Multi-Scale Feature Fusion Convolutional Neural Network for Indoor Small Target Detection.

Multi-Scale Feature Fusion Convolutional Neural Network for Indoor Small Target Detection.
复制标题

用于室内小目标检测的多尺度特征融合卷积神经网络。

DOI:
10.3389/fnbot.2022.881021
复制
发表时间:
2022
影响因子:
3.1
通讯作者:
Ma, Hongjie
Ma, Hongjie
中科院分区:
计算机科学3区
文献类型:
--
作者:
Huang, Li;Chen, Cheng;Yun, Juntong;Sun, Ying;Tian, Jinrong;Hao, Zhiqiang;Yu, Hui;Ma, Hongjie

文献摘要

参考文献

被引文献

相似文献

物体检测技术的发展使机器人与人、环境的交互成为可能,但多变的应用场景使得物体检测技术在实际应用中对中小型物体的检测精度较低。本文基于多尺度特征融合的室内小目标检测方法,利用该设备采集不同角度、光照、阴影条件下的室内图像,并利用图像增强技术建立和放大一个数据集,将室内场景与目标检测层中的SSD算法及其相邻特征融合。在基于迁移学习的室内场景数据集上训练基于多尺度特征融合的Faster R-CNN、YOLOv5、SSD和SSD目标检测模型。实验结果表明,多尺度特征融合可以提高各类目标的检测精度,特别是对于相对小尺度的目标。此外,改进的SSD算法虽然检测速度有所下降,但比faster R-CNN更快,更好地实现了目标检测精度和速度之间的平衡。
The development of object detection technology makes it possible for robots to interact with people and the environment, but the changeable application scenarios make the detection accuracy of small and medium objects in the practical application of object detection technology low. In this paper, based on multi-scale feature fusion of indoor small target detection method, using the device to collect different indoor images with angle, light, and shade conditions, and use the image enhancement technology to set up and amplify a date set, with indoor scenarios and the SSD algorithm in target detection layer and its adjacent features fusion. The Faster R-CNN, YOLOv5, SSD, and SSD target detection models based on multi-scale feature fusion were trained on an indoor scene data set based on transfer learning. The experimental results show that multi-scale feature fusion can improve the detection accuracy of all kinds of objects, especially for objects with a relatively small scale. In addition, although the detection speed of the improved SSD algorithm decreases, it is faster than the Faster R-CNN, which better achieves the balance between target detection accuracy and speed.
DOI: 10.3390/axioms10020106
发表时间: 2021-06-01
期刊: AXIOMS
影响因子: 2
作者:
Chen, Tinggui;Yin, Xiaohua;Cong, Guodong
通讯作者: Cong, Guodong
基于图像信息和脑信号的人体病变检测方法
DOI: 10.1109/access.2019.2891749
发表时间: 2019-01-01
期刊: IEEE ACCESS
影响因子: 3.9
作者:
Li, Gongfa;Jiang, Du;Manogaran, Gunasekaran
通讯作者: Manogaran, Gunasekaran
一种基于健康大脑表面肌电图的机器学习特征提取方法
DOI: 10.1007/s00521-019-04147-3
发表时间: 2019-12-01
影响因子: 6
作者:
Li, Gongfa;Li, Jiahan;Kong, Jianyi
通讯作者: Kong, Jianyi
DOI: 10.1007/s10586-017-1237-1
发表时间: 2019-09-01
影响因子: 4.4
作者:
He, Yang;Li, Gongfa;Liu, Honghai
通讯作者: Liu, Honghai
DOI: 10.1109/tpami.2009.167
发表时间: 2010-09-01
影响因子: 23.6
作者:
Felzenszwalb, Pedro F.;Girshick, Ross B.;Ramanan, Deva
通讯作者: Ramanan, Deva