.png){kind=icon}
返回
Balanced Density Regression Network for Remote Sensing Object Counting
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3402271.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Counting objects in remote sensing is crucial for analyzing their distribution in images. Compared to surveillance perspectives, counting dense objects in remote sensing images is more challenging due to the smaller sizes of these targets. Recently, many methods utilize Gaussian convolution regression to estimate the count of dense objects in remote sensing images. However, most methods ignore the issue of regression imbalance inherent in Gaussian distribution, which is caused by the numerical differences in the center and edge regions. To tackle this challenge, we propose a balanced density regression network (BDRNet) to mitigate regression inaccuracies in Gaussian distributions due to numerical variances. Different from other methods, we divide the regression problem into two steps: first focusing on the regions of interest and then achieving precise regression. BDRNet consists of an adaptive kernel weighting attention (AKWA) mechanism and a pixelwise occupancy prediction module. First, AKWA is designed to acquire accurate semantic feature information, which is obtained by learning the weights of dilated convolutions with different sizes of receptive fields. Second, the Pixel-wise Occupancy Estimation (PwOE) module applies Gaussian position embeddings to point labels to constrain the network to focus on the object region without increasing annotation cost. Finally, the integration of pixelwise occupancy prediction features and kernel weighting features forms multilayer cross-attention mechanisms, facilitating channel-level feature interaction and improving density regression predictions. Thus, the center and edge regions of the Gaussian kernel are treated equally, and the regression is balanced. Additionally, extensive experiments on diverse datasets validate the effectiveness of the method, resulting in preferable performance. The code is available at: https://github.com/HotChieh/BDRNet.
Keyword:
Remote sensing
Kernel
Feature extraction
Task analysis
Convolution
Histograms
Gaussian distribution
Attention mechanism
balanced Gaussian regression
pixelwise estimation
remote object counting
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
A Lightweight Multiscale Feature Fusion Network for Remote Sensing Object Counting用于遥感目标计数的轻量级多尺度特征融合网络
PREAI
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregatioon Network.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Measurements of fatty acid synthesis by incorporation of deuterium from deuterated waterBiochemistry
BiochemistryIF0
PREAI
分享收藏
查看更多内容