Vehicle Detection in Very-High-Resolution Remote Sensing Images Based on an Anchor-Free Detection Model with a More Precise Foveal Area

Xungen Li,Xiao Jiang,Shuaishuai Lv,Qi Ma,Mian Pan,Haibin Yu,Feifei Men

doi:10.3390/ijgi10080549

Xungen Li, Xiao Jiang + Show 5 more

Open Access

https://doi.org/10.3390/ijgi10080549

Copy DOI

Abstract

Vehicle detection in aerial images is a challenging task. The complexity of the background information and the redundancy of the detection area are the main obstacles that limit the successful operation of vehicle detection based on anchors in very-high-resolution (VHR) remote sensing images. In this paper, an anchor-free target detection method is proposed to solve the problems above. First, a multi-attention feature pyramid network (MA-FPN) was designed to address the influence of noise and background information on vehicle target detection by fusing attention information in the feature pyramid network (FPN) structure. Second, a more precise foveal area (MPFA) is proposed to provide better ground truth for the anchor-free method by determining a more accurate positive sample selection area. The proposed anchor-free model with MA-FPN and MPFA can predict vehicles accurately and quickly in VHR remote sensing images through direct regression and predict the pixels in the feature map. A detailed evaluation based on remote sensing image (RSI) and vehicle detection in aerial imagery (VEDAI) data sets for vehicle detection shows that our detection method performs well, the network is simple, and the detection is fast.

Highlights

Using computer technology to complete tasks such as the classification [1], detection [2], and segmentation of remote sensing images has always been a hot topic in the field of image research [3,4]
We propose a VHR remote sensing image detection method based on the anchor-free detection model
The results show that the feature pyramid network (FPN) can improve the detection performance in vehicle target detection in VHR remote sensing images

Summary

Introduction

Using computer technology to complete tasks such as the classification [1], detection [2], and segmentation of remote sensing images has always been a hot topic in the field of image research [3,4]. Among these tasks, vehicle detection in remote sensing images plays an important role in urban vehicle supervision [5,6,7], defense, traffic planning, safety-assisted driving, etc. Vehicle detection in remote sensing images plays an important role in urban vehicle supervision [5,6,7], defense, traffic planning, safety-assisted driving, etc. Researchers usually directly designed and extracted vehicle features manually and classified them to achieve vehicle detection

Methods

Results

Conclusion