Detection of small objects based on feature fusion

被引：0

作者：

Zhang, Pan ^{[1
]}

机构：

[1] Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou, Peoples R China

来源：

2022 PROGNOSTICS AND HEALTH MANAGEMENT CONFERENCE, PHM-LONDON 2022 | 2022年

关键词：

object detection; feature fusion; small objects;

D O I：

10.1109/PHM2022-London52454.2022.00073

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

In order to solve the problem of poor detect effectiveness of small target objects in the process of algorithm, a feature fusion method for Faster R-CNN has been proposed. This method fully fuses the deep and shallow feature information, which well improves the detection model for small objects. Meanwhile, in order to better detect small objects, oversampling is used to preprocess the data, and the corresponding hyperparameter values of the Faster R-CNN model are adjusted. From the experimental results, it is easy to see that the detection accuracy is improved by 7.6%, and for small target objects Bottle, Plant, Cow and Boat is improved by 13.9%, 11.2%, 6.7% and 9.5%, respectively. The detection effect of this model has been substantially improved.

引用

页码：384 / 388

页数：5

共 19 条

[11] Perceptual Generative Adversarial Networks for Small Object Detection [J].

Li, Jianan ;

Liang, Xiaodan ;

Wei, Yunchao ;

Xu, Tingfa ;

Feng, Jiashi ;

Yan, Shuicheng .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1951-1959

[12] SSD: Single Shot MultiBox Detector [J].

Liu, Wei ;

Anguelov, Dragomir ;

Erhan, Dumitru ;

Szegedy, Christian ;

Reed, Scott ;

Fu, Cheng-Yang ;

Berg, Alexander C. .

COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 :21-37

[13] A survey and performance evaluation of deep learning methods for small object detection [J].

Liu, Yang ;

Sun, Peng ;

Wergeles, Nickolas ;

Shang, Yi .

EXPERT SYSTEMS WITH APPLICATIONS, 2021, 172

[14]

Qinmin Fan, 2018, SSD OBJECT DETECTION

[15] You Only Look Once: Unified, Real-Time Object Detection [J].

Redmon, Joseph ;

Divvala, Santosh ;

Girshick, Ross ;

Farhadi, Ali .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :779-788

[16] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].

Ren, Shaoqing ;

He, Kaiming ;

Girshick, Ross ;

Sun, Jian .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149

[17]

Simonyan K, 2015, Arxiv, DOI [arXiv:1409.1556, DOI 10.48550/ARXIV.1409.1556]

[18] A new method of feature fusion and its application in image recognition [J].

Sun, QS ;

Zeng, SG ;

Liu, Y ;

Heng, PA ;

Xia, DS .

PATTERN RECOGNITION, 2005, 38 (12) :2437-2448

[19]

Wang Dongli, 2020, Computer Engineering and Applications, V56, P31, DOI 10.3778/j.issn.1002-8331.1911-0340

← 1 2 →