Difference between revisions of "Projects:Augment marker tracking with visual tracking"
m (→Overview) |
(→Estimated level of difficulty) |
||
| Line 23: | Line 23: | ||
== Estimated level of difficulty == | == Estimated level of difficulty == | ||
| − | + | Generating training data for visual object detection should be a pretty straight-forward standard problem, and is a good way to get into the project and data structures in the framework of a Bachelor/Master project. | |
| − | the | + | |
| − | + | An elaborate problem is to find a way to integrate the visual detections into the overall tracking pipeline, since this requires to find a suitable new algorithmic framework. It is closely related to [[Projects:Improve tracking of individual markers and marker patterns|this project]]. | |
| − | |||
| − | |||
| − | |||
== Provided data == | == Provided data == | ||
Revision as of 08:31, 21 May 2019
Contents
Overview
- Input : Video data, 2D location of birds , 3D trajectory (Labelled and unlabeled) - Output: A. Create 2D trajectories. Object detection on birds. (using simple blob tracking, or using machine learning) B. Match 3D - 2D trajectories to identify identity flips. C. Unlabeled trajectories can be combined with 2D trajectories, to fill gaps in 3D trajectories. (Project 2 output can be useful).
Subprojects: 3.1 Offline data processing; 3.2 Online/quasi-real time solution working from the data stream and video stream (video stream is not directly available in real time for processing, but realtime view is generated in the software, so this could be grabbed)
Contact
Add name of and preferred method how to contact the main PI (i.e. you).
Aims
List the aims of your project, or what you expect anyone taking up the project is supposed to hopefully achieve. The more specific, the better.
Estimated level of difficulty
Generating training data for visual object detection should be a pretty straight-forward standard problem, and is a good way to get into the project and data structures in the framework of a Bachelor/Master project.
An elaborate problem is to find a way to integrate the visual detections into the overall tracking pipeline, since this requires to find a suitable new algorithmic framework. It is closely related to this project.
Provided data
Give a specific description of the datasets you provide or can provide which people need to use to solve your problem. If available and/or necessary, also suggest some means for reading the data format. If you can provide links to the data so people can download an take a look, all the better. Also list any known limitations, whether you can easily acquire/record new data, or any other useful information.
Note: Once the CCU server is up and running, datasets should be stored there for easy availability. See the howtos on storage for details.
Suggested/tested approaches
If you have an idea about how to approach the problem, or have tried something already which did not work well, please provide details here. If available, link some papers or code which might provide a possible solution or algorithm.
