See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/224190295

Advances in vegetation management for power line corridor monitoring using

aerial remote sensing techniques

Conference Paper · November 2010

DOI: 10.1109/CARPI.2010.5624431 · Source: IEEE Xplore

CITATIONS READS

33 1,930

4 authors, including:

Ross F. Hayward Luis Mejias

Queensland University of Technology Queensland University of Technology
23 PUBLICATIONS 966 CITATIONS 111 PUBLICATIONS 2,514 CITATIONS

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Automated Flooded area detection using remotely sensed images View project

Vision based aircraft detection for UAS detect and avoid View project

All content following this page was uploaded by Luis Mejias on 30 May 2014.

The user has requested enhancement of the downloaded file.

2010 1st International Conference on Applied Robotics for the Power Industry
Delta Centre-Ville
Montréal, Canada, October 5-7, 2010
Advances in Vegetation Management for Power
Line Corridor Monitoring Using Aerial Remote
Sensing Techniques
Zhengrong Li, Rodney Walker, Ross Hayward, Luis Mejias
Abstract—This paper presents a comprehensive discussion of
vegetation management approaches in power line corridors
based on aerial remote sensing techniques. We address three
issues 1) strategies for risk management in power line corridors,
2) selection of suitable platforms and sensor suite for data
collection and 3) the progress in automated data processing
techniques for vegetation management. We present initial results
from a series of experiments and, challenges and lessons learnt
from our project.
Index Terms—Power Line Corridor Monitoring, Vegetation
Management, Unmanned Aerial System (UAS), Remote Sensing,
LiDAR, Multi-spectral Imagery, Power Line Detection, Tree
Crown Segmentation, Tree Species Classification
I. INTRODUCTION
T REES, shrubs and other vegetation are of continued
importance to the environment and our daily life. They
provide shade around our roads and houses, offer a habitat
for birds and wildlife, and absorb air pollutants. However,
vegetation around power lines can represent a significant risk
to public safety, the environment and, is one of the main
causes of power outages. It is common knowledge that trees
falling across power lines are the largest cause of power
failures, causing widespread power outages and bushfires [1].
It is not surprising that vegetation management procedures in
power line corridors become a significant maintenance cost
for electrical companies. Currently, activities such as tree
trimming and vegetation control are costly. For example,
Ergon Energy, one of the Australia’s largest electricity
companies, currently spends $80 million a year inspecting and
managing vegetation encroachments on power lines. Correct
and efficient vegetation management not only reduces the
overall cost but also aids in continuous electricity supply by
preventing damage to power lines through removal of tall-
growing species. Ineffective procedures can result in the loss
of reliability in electricity transmission, produce serious
This work was conducted within the CRC for Spatial Information,
established and supported under the Australian Government’s Cooperative
Research Centres Programme, and sees collaboration between the Queensland
University of Technology (QUT), the Australian Research Centre for
Aerospace Automation (ARCAA) and Ergon Energy Australia.
Zhengrong Li and Ross Hayward are with the Faculty of Science and
Technology, Queensland University of Technology (QUT), Brisbane, QLD,
4001, Australia (e-mail: zhengrong.li@qut.edu.au; r.hayward@qut.edu.au).
Rodney Walker and Luis Mejias are with the Australian Research Centre
for Aerospace Automation (ARCAA, QUT), Brisbane, QLD, 4009, Australia
(ra.walker@qut.edu.au; luis.mejias@qut.edu.au).
978-1-4244-6635-1/10/$26.00 ©2010 IEEE
1
hazards and expose electrical companies to significant
financial penalties.
In urban areas, vegetation encroachment is less serious than
in rural areas as access is much easier and prompt
maintenance can be achieved. Moreover, local councils and
private land owners regularly maintain their trees facilitating
the overall maintenance process. However, in rural areas,
inspection and maintenance becomes difficult due to limited
access and large distances to cover. In these areas, traditional
calendar-based tree trimming is performed by operator. This
process is time consuming, labor-intensive and expensive. It
also results in zones being trimmed more frequently than
others, or not cut often enough. In recent years, remote sensing
approaches have proven to be an alternative to traditional
methods. These include improved data collection using
satellite sensors [2, 10], airborne laser scanning system [3, 11],
a stereo vision system [4], and unmanned aerial systems
(UASs) [5, 12]. Therefore, remotely sensed data have great
potential in assisting vegetation management in power line
corridors.
This work is closely aligned with industry, with strong
support and collaboration from Ergon Energy. In this paper,
we present a comprehensive discussion of vegetation
management in power line corridor monitoring based on aerial
remote sensing techniques. We focus on discussing the risk
management strategy, selection of platform and sensor,
advancement in automated data processing, and the challenges
learnt from our project.
II. BACKGROUND
This section provides a summary of our research covering
the risk management strategy using aerial remote sensing
techniques, selection of platform and sensor, and automated
feature extraction from remotely sensed data.
A. Risk Management Strategy
The reliability of electricity supply and distribution is of the
highest priority in power line corridor monitoring. A short-
term strategy is to identify and remove nearby objects (i.e.
buildings and vegetation) around power lines. Generally, the
risk of manmade structures can be controlled through building
regulations. However, vegetation is naturally growing and
particularly in rural areas the growth is unmanaged. Strong
winds and storms can bring branches or even entire trees into
contact with power lines. Unmanaged vegetation can also

grow up into power lines and cause bushfires. These problems
motivate the use of aerial remote sensing techniques for power
line corridor monitoring. Specifically, detecting all vegetation
from remote sensed data that have the potential to pose risks to
power lines and use this to guide the field workers for
vegetation clearance in the corridors.
Ergon Energy has a long-time strategy of managing
vegetation according to different species. The species they are
interested in can be generally categorized as undesirable
species and undesirable species. Species with fast growth rates
and that also have the potential to reach a mature height of
more than four meters are defined as undesirable species.
These undesirable species often pose high risks to electrical
infrastructure and therefore should be identified and removed.
It is also worth mentioning that in the long-term maintenance
strategy low-growing trees or shrubs are encouraged because
they are expected to compete with tall growing species and
deprive the taller trees of light and nutrients. These low
growing species, along with the rare and endangered species,
are defined as desirable species that should be managed
differently.
B. Selection of Platform and Sensor
Satellites and aircrafts are the most widely used platforms
for remote sensing in earth observing data collection. Current
satellite sensors are not the best choice for monitoring power
line corridors due to two critical limitations: the unfavorable
revisit time and lack of choices in optimum spatial and
spectral resolutions. At the most practical level, most
collections of data gathered from satellites are available only
on predetermined schedules, and even those with an “on-
demand” capability are also limited by their orbits and the
demands of other users. In contrast, airborne data collection
offers a much greater level of flexibility. An airborne system
can capture data at any time of the day whereas satellites
generally pass over one site at the same time of a day. Another
advantage of airborne platform is that different sensor
payloads can be easily fitted, while the sensors launched on a
satellite are often not changeable. As a consequence, airborne
systems can be regularly upgraded as sensor technology
advances. Improvements to sensors include systems with
higher spectral and spatial resolution, and advanced
microwave or LiDAR sensors. In addition, higher spatial
resolutions are easier to obtain from airborne platforms, due to
their low altitude. A limitation which impedes large-scale
airborne remote sensing applications is that the traditional
piloted airborne platforms involve high operational costs.
Moreover, using piloted aircraft for power line inspection will
place the operators at a greater level of risk.
Remote sensors mounted on unmanned aerial systems
(UASs) could fill this gap, providing a cheap and flexible way
to gather spatial data from power line corridors which can also
meet the requirements of spatial, spectral, and temporal
resolutions. Recent development in the aerial vehicles
themselves and associated sensing system make UAS
platforms increasingly attractive for both research and
operational mapping [6, 7]. One of the main limitations of
using UASs is their ability to carry power-demanding and
2
heavy payloads. LiDAR systems are too heavy for
small/medium sized UAS platforms. This limitation may be
overcome in the near future as there are already small LiDAR
systems in the market suitable for UASs. However, the
performance of these units in terms of the quality of data
collected is currently well away from their full-sized
counterparts. When combined with LiDAR type systems
UASs would represent the technology of choice for future uses.
C. Automated Data Processing
As may already be evident from previous section, aerial
remote sensing is a fast and cost-effective technique for power
line corridor mapping. There are some commercial data
providers available in the market that can collect high quality
LiDAR data and georeferenced imagery for general mapping
purposes. Compared to corridor mapping, automated and
intelligent information extraction from remotely sense data is
more challenging. One special need for power line corridor
monitoring is to detect the objects of interest for further
interpretation and decision making. The major objects of
interest include power line assets and vegetation. Automated
data processing aims to automatically detect these objects
from aerial imagery, and try to extract more specific
information such as vegetation species and height information.
In this section, we briefly discuss the general methods in
automated data processing.
• Power Line Detection
Risk assessment of power lines and adjacent trees is
meaningful only when power lines can be detected. A straight
line can approximate a power line segment in aerial images.
Therefore, classic line detection algorithms like the Hough
transform may be used to detect power lines in images.
However, while the Hough transform is an effective tool to
detect straight lines, it does not intelligently identify power
lines. Any linear objects will be detected, such as fences,
edges of roads and buildings. Therefore, some prior
knowledge should be used to improve power line detection [5].
For 3D LiDAR point cloud data, line detection can be
conducted either by clustering similar features in a voxel [13]
or mapping 3D data to two 2D planes (horizontal and vertical)
and then roughly detecting the power line points in horizontal
plane and reconstructing the catenary curve in the vertical
plane [14]. No matter which method is used, prior removal of
non-powerline points (e.g. terrain, tree and building) will
always be helpful to reduce the error in power line detection.
• Tree Detection and Classification
Detection of trees has been intensively studied particularly
in the remote sensing of forest environment. Whilst similar in
concept, the environment in power line corridor is more
complex because the background is cluttered with shadows,
bare soil, shrubs and grass; all presenting irregularities that
need to be handled by the detection algorithm. Vegetation has
a distinctive spectral signature, characterized by a low
reflectance in the visible part of the solar spectrum, and a high
reflectance in the near-infrared (NIR) region. Therefore,
incorporating NIR information is widely used in the remote
sensing community for the detection and classification of

vegetation. Combining LiDAR elevation data can further
improve tree detection by removing low-growing grass and
shrubs. For classification of tree species, object-based methods
are preferred as they are straightforward and have been shown
to obtain higher classification accuracy in high resolution
image classification [8]. To conduct an object-based
classification, accurate individual tree segmentation is
required. Subsequent to this, a range of classification
algorithms can be used in the object-feature space.
III. DATA COLLECTION
Data collection in this study included gathering aerial data
as well as ground survey data. The first series of flights were
conducted by a local company. The image data were collected
by a high resolution digital 4-band multi-spectral camera
(DuncanTech MS-4100) with a DGPS/INS mounted in the
cargo area of a Piper Cub. The spatial resolution of the
collected imagery is around 15 cm. The second series of
flights were conducted by another local company using an
airborne LiDAR scanner mounted in a Cessna aircraft. The
LiDAR data was collected with a scan angle of ±30°with an
average sample rate of 9 points per square meter. A separate
data collection has been conducted using two UAS platforms:
the V-TOL Aerospace BAT-3, and the ARCAA UAS platform
Eleanor. The sensors onboard two UAS platforms are natural
color digital cameras (Canon IXUS 960IS and Canon 350D
DSLR).
(a) Multi-spectral imagery collection system
(b) Lidar data collection system
(c) UAS platforms: V-TOL BAT-3 (left) & ARCAA Eleanor (right)
Figure 1 Data Collection Systems
The ground survey was conducted in a 1.5 kilometres corridor
in the towns of Murgon and Wondai in Central East Australia
where the multi-spectral image and LiDAR data were
collected. The ground truth data of vegetation species were
obtained with domain experts’ participation. Figure 2 shows a
mosaic of the test area generated from aerial images acquired
from the trial. It should be noted that classifying all types of
3
species in power line corridors requires significantly more
resources than are currently available, however, classifying
species in a given test area as a proof of concept is possible. In
this research, we focus on three dominant species in our test
field: Eucalyptus tereticornis, Eucalyptus melanophloia, and
Corymbia tesselaris. We abbreviate the species names to
Euc_Ter, Euc_Mel and Cor_Tes. For each species 65 samples
were used with 25 for training and 40 for testing.
Figure 2 Experiment test site
IV. DATA ANALYSIS
In this section, we briefly introduce the developed
algorithms and initial data analysis results from a series of
experiments.
A. Power Line Detection
We developed an algorithm to detect power lines in aerial
imagery [5]. A filter is designed to remove the background
noise and generate an edge map prior to the Hough transform
being employed to detect straight lines. After that, a
knowledge-based line clustering is performed in Hough space
to refine the detection results. The algorithm has been tested
on high resolution color images collected by the UAS
platforms. Figure 3 (a) shows an example of the detection
results. In general, the performance of the algorithm depends
on the quality of the image. Low spatial resolution and motion
blur are the two major problems for the failure of the power
line detection algorithm.
Compared to image based approaches, LiDAR is more
popular for power line survey since it can provide high density
point cloud data and does not reply on illumination conditions.
Moreover, LiDAR can more effectively generate accurate
elevation and terrain models, which can also help to remove
terrain points and other similar linear features (e.g. fences).
There are already some commercial products for detecting and
modeling power lines from LiDAR point cloud data (e.g. PLS-
CADD and TLiD). We have developed an algorithm to
classify terrain and object points by performing statistical
analysis on LiDAR intensity data [14]. After this classification,
the object points were mapped to a horizontal plane to create a
2D grey-level image and the Hough transform is employed to
detect lines. By mapping the rough position of the detected
lines in 2D image back to point cloud data, the power line
points are obtained, but we have not reconstructed the
catenary curve from 3D point clouds. Figure 3 (b) shows an
example of the detection results from point cloud data.
 4

(a) power line detection from aerial imagery (a) original image

(b) power line detection from LiDAR point cloud

Figure 3 Examples of Power Line Detection
B. Tree Detection and Classification
We developed an algorithm to detect and delineate tree
crowns from multi-spectral imagery by using spectral band
ratio as input to a pulse coupled neural network, followed by
morphological reconstruction [15]. The algorithm achieved a
detection rate of 96% and a segmentation accuracy of 75.2%.
The failure cases are mainly due to the under-segmentation of
tree clusters. Some tree crowns are very sparse and present
low contrast to the background which makes it difficult to
detect them. Combining LiDAR data can help to improve tree
segmentation provided the density of points is sufficiently
large. Figure 4 (a) and (b) shows an example of multi-spectral
imagery and tree crown segmentation.
In the tree species classification experiments, texture
features were extracted from each manually segmented tree
crowns and a supervised machine learning technique is used to
identify tree species based on empirical data. A support vector
machine (SVM) is used in this study, which is very popular
and considered as the best performing inductive machine
learning technique. The classification model is built by
training a SVM using a RBF kernel. Table 1 shows the
confusion matrix and classification accuracies when Local
Binary Patterns (LBP) [9] are used to characterize textures.
Figure 4(c) shows an example of a classification map. It
should be noted that selection of appropriate feature
descriptors (e.g. textures) is critical for all image classification
problems [16]. To further improve the results of tree species
classification, feature descriptors with highly discriminative
power should be developed to model tree species. Moreover,
trees can often appear differently in different seasons and even
the same tree species may vary due to their health status. The
data that was available did not provide the opportunity to
classify the same vegetation under different conditions.
Therefore, more variables may need to be considered to model
a specific tree species accurately.
(b) tree crown detection and segmentation
(c) classification map (species are represented using different colors)
Figure 4 Example of Individual Tree Segmentation and Species Classification
Table 1 Confusion Matrix and Classification Accuracy
Actual Predicted Category Classification
Category Euc-Ter Euc-Mel Cor-Tes Accuracy
Euc-Ter 15 12 13 0.375
Euc-Mel 10 26 4 0.65
Cor-Tes 8 2 30 0.75
V. TECHNOLOGICAL ADVANCEMENT AND CHALLENGES
The major technological contributions of this project are: 1)
Evaluation of small fixed-wing UASs and commercial
available multi-spectral and LiDAR sensors for data
collection; 2) algorithm developed for automatic power line
detection from aerial imagery and LiDAR point clouds; 3)
algorithms developed for individual tree crown detection and
delineation; 4) evaluation of machine learning techniques for
object-based tree species classification. Our field trial and
experimental results have demonstrated considerable potential
and merit of applying aerial remote sensing and computer
vision techniques to assist vegetation management in power
line corridors. However, there are still some challenging
problems and gaps between research and real application.
These challenges include:
• Reliable Data Collection Using Small UASs
The environment around power line corridors is very
complex, making it difficult to navigate an UAS over large
and discontinuous networks. The stability and control issues
associated with small UAS's flying at low altitudes are still

challenging. It is worth noting that new approaches should be
developed to ensure a full-sized aerial platform follows the
optimal path when performing an inspection. In addition,
taking into account the sensor field of view (FOV) in the flight
control will be helpful ensure the FOV remains within optimal
boundaries and sensors always collect data from regions of
interest (i.e. power line corridors) [17]. Another area of
attention is the safety procedures associated with the operation
of UAS near infrastructures. One of the most important safety
concerns is how to ensure autonomous flying robots (and
manned aircraft) to safely localize autonomously the most
suitable landing area in case of emergency landing. Safety
system onboard UASs is critical for future civilian UAS
operations (e.g. power line inspection).
• Multi-source Data Fusion
Due to the rapid development of sensor technologies, such
as multispectral/hyperspectral sensor, SAR and LiDAR
sensors onboard airborne platforms, effective fusion of multi-
sensor, multi-resolution, multi-temporal and multi-platform
image data, together with geospatial data and GIS becomes an
emerging challenge for the remote sensing community.
However, it also provides the opportunity to increase the
reliability of the information extraction for robust operational
performance and decision making in corridor monitoring (e.g.
improved classification, increased confidence and reduced
ambiguity). Although the motivation of using LiDAR data and
imagery to improve power line detection and vegetation
classification is clear, how best to combine data of different
spatial resolutions and is still an open issue. Moreover, fusing
multi-temporal data for dynamic corridor monitoring is also
very important in the future work.
• Real-time Data Processing
Currently, processing for object recognition has been
designed for off-line use. Data is collected, stored in a
repository and analyzed at some later time. However, some
real-time processing would be beneficial as there is
information available to assist in the decisions made by the
navigation and data storage systems. For example, if areas can
be identified where the collection of additional data might be
advantageous, then the flight plan of the UAS can be modified.
Alternatively, the real-time identification of regions outside
the immediate vicinity of the power-line where vegetation is
sparse could be used to reduce the resolution of data stored.
Questions concerning the algorithms and computing
architectures that are best suited to increase the autonomy of a
UAS capturing significant amounts of data need to be
addressed.
VI. ACKNOWLEDGMENT
The authors gratefully acknowledge the contributions of
Bred Jeffers from Greening Australia and David Wood from
Ergon Energy for their assistance in the field survey. The
contributions of Steven Mills, Troy Bruggemann, Jinhai Cai,
Marcos Gerardo, Yuee Liu, Jinglan Zhang and Jason Ford
from their original work are also acknowledged.
5
VII. REFERENCES
Periodicals:
[1] S. J. Mills, M. P. Gerardo, Z. Li, J. Cai, R. Hayward, L. Mejias, and R.
Walker, "Evaluation of aerial remote sensing techniques for vegetation
management in power line corridors," IEEE Transactions on Geoscience
and Remote Sensing, 2010 (in press).
[2] Y. Kobayashi, G. G. Karady, G. T. Heydt, and R. G. Olsen, "The
utilization of satellite images to identify trees endangering transimission
lines," IEEE Transactions on Power Delivery, vol. 24, pp. 1703-1709,
2009.
[3] M. L. Lu and Z. Kieloch, "Accuracy of transmission line modeling
based on aerial LiDAR survey " IEEE Transactions on Power Delivery,
vol. 23, pp. 1655-1663, 2008.
[4] C. Sun, R. Jones, H. T. X. Wu, K. Cheong, R. Beare, M. Buckley, and
M. Berman, "Measuring the distance of vegetation from powerlines
using stereo vision " ISPRS Journal of Photogrammetry & Remote
Sensing, vol. 60, pp. 269-283, 2006.
[5] Z. Li, Y. Liu, R. Walker, R. Hayward, and J. Zhang, "Towards
automatic power line detection for a UAV surveillance system using
pulse coupled neural filter and an improved Hough transform," Machine
Vision and Applications, 2009 (in press).
[6] J. A. J. Berni, P. J. Zarco-Tejada, L. Suárez, and E. Fereres, "Thermal
and narrowband multispectral remote sensing for vegetation monitoring
from an unmanned aerial vehicle," IEEE Transactions on Geoscience
and Remote Sensing, vol. 47, pp. 722-738, 2009.
[7] A. Gurtner, D. G. Greer, R. R. Glassock, L. Mejias, R. Walker, and W.
W. Boles, "Investigation of fish-eye lenses for small-UAV aerial
photography," IEEE Transactions on Geoscience and Remote Sensing,
vol. 47, pp. 709-721, 2009.
[8] T. Blaschke, "Object-based image analysis for remote sensing," ISPRS
Journal of Photogrammetry & Remote Sensing, vol. 65, pp. 2-16, 2010.
[9] T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution grey-scale
and rotation invariant texture classification with local binary patterns,"
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
24, pp. 971-987, 2002.
Papers from Conference Proceedings (Published):
[10] A. M. K. Beltrame, M. G. M. Jardini, R. M. acbsen, and J. A. uintanilha,
"Vegetation identification and classification in the domain limits of
powerlines in Brazilian Amazon forest," in IEEE International
Geoscience and Remote Sensing Symposium, 2007, pp. 2314-2317.
[11] S. Clode and F. Rottensteiner, "Classification of trees and powerlines
from medium resolution airborne laserscanner data in urban
environments," in APRS Workshop on Digital Image Computing
Brisbane, Australia, 2005.
[12] D. Jones, I. Golightly, J. Roverts, K. Usher, and G. Earp, "power line
inspection - a uav concept," in The IEE Forum on Autonomous Systems
London, United Kingdom, 2005
[13] Y. Jwa, G. Sohn, and H. B. Kim, "Automatic 3D power line
reconstruction using airborne lidar data," in ISPRS Laserscanning 2009
Paris, France, 2009.
[14] Y. Liu, Z. Li, R. Hayward, R. Walker, and H. Jin, "Classification of
airborne lidar intensity data using statistical analysis and Hough
transform with application to power line corridors," in International
Conference on Digital Image Computing: Techniques and Applications
Melbourne, Australia, 2009.
[15] Z. Li, R. Hayward, J. Zhang, Y. Liu, and R. Walker, "Towards
automatic tree crown detection and delineation in spectral feature space
using PCNN and morphological reconstruction," in IEEE International
Conference on Image Processing, Cairo, Egypt, 2009.
[16] Z. Li, R. Hayward, J. Zhang, H. Jin, and R. Walker, "Evaluation of
spectral and texture features for object-based vegetation species
classification using support vector machines," in ISPRS TC VII
Symposium Vienna, Austria (IAPRS vol. 38 part 7A), 2010.
[17] S. Mills, J. Ford, and L. Mejias, "Vision based control for fixed wing
UAVs inspecting locally linear infrastructure with skid-to-turn
maneuvers" in The International Conference on Unmanned Aerial
Vehicles, Dubai, UAE, 2010.
 6

VIII. BIOGRAPHIES
Zhengrong Li received the B. Eng. and M. Eng.
degree in 2003 and 2006 respectively from
Northwest A&F University, China. He was
appointed an assistant lecturer at the College of
Information Engineering, Northwest A&F University
since 2006. He is currently working toward the Ph.D.
degree at the Queensland University of Technology
with the support of Cooperative Research Centre for
Spatial Information (CRCSI). His research interests
include remote sensing image processing,
computational intelligence, and pattern recognition.

Rodney A. Walker (M’01) was born in Cairns,

Australia, in 1969. He received the B. Eng. degree in
electronic systems and the B.App.Sc in computing
from Queensland University of Technology in 1992.
He completed his PhD in satellite navigation from
the same institution in 1999 after spending a year
studying at the Rutherford Appleton Laboratory in
the UK. From 1998 to 2005 he was responsible for
the GPS payload on Australia’s Federation Satellite
working closely with NASA JPL during this time.
Since 2000 he has directed his interests to ICT in aviation and created the
Australian Research Centre for Aerospace Automation which now has over 30
full-time staff. He is also a private pilot with NVFR and Aerobatics
endorsements.

Ross Hayward (M'00) received the B.Sc. degree

from the Australian National University (ANU) in
Canberra, Australia in 1983, a Graduate Diploma in
Computer Science and a Phd. in connectionist
systems from the Queensland University of
Technology Brisbane, Australia in 1993 and 2001
respectively. He has been a lecturer at QUT since
2002 teaching in the areas of artificial Intelligence,
programming languages and computer architecture.
He is also a member of the IEEE Computational
Intelligence and Computer Societies and regularly organizes QUT's
participation in the southeast Queensland computational intelligence chapter.
His areas of interest include computer vision and machine learning for robotic
platforms.

Luis Mejias (M’07) received the B.E. degree in

electronics from the Universidad Nacional
Experimental Politécnica, Barquisimeto, Venezuela,
and the M.Sc. and Ph.D. degrees in
telecommunication systems, and robotics and
automation, respectively, from the Universidad
Politécnica de Madrid, Madrid, Spain.
While completing the Ph.D. degree, he was
leading the team in vision-guided unmanned aerial
vehicle (UAV) for surveillance and visual
inspection. He gained extensive experience in
unmanned aerial vehicles and, in particular, autonomous helicopter platforms,
investigating computer vision techniques for control and navigation. Dr.
Mejias is currently a Lecturer in Aerospace Avionics at Queensland
University of Technology (QUT), Brisbane, Australia, and Research Scientist
in Unmanned Aerial Technologies at the Australian Research Center for
Aerospace Automation at QUT.

View publication stats