Apparatus and Method for Person Re-Identification based on Heterogeneous Sensor Camera
The present invention may provide an apparatus and method for person re-identification based on a heterogeneous sensor camera. The apparatus can perform learning based on a feature map extracted from images acquired from the heterogeneous sensor camera and a warping feature map that warps pixels cor...
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: | The present invention may provide an apparatus and method for person re-identification based on a heterogeneous sensor camera. The apparatus can perform learning based on a feature map extracted from images acquired from the heterogeneous sensor camera and a warping feature map that warps pixels corresponding to each other in the feature map and, especially, calculate dense triple loss for the feature map and the warping feature map to be reflected on learning, so it is possible to extract subdivided local information even from non-sorted images and re-identify a person even in images acquired in very different conditions in various cameras.
본 발명은 이종 센서 카메라에서 획득된 이미지들에서 추출된 특징맵과 함께 특징맵에서 서로 대응하는 픽셀을 와핑한 와핑 특징맵을 기반으로 학습을 수행하며, 특히 특징맵과 와핑 특징맵에 대한 밀집 삼중 손실을 계산하여 학습에 반영함으로써, 정렬되지 않은 이미지들에서도 세분화된 로컬 정보를 추출할 수 있어 다양한 카메라에서 매우 상이한 조건에서 획득된 이미지로부터도 사람을 정확하게 재식별할 수 있는 사람 재식별 장치 및 방법을 제공할 수 있다. |
---|