Multi-scale object detection by bottom-up feature pyramid network

Multi-scale object detection by bottom-up feature pyramid network

The deep neural networks has been developed fast and shown great successes in many significant fields, such as smart surveillance, self-driving and face recognition. The detection of the object with multi-scale and multi-aspect-ratio is still the key problem. In this study, the authors propose a bot...

Full description

Bibliographic Details
Main Authors: Zhao Boya, Zhao Baojun, Tang Linbo, Wu Chen
Format: Article
Language:English
Published: Wiley 2019-10-01
Series:The Journal of Engineering
Subjects:
image representation
object detection
face recognition
neural nets
feature extraction
backbone network
multiaspect-ratio anchor generation
multiscale feature representation
deep neural networks
feature pyramid network
multiscale object detection
pascal visual object detection dataset
multiscale feature map
Online Access:https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0314

Internet

https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0314

Similar Items