18273612. TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM simplified abstract (NEC Corporation)
Contents
- 1 TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Original Abstract Submitted
TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM
Organization Name
Inventor(s)
Royston Rodrigues of Tokyo (JP)
TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18273612 titled 'TRAINING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGEMEDIUM
Simplified Explanation
The training apparatus described in the patent application acquires ground-view and aerial-view images, along with alignment information, to train a discriminator that extracts partial aerial regions from the aerial-view image and determines if the ground-view image matches the aerial-view image based on these regions.
- The training apparatus extracts correctly-aligned and mis-aligned partial aerial regions from the aerial-view image.
- The discriminator is trained using both the correctly-aligned and mis-aligned partial aerial regions as positive examples.
Potential Applications
This technology could be applied in various fields such as:
- Augmented reality
- Urban planning
- Environmental monitoring
Problems Solved
This technology helps in:
- Aligning ground-view and aerial-view images accurately
- Enhancing image recognition capabilities
Benefits
The benefits of this technology include:
- Improved accuracy in image matching
- Enhanced training of discriminators
- Increased efficiency in image processing tasks
Potential Commercial Applications
Optimizing this technology for commercial use could lead to applications in:
- Drone navigation systems
- Surveillance systems
- Agricultural monitoring
Unanswered Questions
How does this technology handle variations in lighting conditions between ground-view and aerial-view images?
What are the limitations of using partial aerial regions for image matching compared to other methods?
Original Abstract Submitted
A training apparatus () acquires a ground-view image (), an aerial-view image (), and alignment information (), and trains a discriminator () that extracts a plurality of partial aerial regions () from the aerial-view image () and determines that the ground-view image () matches the aerial-view image () when there is the partial aerial region () that matches the ground-view image (). The training apparatus () extracts a correctly-aligned partial aerial region () and a mis-aligned partial aerial region () from the aerial-view image (). The correctly-aligned partial aerial region () is indicated by the alignment information () and corresponds to the ground-view image (). The mis-aligned partial aerial region () partially overlaps the correctly-aligned partial aerial region (). The training apparatus () trains the discriminator () using both the correctly-aligned partial aerial region () and the mis-aligned partial aerial region () as positive examples.