- Tài khoản và mật khẩu chỉ cung cấp cho sinh viên, giảng viên, cán bộ của TRƯỜNG ĐẠI HỌC FPT
- Hướng dẫn sử dụng: Xem Video .
- Danh mục tài liệu mới: Tại đây .
- Đăng nhập : Tại đây .

accurate visitors web counter
Visits Counter
FPT University|e-Resources > Đồ án tốt nghiệp (Dissertations) > Khoa học máy tính >
Please use this identifier to cite or link to this item: /handle/123456789/3323

Authors: Phan, Duy Hung
Vu, Thanh Dat
Ngo, Viet Hoai Bao
Keywords: Computer Science
Issue Date: 2022
Publisher: FPTU Ha Noi
Abstract: End-to-end Network has become increasingly important in multi-tasking. One prominent example of this is the growing significance of a driving perception system in autonomous driving. This thesis systematically studies an end-to-end perception network for multi-tasking and proposes several key optimizations to improve accuracy. First, the study proposes efficient segmentation head and box/class prediction networks based on weighted bidirectional feature network. Second, the study proposes automatically customized anchor for each level in the weighted bidirectional feature network. Third, the study proposes an efficient training loss function and training strategy to balance and optimize network. Based on these optimizations, we have developed an end-to-end perception network to perform multi-tasking, including traffic object detection, drivable area segmentation and lane detection simultaneously, called HybridNets, which achieves better accuracy than prior art. In particular, HybridNets achieves 77.3 mean Average Precision on Berkeley DeepDrive Dataset, outperforms lane detection with 31.6 mean Intersection Over Union with 12.83 million parameters and 15.6 billion floating-point operations. In addition, it can perform visual perception tasks in real-time and thus is a practical and accurate solution to the multitasking problem. Code is available at https://github.com/datvuthanh/HybridNets
URI: /handle/123456789/3323
Appears in Collections:Khoa học máy tính

Files in This Item:

File Description SizeFormat
Thesis-HybridNets End-to-End.pdfFree1.65 MBAdobe PDF book.png
Slide-HybridNets End-to-End.pdfFree34.27 MBAdobe PDF book.png

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


  Collections Copyright © FPT University

FSE Hoa Lac Library

Add : Room 107, 1st floor, Hoa Lac campus, Km28 Thang Long Avenue, Hoa Lac Hi-Tech Park

Office tel: + 844.66805912  / Email :  thuvien_fu_hoalac@fpt.edu.vn

 - Feedback