18380055. ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM simplified abstract (NEC Corporation)
Contents
- 1 ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM - 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 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM
Organization Name
Inventor(s)
Yasunori Babazaki of Tokyo (JP)
ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18380055 titled 'ACTION RECOGNITION APPARATUS, TRAINING APPARATUS, ACTION RECOGNITION METHOD, TRAINING METHOD, AND STORAGE MEDIUM
Simplified Explanation
The patent application describes a technique for accurately recognizing an action of a person in an image sequence, even when the region related to the action is not fully shown.
- First calculation section calculates action feature information from a partial sequence.
- Second calculation section corrects the action feature information using past feature information.
- Action recognition section recognizes the action based on the corrected information.
Potential Applications
This technology could be applied in surveillance systems, sports analytics, and human-computer interaction.
Problems Solved
This technology solves the problem of accurately recognizing actions in image sequences where the relevant region may not be fully visible.
Benefits
The benefits of this technology include improved accuracy in action recognition, even in challenging visual conditions.
Potential Commercial Applications
Potential commercial applications include security systems, video analysis software, and virtual reality systems.
Possible Prior Art
One possible prior art could be existing action recognition algorithms that do not take into account past feature information for correcting action feature information.
Unanswered Questions
How does this technique perform in low-light conditions?
The patent application does not mention the performance of the technique in low-light conditions.
What is the computational complexity of this technique?
The patent application does not provide information on the computational complexity of the technique.
Original Abstract Submitted
A provided technique accurately recognizes an action of a person even in a time zone in which a region related to an action of the person is not sufficiently shown in an image sequence. An action recognition apparatus includes: a first calculation section for calculating, based on a first partial sequence in an image sequence constituting a time series, first action feature information indicating an action feature of a person included as a subject in an image in the first partial sequence; a second calculation section for calculating, based on past feature information calculated based on a second partial sequence including at least one past image prior to the first partial sequence in the image sequence, second action feature information obtained by correcting the first action feature information; and an action recognition section for recognizing an action of the person based on the second action feature information.
