Skip to main content

R-CNN for Small Object Detection

Author(s): Chen, Chenyi; Liu, Ming-Yu; Tuzel, Oncel; Xiao, Jianxiong

To refer to this page use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Chenyi-
dc.contributor.authorLiu, Ming-Yu-
dc.contributor.authorTuzel, Oncel-
dc.contributor.authorXiao, Jianxiong-
dc.identifier.citationChen, Chenyi, Ming-Yu Liu, Oncel Tuzel, and Jianxiong Xiao. "R-CNN for Small Object Detection." In Asian Conference on Computer Vision (2016): pp. 214-230. doi:10.1007/978-3-319-54193-8_14en_US
dc.description.abstractExisting object detection literature focuses on detecting a big object covering a large part of an image. The problem of detecting a small object covering a small part of an image is largely ignored. As a result, the state-of-the-art object detection algorithm renders unsatisfactory performance as applied to detect small objects in images. In this paper, we dedicate an effort to bridge the gap. We first compose a benchmark dataset tailored for the small object detection problem to better evaluate the small object detection performance. We then augment the state-of-the-art R-CNN algorithm with a context model and a small region proposal generator to improve the small object detection performance. We conduct extensive experimental validations for studying various design choices. Experiment results show that the augmented R-CNN algorithm improves the mean average precision by 29.8% over the original R-CNN algorithm on detecting small objects.en_US
dc.format.extent214 - 230en_US
dc.relation.ispartofAsian Conference on Computer Visionen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleR-CNN for Small Object Detectionen_US
dc.typeConference Articleen_US

Files in This Item:
File Description SizeFormat 
RCNNSmallObj.pdf3.8 MBAdobe PDFView/Download

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.