| 自适应融合特征的人群计数网络 |
| |
| 引用本文： | 左健豪,姜文刚.自适应融合特征的人群计数网络[J].计算机工程与应用,2021,57(21):203-208. |
| |
| 作者姓名： | 左健豪 姜文刚 |
| |
| 作者单位： | 江苏科技大学 电子信息学院，江苏 镇江 212003 |
| |
| 摘 要： | 针对人群计数方法中存在的尺度变化和多层级特征融合不佳的问题，基于U-Net的编码器-解码器网络结构，提出一种自适应特征融合网络，来进行精准的人群计数。提出自适应特征融合模块，根据解码器分支的需要，高效地聚合编码器分支提取的高层语义信息和底层的边缘信息；提出自适应上下文信息提取器，从不同感受野下提取多尺度的上下文信息并自适应加权融合，提高网络对于人头尺度变化的鲁棒性。在ShanghaiTech、UCF-CC-50和UCG-QNRF上的实验表明，与目前主流的人群计数算法相比，该算法具有更强的准确性和鲁棒性。
|
| 关 键 词： | 人群计数 卷积神经网络 密度估计 多层级特征 尺度变化 特征融合 |
Adaptive Feature Fusion Network for Crowd Counting |
| |
| ZUO Jianhao,JIANG Wengang.Adaptive Feature Fusion Network for Crowd Counting[J].Computer Engineering and Applications,2021,57(21):203-208. |
| |
| Authors: | ZUO Jianhao JIANG Wengang |
| |
| Affiliation: | School of Electronic Information, Jiangsu University of Science and Technology, Zhenjiang, Jiangsu 212003, China |
| |
| Abstract: | In an attempt to solve the problems of scale change and multi-level feature fusion in population counting method, inspired by U-Net encoder decoder structure network, an adaptive feature fusion network is proposed to carry out accurate population counting. The Adaptive Feature Fusion Module（AFFM） is proposed to efficiently aggregate the high-level semantic information and low-level spatial detail extracted by the encoder branch according to the needs of decoder branch. The Adaptive Context Extractor（ACE） is proposed to extract multi-scale context information on multiple effective field-of-views, then these features are adaptively fused to improve the robustness of the network to scale changes. By conducting exhaustive experiments on Shanghai Tech, UCF-CC-50 and UCF-QNRF, the results show that the network has high accuracy and robustness. |
| |
| Keywords: | crowd counting Convolutional Neural Network（CNN） density estimation multi?level features scale variation feature fusion |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
