Object Detection Based on Multiple Information Fusion Net
Object detection has been playing a significant role in computer vision for a long time, but it is still full of challenges. In this paper, we propose a novel object detection framework based on relationship among different objects and the scene-level information of the whole image to cope with the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/1/418 |
id |
doaj-80f1c8d459b146708062177e282e08be |
---|---|
record_format |
Article |
spelling |
doaj-80f1c8d459b146708062177e282e08be2020-11-25T01:46:20ZengMDPI AGApplied Sciences2076-34172020-01-0110141810.3390/app10010418app10010418Object Detection Based on Multiple Information Fusion NetYanni Zhang0Jun Kong1Miao Qi2Yunpeng Liu3Jianzhong Wang4Yinghua Lu5College of Information Science and Technology, Northeast Normal University, Changchun 130000, ChinaCollege of Information Science and Technology, Northeast Normal University, Changchun 130000, ChinaCollege of Information Science and Technology, Northeast Normal University, Changchun 130000, ChinaCollege of Information Science and Technology, Northeast Normal University, Changchun 130000, ChinaCollege of Information Science and Technology, Northeast Normal University, Changchun 130000, ChinaInstitute for Intelligent Elderlycare, College of Humanities and Sciences, Northeast Normal University, Changchun 130000, ChinaObject detection has been playing a significant role in computer vision for a long time, but it is still full of challenges. In this paper, we propose a novel object detection framework based on relationship among different objects and the scene-level information of the whole image to cope with the problem that some strongly correlated objects are difficult to be recognized. Our motivation is to enrich the semantics of object detection feature by a scene-level information branch and a relationship branch. There are three important changes of our framework over traditional detection methods: representation of relationship, scene-level information as the prior knowledge and the fusion of the above two information. Extensive experiments are carried out on PASCAL VOC and MS COCO databases. The experimental results show that the detection performance can be improved by introducing relationship and scene-level information, and our proposed model achieve better performance than several classical and state-of-the-art methods.https://www.mdpi.com/2076-3417/10/1/418object relationshipscene-level informationinformation fusionobject detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yanni Zhang Jun Kong Miao Qi Yunpeng Liu Jianzhong Wang Yinghua Lu |
spellingShingle |
Yanni Zhang Jun Kong Miao Qi Yunpeng Liu Jianzhong Wang Yinghua Lu Object Detection Based on Multiple Information Fusion Net Applied Sciences object relationship scene-level information information fusion object detection |
author_facet |
Yanni Zhang Jun Kong Miao Qi Yunpeng Liu Jianzhong Wang Yinghua Lu |
author_sort |
Yanni Zhang |
title |
Object Detection Based on Multiple Information Fusion Net |
title_short |
Object Detection Based on Multiple Information Fusion Net |
title_full |
Object Detection Based on Multiple Information Fusion Net |
title_fullStr |
Object Detection Based on Multiple Information Fusion Net |
title_full_unstemmed |
Object Detection Based on Multiple Information Fusion Net |
title_sort |
object detection based on multiple information fusion net |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-01-01 |
description |
Object detection has been playing a significant role in computer vision for a long time, but it is still full of challenges. In this paper, we propose a novel object detection framework based on relationship among different objects and the scene-level information of the whole image to cope with the problem that some strongly correlated objects are difficult to be recognized. Our motivation is to enrich the semantics of object detection feature by a scene-level information branch and a relationship branch. There are three important changes of our framework over traditional detection methods: representation of relationship, scene-level information as the prior knowledge and the fusion of the above two information. Extensive experiments are carried out on PASCAL VOC and MS COCO databases. The experimental results show that the detection performance can be improved by introducing relationship and scene-level information, and our proposed model achieve better performance than several classical and state-of-the-art methods. |
topic |
object relationship scene-level information information fusion object detection |
url |
https://www.mdpi.com/2076-3417/10/1/418 |
work_keys_str_mv |
AT yannizhang objectdetectionbasedonmultipleinformationfusionnet AT junkong objectdetectionbasedonmultipleinformationfusionnet AT miaoqi objectdetectionbasedonmultipleinformationfusionnet AT yunpengliu objectdetectionbasedonmultipleinformationfusionnet AT jianzhongwang objectdetectionbasedonmultipleinformationfusionnet AT yinghualu objectdetectionbasedonmultipleinformationfusionnet |
_version_ |
1725020198228983808 |