An Improved FBPN-Based Detection Network for Vehicles in Aerial Images.

Bin Wang,Yinjuan Gu

doi:10.3390/s20174709

Abstract

With the development of artificial intelligence and big data analytics, an increasing number of researchers have tried to use deep-learning technology to train neural networks and achieved great success in the field of vehicle detection. However, as a special domain of object detection, vehicle detection in aerial images still has made limited progress because of low resolution, complex backgrounds and rotating objects. In this paper, an improved feature-balanced pyramid network (FBPN) has been proposed to enhance the network’s ability to detect small objects. By combining FBPN with modified faster region convolutional neural network (faster-RCNN), a vehicle detection framework for aerial images is proposed. The focal loss function is adopted in the proposed framework to reduce the imbalance between easy and hard samples. The experimental results based on the VEDIA, USCAS-AOD, and DOTA datasets show that the proposed framework outperforms other state-of-the-art vehicle detection algorithms for aerial images.

Highlights

Object detection has been a fundamental problem in computer vision
We focus on vehicle detection in aerial images and propose a feature-balanced pyramid network (FBPN) for better feature extraction
The series of methods based on region convolutional neural network (RCNN) uses region proposal for object detection and the results prove that they perform well when dealing with object detection tasks

Summary

Introduction

Object detection has been a fundamental problem in computer vision. It plays an important role in various fields such as civil and security [1]. Instead of selective search used in [8], faster RCNN utilizes a RPN for generating high-quality region proposals. FBPN is adopted to faster RCNN because it can combine features from shallow layers and deep layers which are suitable for vehicle detection in as the 2020, backbone. Recognizing of different sizes is a fundamental challenge computer shallow layers andobjects deep layers which are suitable for vehicle detection in in aerial images.vision. It can be traditional algorithm like “Pyramid methods in image processing” [17]. RPNfeatures is designed to generate region proposals features based on this method are computed on each of the image scales independently, which is pooling is used to extract features. Resnet-101 model [3] is selected as the backbone network instead of computation intensive.

Methods

Results

Conclusion