Welcome to the InfoSci Platform
Reference Hub6
A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection

A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection

Gang Liu, Chuyi Wang
Copyright: © 2020 |Volume: 16 |Issue: 3 |Pages: 14
ISSN: 1548-3924|EISSN: 1548-3932|EISBN13: 9781799804994|DOI: 10.4018/IJDWM.2020070107
Cite Article Cite Article

MLA

Liu, Gang, and Chuyi Wang. "A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection." IJDWM vol.16, no.3 2020: pp.132-145. http://doi.org/10.4018/IJDWM.2020070107

APA

Liu, G. & Wang, C. (2020). A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection. International Journal of Data Warehousing and Mining (IJDWM), 16(3), 132-145. http://doi.org/10.4018/IJDWM.2020070107

Chicago

Liu, Gang, and Chuyi Wang. "A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection," International Journal of Data Warehousing and Mining (IJDWM) 16, no.3: 132-145. http://doi.org/10.4018/IJDWM.2020070107

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Neural network models have been widely used in the field of object detecting. The region proposal methods are widely used in the current object detection networks and have achieved well performance. The common region proposal methods hunt the objects by generating thousands of the candidate boxes. Compared to other region proposal methods, the region proposal network (RPN) method improves the accuracy and detection speed with several hundred candidate boxes. However, since the feature maps contains insufficient information, the ability of RPN to detect and locate small-sized objects is poor. A novel multi-scale feature fusion method for region proposal network to solve the above problems is proposed in this article. The proposed method is called multi-scale region proposal network (MS-RPN) which can generate suitable feature maps for the region proposal network. In MS-RPN, the selected feature maps at multiple scales are fine turned respectively and compressed into a uniform space. The generated fusion feature maps are called refined fusion features (RFFs). RFFs incorporate abundant detail information and context information. And RFFs are sent to RPN to generate better region proposals. The proposed approach is evaluated on PASCAL VOC 2007 and MS COCO benchmark tasks. MS-RPN obtains significant improvements over the comparable state-of-the-art detection models.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.