Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
リアルタイムオブジェクト検出及び語意分割の同時行いシステム及び方法及び非一時的なコンピュータ可読媒体
Document Type and Number:
Japanese Patent JP7284352
Kind Code:
B2
Abstract:
System and method for simultaneous object detection and semantic segmentation. The system includes a computing device. The computing device has a processor and a non-volatile memory storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive an image of a scene; process the image using a neural network backbone to obtain a feature map; process the feature map using an object detection module to obtain object detection result of the image; and process the feature map using a semantic segmentation module to obtain semantic segmentation result of the image. The object detection module and the semantic segmentation module are trained using a same loss function comprising an object detection component and a semantic segmentation component.

Inventors:
Mao Fonda
cyan way
Lou Chumong
Chan Waydon
Application Number:
JP2022547758A
Publication Date:
May 30, 2023
Filing Date:
February 19, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
Beijing Jingdong Shangke Information Technology Co., Ltd.
JD.com American Technologies Corporation
International Classes:
G06T7/00; G06N3/0464; G06N3/08; G06T7/11; G06V10/764; G06V10/82; G06V20/00
Foreign References:
US20190057507
US20190050667
Other References:
Wei XIANG et al.,ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation,2019 IEEE Winter Conference on Applications of Computer Vision (WACV),IEEE,2019年01月,pp.1789-1796
Hengshuang ZHAO et al.,Pyramid Scene Parsing Network,Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),IEEE,2017年,pp. 2881-2890
Attorney, Agent or Firm:
Toranomon Intellectual Property Office