International Journal of Computational Intelligence Systems

<Previous Article In Issue
Next Article In Issue>
Volume 11, Issue 1, 2018, Pages 951 - 961

SCAN: Semantic Context Aware Network for Accurate Small Object Detection

Authors
Linting Guan1, 2, glinting@tongji.edu.cn, Yan Wu1, *, yanwu@tongji.edu.cn, Junqiao Zhao1, zhaojunqiao@tongji.edu.cn
1College of Electronics & Information Engineering, Tongji University, Telecom Building, 4800 Cao’an Road, Jiading, Shanghai, 201804, China
2College of Mathematics, Physics and Information Science, Zhejiang Ocean University, 1 South Haida Road, Lincheng, Zhoushan, Zhejiang 316004, China
*Correspond Author.
Corresponding Author
Received 15 July 2017, Accepted 28 March 2018, Available Online 12 April 2018.
DOI
10.2991/ijcis.11.1.72How to use a DOI?
Keywords
Deep learning; object detection; semantic features
Abstract

Recent deep convolutional neural network-based object detectors have shown promising performance when detecting large objects, but they are still limited in detecting small or partially occluded ones—in part because such objects convey limited information due to the small areas they occupy in images. Consequently, it is difficult for deep neural networks to extract sufficient distinguishing fine-grained features for high-level feature maps, which are crucial for the network to precisely locate small or partially occluded objects. There are two ways to alleviate this problem: the first is to use lower-level but larger feature maps to improve location accuracy and the second is to use context information to increase classification accuracy. In this paper, we combine both methods by first constructing larger and more meaningful feature maps in top-down order and concatenating them and subsequently fusing multilevel contextual information through pyramid pooling to construct context aware features. We propose a unified framework called the Semantic Context Aware Network (SCAN) to enhance object detection accuracy. SCAN is simple to implement and can be trained from end to end. We evaluate the proposed network on the KITTI challenge benchmark and present an improvement of the precision.

Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

<Previous Article In Issue
Next Article In Issue>
Journal
International Journal of Computational Intelligence Systems
Volume-Issue
11 - 1
Pages
951 - 961
Publication Date
2018/04/12
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
10.2991/ijcis.11.1.72How to use a DOI?
Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Cite this article

risenwbib
TY  - JOUR
AU  - Linting Guan
AU  - Yan Wu
AU  - Junqiao Zhao
PY  - 2018
DA  - 2018/04/12
TI  - SCAN: Semantic Context Aware Network for Accurate Small Object Detection
JO  - International Journal of Computational Intelligence Systems
SP  - 951
EP  - 961
VL  - 11
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.11.1.72
DO  - 10.2991/ijcis.11.1.72
ID  - Guan2018
ER  -