Efficient Small Object Detection with an Improved Region Proposal Networks

Author:

Ma Dong Wen,Wu Xiao Jun,Yang Honghong

Abstract

Abstract Although the state-of-the-art object detection methods, which depend on region proposal algorithms to hypothesize object locations, have achieved high detection accuracy, it still struggles in small-size object detection. In this paper, we present a novel method with a multi-scale and multi-tasking region proposal method to effectively detect small object. In the proposed method, multi-scale features and high-level features are employed to locate object position and identify object category, respectively. The main contributions of the proposed approach are two-fold: (1) A simpler way is used to improve the accuracy performance of small object detection, instead of the complex image pyramids and the complex combination framework, and make the object detection task more flexible. (2) Based on multi-scale and multi-tasking approaches, object location information in low layers and object semantic information in deep layers are made fully advantage respectively. The experimental results on the PASCAL VOC dataset show that the proposed method achieves the state-of-the art object detection accuracy.

Publisher

IOP Publishing

Subject

General Medicine

Reference24 articles.

1. Learning to Combine Mid-Level Cues for Object Proposal Generation;Lee,2016

2. Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction;Zhang,2015

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3