Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3

TL;DR

This study compares Faster R-CNN and YOLOv3 for car detection in aerial images, revealing that YOLOv3 generally performs better but has limitations with varying object sizes and scales.

Contribution

It provides a comprehensive evaluation of two leading CNN algorithms for aerial car detection across diverse datasets and conditions.

Findings

YOLOv3 outperforms Faster R-CNN in most scenarios.

YOLOv3 has lower recall with large scale variations.

Performance depends on dataset characteristics and hyperparameters.

Abstract

In this paper, we address the problem of car detection from aerial images using Convolutional Neural Networks (CNN). This problem presents additional challenges as compared to car (or any object) detection from ground images because features of vehicles from aerial images are more difficult to discern. To investigate this issue, we assess the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN, which is the most popular region-based algorithm, and YOLOv3, which is known to be the fastest detection algorithm. We analyze two datasets with different characteristics to check the impact of various factors, such as UAV's altitude, camera resolution, and object size. A total of 39 training experiments were conducted to account for the effect of different hyperparameter values. The objective of this work is to conduct the most robust and exhaustive comparison between these two cutting-edge algorithms on the specific domain of aerial images. By using a variety of metrics, we show that YOLOv3 yields better performance in most configurations, except that it exhibits a lower recall and less confident detections when object sizes and scales in the testing dataset differ largely from those in the training dataset.