Apparatus for detecting object based on fusion learning model and method thereof

Provided are an object detection device based on learning model convergence and a method thereof. According to an embodiment of the present invention, the object detection device based on learning model convergence comprises: a camera which acquires images around a vehicle; and a control unit which...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: JITESH KUMAR SINGH, ARPIT AWASTHI, S.VINUCHACKRAVARTHY
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Provided are an object detection device based on learning model convergence and a method thereof. According to an embodiment of the present invention, the object detection device based on learning model convergence comprises: a camera which acquires images around a vehicle; and a control unit which is communicatively connected to the camera. Here, the control unit is configured to extract features from an acquired image, detect objects based on the extracted features, perform semantic segmentation based on the extracted features, and combine loss functions for object detection and semantic segmentation by differential weighting to fuse a plurality of models into a single model. 학습모델 융합 기반 객체검출 장치 및 그 방법이 제공된다. 본 발명의 실시예에 따른 학습모델 융합 기반 객체검출 장치는 차량 주변의 이미지를 획득하는 카메라, 및 카메라에 통신적으로 연결되는 제어부를 포함한다. 여기서, 제어부는 획득된 이미지에서 특징을 추출하고, 추출된 특징을 기반으로 객체를 감지하며, 추출된 특징을 기반으로 시멘틱 분할을 수행하고, 단일 모델로 융합하기 위해 객체 감지 및 시멘틱 분할에 대한 손실 함수를 차등 가중치에 의해 조합하도록 구성된다.