Tasks #1395
Implement ROIExtractor
Status: | Closed | Start date: | 02/04/2013 | |
---|---|---|---|---|
Priority: | Normal | Due date: | ||
Assignee: | S. Wrede | % Done: | 0% | |
Category: | - | Estimated time: | 4.00 hours | |
Target version: | - |
Description
Implement a component which extract regions-of-interest patches (based on bounding boxes) out of a video stream, e.g., to generate training data for face or object recognizers. Initial implementation should at least work with rst.vision.Faces.
Implementation
- should utilize the timesync library to fuse bounding box detections with the closest video image based on create timestamps (or using cause vector information)?
- should write the patches to files.
Related issues
History
#1 Updated by S. Wrede over 11 years ago
- Description updated (diff)
- Estimated time set to 4.00
#2 Updated by S. Wrede over 11 years ago
Later on, think about integration with a tracking algorithm to ease labeling.
#3 Updated by J. Moringen almost 11 years ago
- Target version changed from rsb-0.9 to rsb-0.10
#4 Updated by J. Moringen over 10 years ago
- Target version changed from rsb-0.10 to rsb-0.11
#5 Updated by J. Moringen over 10 years ago
- Target version changed from rsb-0.11 to rsb-0.12
#6 Updated by J. Moringen about 8 years ago
- Target version changed from rsb-0.12 to rsb-0.14
#7 Updated by J. Moringen almost 8 years ago
- Target version changed from rsb-0.14 to rsb-0.15
#8 Updated by J. Moringen almost 8 years ago
- Target version deleted (
rsb-0.15)
#9 Updated by J. Moringen over 7 years ago
- Copied to Tasks #2697: Implement ROIExtractor added
#10 Updated by J. Moringen over 7 years ago
- Status changed from New to Closed