18029022. METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION simplified abstract (Kia Corporation)
Contents
- 1 METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION
Organization Name
Inventor(s)
Seung Wook Park of Yongin-si (KR)
Wha Pyeong Lim of Hwaseong-si (KR)
METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18029022 titled 'METHOD AND APPARATUS FOR CODING FEATURE MAP BASED ON DEEP LEARNING IN MULTITASKING SYSTEM FOR MACHINE VISION
Simplified Explanation
The VCM coding apparatus and method involve generating and compressing a common feature map for multiple tasks in a machine vision system, with the ability to create task-specific feature maps for improved performance when necessary.
- The VCM coding apparatus is designed for deep learning-based feature map coding in a multitasking system for machine vision.
- It can generate and compress a common feature map related to multiple tasks from an original video.
- The apparatus can also produce task-specific feature maps for enhanced performance beyond what the common feature map can provide.
- The goal is to ensure acceptable performance levels for both machine vision and human vision.
Potential Applications
- Machine vision systems
- Video processing technologies
- Artificial intelligence applications
Problems Solved
- Efficient generation and compression of feature maps for multitasking systems
- Enhanced performance through task-specific feature maps
- Balancing performance for both machine and human vision
Benefits
- Improved performance in machine vision tasks
- Flexibility to adapt to different task requirements
- Efficient use of resources for feature map generation and compression
Original Abstract Submitted
A VCM coding apparatus and a VCM coding method, related to a deep learning-based feature map coding apparatus in a multitasking system for machine vision, are provided for performing default procedures of generating and compressing a common feature map related to multiple tasks implied by an original video. The VCM coding apparatus and the VCM coding method can further generate and compress a task-specific feature map whenever needed for higher performance than obtainable with the common feature map to ensure relatively acceptable performance for both machine vision and human vision.