PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images

TL;DR

PSGCNet is a novel deep learning framework that effectively addresses scale variation, background interference, and density non-uniformity in remote sensing object counting by integrating pyramidal scale and global context modules.

Contribution

The paper introduces PSGCNet, combining a pyramidal scale module and a global context module, with a Bayesian-based supervision method for improved dense object counting in remote sensing images.

Findings

Outperforms state-of-the-art methods on four remote sensing datasets.

Demonstrates strong generalization on crowd counting datasets.

Effectively handles scale variation and non-uniform density.

Abstract

Object counting, which aims to count the accurate number of object instances in images, has been attracting more and more attention. However, challenges such as large scale variation, complex background interference, and non-uniform density distribution greatly limit the counting accuracy, particularly striking in remote sensing imagery. To mitigate the above issues, this paper proposes a novel framework for dense object counting in remote sensing images, which incorporates a pyramidal scale module (PSM) and a global context module (GCM), dubbed PSGCNet, where PSM is used to adaptively capture multi-scale information and GCM is to guide the model to select suitable scales generated from PSM. Moreover, a reliable supervision manner improved from Bayesian and Counting loss (BCL) is utilized to learn the density probability and then compute the count expectation at each annotation. It can relieve non-uniform density distribution to a certain extent. Extensive experiments on four remote sensing counting datasets demonstrate the effectiveness of the proposed method and the superiority of it compared with state-of-the-arts. Additionally, experiments extended on four commonly used crowd counting datasets further validate the generalization ability of the model. Code is available at https://github.com/gaoguangshuai/PSGCNet.