Method and Apparatus for Coding Feature Map Based on Deep Learning in Multitasking System for Machine Vision
As a disclosure of a device for coding of a deep learning-based feature map in a multiple task system for a machine vision, the present embodiment provides the device and method for coding a VCM that compress by generating a common feature map related to the multiple task implied by an original vide...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Patent |
Sprache: | eng ; kor |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | As a disclosure of a device for coding of a deep learning-based feature map in a multiple task system for a machine vision, the present embodiment provides the device and method for coding a VCM that compress by generating a common feature map related to the multiple task implied by an original video to ensure a relatively acceptable performance for all of a machine vision and a human vision, and additionally generate and compress a task-specific feature map when an improved performance is required compared to a case of using the common feature map. Therefore, the present invention is capable of having an effect of enabling to be transmitted at low costs.
머신 비전을 위한 다중 태스크 시스템에서의 딥러닝 기반 특징맵 코딩 장치에 관한 개시로서, 본 실시예는, 머신 비전 및 인간의 시각 모두에 대해 비교적 용인할 수 있는 성능을 보장하기 위해, 원본 비디오가 함축하는 다중 태스크와 관련된 공통 특징맵을 생성하여 압축하되, 공통 특징맵을 이용하는 경우보다 개선된 성능이 필요 시, 태스크 특화 특징맵을 추가로 생성하여 압축하는 VCM 코딩 장치 및 방법을 제공한다. |
---|