multi-tiered open-source approach to reach as wide an audience as possible. Kitware’s government-funded efforts to develop critical defense technology will be released back to the defense community via Forge.mil, a government open source repository. Infrastructure, algorithms, and systems without release restrictions will be provided to the larger video analytics community via KWiver.org and github.
Our goal is to provide a video analytics technology baseline for repeatable and reproducible experiments, and to provide a focal point for collaboration and contributions from groups across the community. KWiver plans to provide several foundational capabilities. A multi-processing framework allows algorithmic worker code to execute and communicate in a multiprocessing environment. A companion data abstraction layer allows code to scale from small-scale desktop environments based on file I/O to large multi-core systems communicating via databases. Visualization tools provide cross-platform GUIs for viewing algorithmic results overlaid on source video data. Finally, an integrated evaluation framework enables not only quantitative evaluation via common detection and tracking
metrics, but qualitative feedback by feeding annotation and scoring states to the visualization tools. KWiver is the technology behind a full-frame, frame-rate WAMI tracker which has been deployed OCONUS and has been released as government open source on Forge.mil. Upcoming releases will include FMV source data, ground truth, baseline tracking capability, computed tracking results, and evaluation products.
Towards visual analysis of unconstrained images in social forums: Studies on concept detection and personalized economy of images in social networks
By Sangmin Oh, Eric Smith, Yiliang Xu, Anthony Hoogs
Physical Event