IEEE Geoscience and Remote Sensing Magazine - September 2019 - 47

coordinates on checkpoints and evaluate cross sections
and residuals on generated point cloud surfaces.
◗ Urban Drone Data Set [101]: This is a collection of UAV
images extracted from 10 video sequences used for SfM.
About 1 to 2% of the data (about 205 frames) is annotated by three semantic classes (vegetation, buildings,
and free space) for semantic constraints in 3D reconstruction. The data were acquired by the DJI-Phantom 4
at altitudes between 60 and 100 m over the four Chinese
cities of Beijing, Huludao, Zhengzhou, and Cangzhouo.
◗ UAV image mosaicking data set [138]: This data set consists of hundreds of images captured by UAVs. The corresponding DOMs are generated by a digital photogrammetry grid, which can be used as the gold standard for
evaluating mosaicking algorithms.

3D CITY MODELING
The camera-based UAV system provides a powerful tool to
obtain 3D models of urban scenarios in a noninvasive and
low-cost manner. The city components are reconstructed
for urban planning, including visualization, measurement,
inspection, and illegal building monitoring [169].
In [94], a pilot project was conducted using UAV-RS to
build high-resolution, large-scale models in complex urban
areas. Specifically, a Falcon octocopter UAV equipped with
a Sony camera was employed to acquire images from lower
than 150 m and generate 3D models of a campus with an
approximately 6- to 8-cm accuracy. Geographic information system layers and near-infrared channels were also
combined to help in the reconstruction of urban terrain
and the extraction of streets, buildings, and vegetation.

APPLICATIONS
UAV-RS has drawn increasing attention in recent years. It
is widely used to quickly acquire high-resolution data in
small areas or fly in high-risk or difficult regions to carry
out remote sensing tasks. Based on remote sensing products, e.g., DOMs, DEMs, and 3D models, UAV-RS is applied
for urban planning, engineering monitoring, ecological research, and so on. The applications of UAV-RS seem to be
unlimited and are continually growing.
Recognizing space limitations, we focus in this section on
some potential and novel applications. Some other mature
or long-standing use areas, such as precision agriculture [2],
coastal and polar monitoring [17], [25], [164], disaster and
emergency monitoring [6], and atmospheric monitoring
[165], could not be considered here but can be explored in
[20], [22], [166], and [167]. In fact, other applications not
examined here are still booming and deserve attention.

BUILT ENVIRONMENT MONITORING AND ASSESSMENT
UAV-RS provides benefits in the monitoring and assessing
of the built environment to maintain and improve living
conditions. Regular inspection is necessary to assess infrastructure health and identify any faults at an early stage to
ensure that the required maintenance is performed. For
instance, one study assessed building damage based on
gaps in UAV image-derived 3D point clouds, which were
identified by support vector machines (SVMs) and random
forests based on the surrounding damage patterns [171].
Another work acquired UAV visible and infrared images to
monitor the condition and structural health of bridges, including bridge deterioration, deck delamination, road surface aging, and crack and deformation detection [172]. The
inspection helped engineers prioritize critical repair and
maintenance needs.
UAV-based infrared remote sensing presents an opportunity to inspect and analyze the urban thermal environment,
building performance, and heat transfer at a micro scale so
as to maintain the energy efficiency of such infrastructure
and building stock [170]. An example of scrutinizing the
thermal environment in buildings using UAVs is shown in
Figure 14. A 3D thermal model of a building is generated for
the monitoring and analysis of an edifice's heat distribution

URBAN PLANNING AND MANAGEMENT
In recent years, UAV-RS applications in urban planning
and management have experienced exponential growth,
including inspection of infrastructure conditions, monitoring of urban environments and transportation, 3D landscape mapping, and urban planning [3], [168].

16 °C

(a)

(b)

(c)

0 °C

FIGURE 14. A depiction of UAV monitoring of the thermal information of buildings [171]: (a) data acquisition for building inspection by
UAVs; (b) an infrared image of a building, which reflects thermal information; and (c) a 3D thermal model of a building (taken from Rakha
and Gorodetsky [170]).
SEPTEMBER 2019

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE

IEEE Geoscience and Remote Sensing Magazine - September 2019

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - September 2019