A Survey of Computer Vision Methods for 2D Object Detection from Unmanned Aerial Vehicles

Abstract

The spread of Unmanned Aerial Vehicles (UAVs) in the last decade revolutionized many applications fields. Most investigated research topics focus on increasing autonomy during operational campaigns, environmental monitoring, surveillance, maps, and labeling. To achieve such complex goals, a high-level module is exploited to build semantic knowledge leveraging the outputs of the low-level module that takes data acquired from multiple sensors and extracts information concerning what is sensed. All in all, the detection of the objects is undoubtedly the most important low-level task, and the most employed sensors to accomplish it are by far RGB cameras due to costs, dimensions, and the wide literature on RGB-based object detection. This survey presents recent advancements in 2D object detection for the case of UAVs, focusing on the differences, strategies, and trade-offs between the generic problem of object detection, and the adaptation of such solutions for operations of the UAV. Moreover, a new taxonomy that considers different heights intervals and driven by the methodological approaches introduced by the works in the state of the art instead of hardware, physical and/or technological constraints is proposed.

Artificial and beneficial – Exploiting artificial images for aerial vehicle detection

“…In our framework, we aim for an object detector designed to perform well on aerial images. Although many object detectors specialized for aerial images have been proposed in the past (see, e.g., [4], [50]), we observe that standard object detectors with small modifications are suitable for our data. We decide to use the RetinaNet [7] for this work and modify it accordingly.…”

“…The vanilla RetinaNet is designed for common datasets like MS COCO [11], which typically contain earthbound imagery. In contrast, our aerial images, for example, have a different perspective and scale [4], which we take into account with the following modifications.…”

“…This removes the burden of creating a suitable dataset and allows us to determine baseline performance measurements. Multiple datasets contain imagery and annotations suitable for object and especially vehicle detection in top-down aerial images, which have been reviewed by Azimi et al [57] and Cazzato et al [4]. Datasets like DOTA [13], COWC [58], VEDAI [59], DLR-MVDA [60], DLR-Skyscapes [61] and recently EAGLE [57], vary in resolution, type and quality of annotation, numbers of objects, classes and images.…”

Object Detection Combining CNN and Adaptive Color Prior Features

“…In 2012, the AlexNet network [ 27 ] proposed by Alex Krizhevsky et al achieved results far surpassing traditional object detection algorithms in the large-scale visual recognition challenge, which made deep neural network technology attract people’s attention in the field of image recognition and object detection. After several years of development, deep neural networks have been widely used in object detection tasks [ 28 , 29 , 30 , 31 , 32 , 33 ]. These algorithms are mainly divided into object detection algorithms that are based on candidate boxes and object detection algorithms based on regression.…”

Pavement Crack Detection from Hyperspectral Images Using a Novel Asphalt Crack Index

“…There is currently an increasing interest in the application of HSI with UAV to monitor the conditions of city roads, see [19,44] for a review of UAV based sensors. However, the use of HSI for road condition monitoring had been reported in a few studies using several spectral descriptors.…”