Detection and tracking of objects in underwater video
Abstract
For oceanographic research, remotely operated underwater vehicles (ROVs) routinely record several hours of video material each day. Manual processing of such large amounts of video has become a major bottleneck for scientific research based on this data. We have developed an automated system that detects and tracks objects that are of potential interest for human video annotators. By pre-selecting salient targets for track initiation using a selective attention algorithm, we reduce the complexity of multi-target tracking, in particular of the assignment problem. Detection of low-contrast translucent targets is difficult due to variable lighting conditions and the presence of ubiquitous noise from high-contrast organic debris ("marine snow") particles. We describe the methods we developed to overcome these issues and report our results of processing ROV video data.
Additional Information
© 2004 IEEE. This project originated at the 2002 Workshop for Neuromorphic Engineering in Telluride, CO, USA. We thank the David and Lucille Packard Foundation, NSF, NIMH and the NSF Research Coordination Network (RCN) Institute for Neuromorphic Engineering (lNE) for making this research possible. We thank K. Salamy, J. Harmssen and A. Wilson for technical assistance at MBARI. M. Risi engineered our video capture system, D. Cline engineered the Beowulf computer cluster, and R. Sherlock guided our analysis of video images. We thank B. Robison, J. Connor, N. Jacobsen Stout and the MBARI video lab staff for their interest and support.Attached Files
Published - Detection_and_tracking_of_objects_in_underwater_video.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:31ff94fb3a05b5ecac7b644ec1b86b27
|
458.6 kB | Preview Download |
Additional details
- Eprint ID
- 120771
- Resolver ID
- CaltechAUTHORS:20230412-825909000.1
- David and Lucile Packard Foundation
- NSF
- NIH
- Center for Neuromorphic Systems Engineering, Caltech
- Created
-
2023-04-18Created from EPrint's datestamp field
- Updated
-
2023-04-18Created from EPrint's last_modified field
- Caltech groups
- Koch Laboratory (KLAB)