Content uploaded by Tariq Rahim
Author content
All content in this area was uploaded by Tariq Rahim on Nov 12, 2021
Content may be subject to copyright.
Improved CNN-based Path Planning So an Autonomous UAV Can Climb Stairs By using a
LiDAR Sensor
저자
(Authors)
Yeon Ji Choi, Tariq Rahim, Soo Young Shin
출처
(Source)
IEIE Transactions on Smart Processing & Computing 10(5), 2021.10, 390-397 (8 pages)
발행처
(Publisher)
대한전자공학회
The Institute of Electronics and Information Engineers
URL http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE10620516
APA Style Yeon Ji Choi, Tariq Rahim, Soo Young Shin (2021). Improved CNN-based Path Planning So
an Autonomous UAV Can Climb Stairs By using a LiDAR Sensor. IEIE Transactions on Smart
Processing & Computing, 10(5), 390-397.
이용정보
(Accessed)
저작권 안내
DBpia에서 제공되는 모든 저작물의 저작권은 원저작자에게 있으며, 누리미디어는 각 저작물의 내용을 보증하거나 책임을 지지
않습니다. 그리고 DBpia에서 제공되는 저작물은 DBpia와 구독계약을 체결한 기관소속 이용자 혹은 해당 저작물의 개별 구매자
가 비영리적으로만 이용할 수 있습니다. 그러므로 이에 위반하여 DBpia에서 제공되는 저작물을 복제, 전송 등의 방법으로 무단
이용하는 경우 관련 법령에 따라 민, 형사상의 책임을 질 수 있습니다.
Copyright Information
Copyright of all literary works provided by DBpia belongs to the copyright holder(s)and Nurimedia does not guarantee
contents of the literary work or assume responsibility for the same. In addition, the literary works provided by DBpia may
only be used by the users affiliated to the institutions which executed a subscription agreement with DBpia or the
individual purchasers of the literary work(s)for non-commercial purposes. Therefore, any person who illegally uses the
literary works provided by DBpia by means of reproduction or transmission shall assume civil and criminal responsibility
according to applicable laws and regulations.
금오공과대학교
202.31.134.***
2021/11/12 09:19 (KST)
IEIE Transactions on Smart Processing and Computing, vol. 10, no. 5, October 2021
https://doi.org/10.5573/IEIESPC.2021.10.5.390 390
IEIE Transactions on Smart Processing and Computing
Improved CNN-based Path Planning So an Autonomous
UAV Can Climb Stairs By using a LiDAR Sensor
Yeon Ji Choi1, Tariq Rahim2, and Soo Young Shin3*
Department of IT Convergence Engineering, Kumoh National Institute of Technology / Gumi, Korea
yzygzy@kumoh.ac.kr, tariqrahim@ieee.org, wdragon@kumoh.ac.kr
* Corresponding Author: Soo Young Shin
Received April 7, 2021; Revised May 25, 2021; Accepted July 9, 2021; Published October 30, 2021
* Regular Paper
* Extended from a Conference: Preliminary results of this paper were presented at the ICEIC Winter 2021. This paper has
been accepted by the editorial board through the regular reviewing process that confirms the original contribution.
Abstract: Unmanned aerial vehicles (UAVs) have tremendous potential in civil and public areas.
These are especially beneficial in applications where human lives are threatened. Autonomous
navigation in unknown environments is a challenging issue for UAVs where decision-based
navigation is required. In this paper, a deep learning (DL) approach is presented that aids
autonomous navigation for UAVs in completely unknown, GPS-denied indoor environments. The
UAV is equipped with a monocular camera and a light detection and ranging (LiDAR) sensor to
determine each next maneuver and distance calculation, respectively. For deeper feature extraction,
a version of You Only Look Once (YOLOv3-tiny) is improved by adding a convolution layer with
different filter sizes. The process is observed as an exercise where the DL model classifies the
targeted image as stairs or not stairs. We created our dataset considering the indoor scenario for
specific implementation. Comprehensive experimental results are compared with YOLOv3-tiny,
indicating better performance in terms of accuracy, recall, F1-score, precision, and maneuvering
movements.
Keywords: UAVs, CNN, Path planning, Stair climbing, LiDAR sensor
1. Introduction
UAV use is growing in areas such as scientific research,
rescue missions, commerce, and agriculture. Originally,
UAVs were developed to be managed by an on-the-ground
pilot via remote-control communication [1]. Recently,
UAVs have been moving closer to navigating with unusual
degrees of autonomy. Most UAVs employ global
navigation satellite system technology and inertial sensors
to determine their geospatial positioning. It is necessary to
overcome factors such as GPS signal error, narrow
passageways, and transparent glass for stable-flight UAVs
in indoor environments [2]. Studies in image-based stair-
recognition for robots [3] and of techniques for ground
robots [4] are ongoing; however, there is a lack of such
research with UAVs. An abundance of techniques, varying
from learning-based to non–learning-based, have been
suggested to resolve UAV navigation dilemmas. The most
popular non–learning-based method is sensing and
avoidance, which prevents accidents by steering vehicles
in a reverse orientation and navigating by path planning [5,
6]. Another type of non–learning-based technique takes
advantage of simultaneous localization and mapping
(SLAM). The inspiration is that, after creating a map of the
surroundings by utilizing SLAM, navigation is
accomplished by path planning [7, 8]. The work in [7]
combines GraphSLAM [9] with an online path planning
module in a proposal-approving UAV to determine
obstacle-free trajectories in foliage. A general
characteristic of non–learning-based approaches is that
they demand precise path planning, which may result in
unanticipated failures when environments are extremely
dynamic and complicated. To address this matter, machine
learning (ML) methods such as imitation learning and
reinforcement learning (RL) have been explored [10-12].
For example, a model-based RL approach called
TEXPLORE [12] was presented, which is a high-level
control system for navigation of a UAV within a grid map
having no barriers. And an imitation learning–based
controller utilizing a small set of human displays was
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
IEIE Transactions on Smart Processing and Computing, vol. 10, no. 5, October 2021
391
presented that obtains reliable performance in forested
areas [10].
Therefore, this paper proposes a convolutional neural
network (CNN)-based system based on real-time stair
recognition that can fly a UAV without colliding with
stairs, and that obtains distance information between walls
or stairs through 2D light detection and ranging (LiDAR)
with a camera mounted on the UAV. In addition,
algorithms were designed for systems that recognize stairs,
avoid collisions, and maneuver themselves, which is one
of the obstacles to an autonomous flight process, and flight
experiments were carried out after the actual UAV was
implemented.
Deep learning (DL), which is a subcategory of machine
learning, acts like the human brain, and is therefore known
as artificial intelligence (AI). Many applications of
machine learning have been proposed, with different
signals representing data such as music signals [13], 2D
signals or images [14], and video signals [15]. CNNs are
used for various purposes, such as classification, detection,
and pattern recognition, especially in health [16], drone
applications [17], and autonomous driving systems.
Recently, You Only Look Once (YOLO) was introduced
for real-time detection of objects, with each version
improving the mean average precision (mAP) per frame
per second [18].
In this work, we attempted for the first time to use the
YOLOv3-tiny model, and improved the model further by
adding a convolution layer to extract deep features for the
detection of stairs. This DL detection model was used in a
classification problem to determine each next maneuver.
The rest of this paper is organized as follows. Section 2
details related work, while Section 3 explains the proposed
scheme. Section 4 summarizes the experimental results
and the analysis. Section 5 provides concluding statements
and suggests the scope of future work.
2. Related Work
Previously, a 3D map of the local area was developed
for autonomous UAV navigation. In some cases, these
methods were used to map exact quadcopters [19, 20].
However, these methods are based on a smart control
scheme, thereby restricting their use to laboratory settings
[21-23]. The map is learned through other manual route
methods, and quadcopters travel the same path [24]. For
most outdoor flights (where precision is not as high as
indoors), a GPS-based posing projection is used.
Most applications use scale sensors, such as infrared
sensors, RGB-D (red, green, blue depth) sensors, or laser
range sensors [25]. A single ultrasonic sensor was used in
[26] as an automated navigation device with an infrared
sensor. The condition evaluation method of the LiDAR
and inertial measurement unit (IMU) was advanced to
work independently in uncertain conditions that are denied
by a GPS [27]. Range sensors have limitations, being
heavy and high in power consumption.
The simultaneous localization and mapping (SLAM)
technique uses separate optical sensors to create a 3D
image [21-23] from every UAV position on the map. A 3D
map of an unknown indoor scenario was used for the
SLAM laser range finder [25]. The SLAM technique [29,
31] offers single-camera indoor navigation. SLAM is
highly complicated when it comes to regenerating the 3D
map region, requiring precise measurements and extensive
resources because additional sensors are needed.
SLAM can also set contact delays during real-time
navigation. The studies in [31] and [32] addressed these
issues. SLAM is primarily a practical system, and its
output with indoor materials (such as walls/roofs) is not
considered good, because its differential intensity is very
weak. The entire corridor comprises partitions, roofs, and
floors, and SLAM technologies cannot attain the desired
navigational quality.
3. The Proposed Scheme
This section discusses the system configuration for
UAV recognition of stairs, the deep learning model using
YOLOv3-tiny, and the improved YOLOv3-tiny for
detecting stairs.
3.1 System Configuration
The proposed system was designed based on
recognizing stairs with a camera mounted on the UAV for
indoor environments and on distances measured via the 2D
LiDAR sensor attached to the UAV’s side. Fig. 1 shows
the flowchart for the entire system. The connections and
communications between the parts are both wired and
wireless, as shown in Fig. 2. In particular, communications
among the ground control station, the UAV, and the
onboard PC is via Wi-Fi/LTE. Meanwhile, the wired
connection is only used for the sensor.
The system’s actual implementation uses a Parrot
Bebop 2 drone, which is suitable for narrow passageways
and convenient for load sensors. The UAV is equipped
with an RPLiDAR S1 laser scanner, which rotates 360°
and can measure distances up to 40m with a lightweight,
mainboard Jetson TX2 embedded computing device
(Auvidea J120 carrier board) as shown in Fig. 3(c). The
Fig. 1. Flowchart for the proposed implementation.
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
Choi et al.: Improved CNN-based Path Planning So an Autonomous UAV Can Climb Stairs By using a LiDAR Sensor
392
Lenovo ThinkPad T580 is used as a ground control system
(GCS), and the equipment required for the experiment is
listed in Table 1. All algorithms are implemented in
Python, and the Robot Operating System (ROS) was used
as middleware (software that can run multiple different
programs together) in a kinetic version.
The LiDAR sensor uses distances measured along 360
points, as shown in Fig. 3(b). The distance data obtained
by the LiDAR sensor were 0° to the floor, 90° to the front,
and 180° to the ceiling, based on the direction of progress
for the UAV. In the polar coordination system, each of the
raw laser points is defined as {(di, θi); 0 ≤ i ≤ 359}, where
di is the distance from the UAV center to the object, and θi
is the relative angle of measurement. The information
obtained by the LiDAR is stored as a vector (di, θi), and the
stored data are checked to convert the values of the infinity
scan.
3.2 Stair-climbing System
Algorithm 1 is used by the UAV to climb stairs. When
steps are recognized by the camera, the algorithm starts. If
the distance between the UAV and the stairs is longer than
r meters, a straight start is performed on the x-axis, or a
rising maneuver on the z-axis, to avoid collisions if the
distance is less than r m. At this instant, if a staircase is not
recognized, the stair climb mission is determined as
complete, and recognition for climbing the next step
commences.
3.3 Deep Learning Model for Detection of
Stairs
In this study, a DL approach is implemented for
detecting stairs, which the drone uses to make decisions
intelligently in order to follow the stairs and determine the
next maneuver. In this work, we improved the YOLOv3-
tiny default model. The backbone of YOLO is darknet,
where the YOLOv3-tiny default model uses six max-
pooling and seven convolution layers. We modified it by
adding one more layer. Instead of the softmax function,
and where multi-class classification and detection is an
Fig. 2. Network connections and the architecture of the
proposed system.
Fig. 3. System configuration: (a) UAV movement axes;
(b) illustration of the RPLiDAR S1 scanning process;
(c) the 2D-LiDAR sensor and the Jetson-TX2 onboard
PC attached to the UAV; (d) the test environment.
Table 1. Experiment Parameters.
Device Model name Company
Lidar sensor RPLiDAR S1 Slamtec
UAV Bebop drone 2 Parrot
Onboard PC Jetson TX2 Nvidia
Carrier board Auvidea J120 Auvidea
GCS ThinkPad T580 Lenovo
LTE modem LTE USB Stick Huawei
A
lgorithm 1. Stai
r
-climbing algorithm.
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
IEIE Transactions on Smart Processing and Computing, vol. 10, no. 5, October 2021
393
issue, regression is employed to solve the multi-class
detection and classification problem [33].
The proposed model starts by dividing the stair-image
input into a G × G grid in the training stage. A bounding
box is used as a tool for labeling five features—width w,
height h, vertical height v, horizontal height u—as shown
in Fig. 4, and confidence score C, which represents the
presence of stairs within the bounding box, and hence,
represents the accuracy.
In the proposed YOLOv3-tiny method, we attempt to
make the model computationally inexpensive, along with
implementing it to extract more semantic features. Max-
pooling is used after each convolution layer to reduce the
computational complexity and improve image feature
extraction. Fig. 6 shows the network architecture for both
the default and the improved YOLOv3-tiny models. The
loss function is obtained as an end-to-end network, and can
be expressed as follows [33]:
0
a
S
i
loss iouErr coordErr clsErr
=
=++
∑ (1)
where iouErr, coordErr, and clsErr indicate the IOU error,
coordinates error, and classification error, respectively. We
used a rectified linear unit (ReLU) as an activation
function to achieve sparsity and reduce vanishing gradient
issues [25]. Table 2 details the training configuration
employed for both YOLOv3-tiny and the proposed
improved YOLOv3-tiny model.
3.4 ROS
The nodes that are separated and managed by the
master are shown in Fig. 5. In addition, the topic node
continuously communicates the results processed by the
publisher node, and makes them available to other nodes
by subscription. The system proposed in this paper is
largely a UAV status message, a scan value obtained from
the LiDAR, and a visual message obtained from the UAV
camera. When running darknet on the ROS, the messages
required from the published messages are subscripted.
Among them, a message containing information on the
bounding box is received through the darknet_ros node.
When the proposed DL model detects a staircase, a
Fig. 5. ROS node graph.
Fig. 4. Definition of the bounding box.
Fig. 6. YOLO models: the default YOLOv3-tiny and the
improved YOLOv3-tiny.
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
Choi et al.: Improved CNN-based Path Planning So an Autonomous UAV Can Climb Stairs By using a LiDAR Sensor
394
message from the LiDAR is subscribed as a token that
allows the UAV to perform actions and maneuvering
based on the incoming output. This process continues till
detection is performed within darknet_ros.
4. Experimental Results and Analysis
A dataset was created in the Kumoh National Institute
of Technology, South Korea, by employing a Bebop drone
that has a high-resolution camera and a GPS mounted on it.
The dataset comprises 1000 images at a resolution of
1920 1080× resized to 428 428× before model training.
For training and testing purposes, the dataset was split
70% and 30%, respectively. Fig. 7 depicts the training
phase of the proposed improved YOLOv3-tiny model
where 20,000 epochs were set. As shown in Fig. 7, the
blue line represents the average loss achieved (0.215)
whereas the red line represents the highest mAP (91.6%).
The detection performance of the improved YOLOv3-
tiny model was benchmarked against the default model by
utilizing the same parametric configurations and dataset.
The metrics used to reflect the efficacy in stair detection of
both models are accuracy, recall, F1-score, and precision.
Table 3 shows that the proposed improved YOLOv3-tiny
model outperformed the default model in terms of
accuracy, recall, and F1-score. Furthermore, a low
precision value with higher values of other performance
metrics shows stable performance from the model.
Fig. 8 shows the real-time detection of the proposed
model, where the top left image represents the starting
point of the UAV after takeoff, and the top right image
represents the middle position of the UAV when hovering
and climbing. In Fig. 8, the bottom left image shows the
last step of the stairs, while the bottom right image shows
the instant when the UAV was located at a distance of r
meters from the stairs.
For the experimental scenario, the set of stairs climbed
was 2.1 m long and 2.85 m wide, as shown in Fig. 3(d).
Based on Algorithm 1, Some of the experiment’s results
are shown in Fig. 9, depicting commands sent by the GCS
and the corresponding images from the built-in camera of
the UAV. In Fig. 9, we have tried to show the different
stages in the decisions made by the UAV, such as moving
forward or upward, hovering, and going to the next stair to
climb it. Furthermore, the actual trajectory-wise UAV
movement from the beginning of the staircase to the
beginning of the next step is shown in Fig. 10 as a 3D plot.
This movement started at approximately 0.8 m from the
starting point of the stairs. In total, 88 experiments were
performed three times each, and the results are shown in
Table 4 for the time elapsed during takeoff and landing on
average, reported to be 55.97 sec.
Table 2. Training Parameters for Both Models.
Parameters for training Configuration values
Image/stairs 428 x 428
Batch size 32
Learning rate 0.001
Optimizer Stochastic gradient descent
Decay 0.0005
Momentum 0.9
Epochs 20,000
Table 3. Performance of the Detection Scheme.
Parameter metrics YOLOv3-tiny
(%) [17]
Modified
YOLOv3-tiny
(%)
Accuracy 90.01 92.06
Recall 89.00 91.00
F1-score 83.00 85.00
Precision 78.00 73.00
Fig. 7. Training phase of the improved YOLOv3-tiny.
Fig. 8. Detection results from the improved YOLOv3-
tiny model.
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
IEIE Transactions on Smart Processing and Computing, vol. 10, no. 5, October 2021
395
Fig. 10. Trajectory of the UAV.
Table 4. Performance Time of the Proposed Stair-
climbing Scheme.
No. Takeoff Landing
1 0:06.35 1:00.91
2 0:05.22 0:57.16
3 0:05.78 1:07.18
Average 0:05.78 1:01.75
5. Conclusion
In this study, we designed, implemented, and
experimented with a system in which a UAV recognizes
and climbs stairs, which are obstacles often encountered
during indoor flight. The system was implemented through
a CNN-based imaging process for real-time stair
(a) (b)
(c) (d)
Fig. 9. GCS screen commands and screen shots from the UAV’s built-in camera for (a) forward movement; (b)
upward movement; (c) hovering; (d) going to the next stair.
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
Choi et al.: Improved CNN-based Path Planning So an Autonomous UAV Can Climb Stairs By using a LiDAR Sensor
396
recognition and by using LiDAR-based distance
measurements. The accuracy derived from stair
recognition was 92.06%, and the actual test results showed
that stair climbing was carried out without collisions.
Future research would require more efficient
algorithms to climb various types of stairs. Moreover, the
proposed system can be combined with SLAM navigation
to expand studies to systems that can autonomously fly
through multiple floors.
Acknowledgement
This work was supported by the Priority Research
Centers Program through the National Research
Foundation of Korea (NRF) funded by the Ministry of
Education, Science and Technology
(2018R1A6A1A03024003).
References
[1] P. R. Prasad, et al., "Monocular vision aided
autonomous UAV navigation in indoor corridor
environments." IEEE Transactions on Sustainable
Computing, Vol. 4, No. 1, pp. 96-108, 2018. Article
(CrossRefLink)
[2] Y. Lu, et al., "A survey on vision-based UAV
navigation." Geo-spatial information science, Vol. 21,
No. 1, pp. 21-32, 2018. Article (CrossRefLink)
[3] M. Ilyas, et al., "Design of sTetro: A Modular,
Reconfigurable, and Autonomous Staircase Cleaning
Robot," Journal of Sensors, Vol. 2018, 16 pages. Jul.
2018. Article (CrossRefLink)
[4] X. Gao, et al., “Dynamics and stability analysis on
stairs climbing of wheel–track mobile robot,”
International Journal of Advanced Robotic Systems,
Vol. 14, No. 4, pp. 1729881417720783, 2017. Article
(CrossRef Link)
[5] J. Israelsen, et al., "Automatic collision avoidance for
manually tele-operated unmanned aerial vehicles." In
2014 IEEE International Conference on Robotics and
Automation (ICRA), pp. 6638-6643, 2014. Article
(CrossRef Link)
[6] L. Chnibo, et al., "UAV position estimation and
collision avoidance using the extended Kalman
filter." IEEE Transactions on Vehicular Technology,
Vol. 62, No. 6, pp. 2749-2762, 2013. Article
(CrossRef Link)
[7] J. Cui, et al., "Autonomous navigation of UAV in
foliage environment." Journal of intelligent & robotic
systems, Vol. 84, No. 1 pp. 259-276, 2016. Article
(CrossRef Link)
[8] Z. Huizhong, et al., "StructSLAM: Visual SLAM
with building structure lines." IEEE Transactions on
Vehicular Technology, Vol. 64, No. 4 pp. 1364-1375,
2015. Article (CrossRef Link)
[9] A. E. Oguz, et al., "On the consistency analysis of A-
SLAM for UAV navigation. Proc. SPIE 9084,
Unmanned Systems Technology XVI, Vol. 9084, pp.
90840R, June. 2014. Article (CrossRef Link)
[10] S. Ross, et all., "Learning monocular reactive uav
control in cluttered natural environments." In 2013
IEEE international conference on robotics and
automation, pp. 1765-1772, 2013. Article (CrossRef
Link)
[11] A. Fraust, et all., "Automated aerial suspended cargo
delivery through reinforcement learning." Artificial
Intelligence, Vol. 247, pp. 381-398, 2017. Article
(CrossRef Link)
[12] N. Imanberdiyev, et all., "Autonomous navigation of
UAV by using real-time model-based reinforcement
learning." In 2016 14th international conference on
control, automation, robotics and vision (ICARCV),
pp. 1-6, 2016. Article (CrossRef Link)
[13] B. L. Sturm, et al., "Machine learning research that
matters for music creation: A case study," Journal of
New Music Research, Vol. 48, No.1, pp. 36-55, 2019.
Article (CrossRefLink)
[14] J. Raharjo, et al., “Cholesterol level measurement
through iris image using gray level co-occurrence
matrix and linear regression,” ARPN Journal of
Engineering and Applied Sciences, Vol. 14, No. 21,
pp. 3757–3763, Nov. 2019. Article (CrossRef Link)
[15] Y. Zhang, et al., "Machine learning based video
coding optimizations: A survey." Information
Sciences, Vol. 506, pp.395-423, Jan. 2020. Article
(CrossRef Link)
[16] M. Heidari, et al., "Improving the performance of
CNN to predict the likelihood of COVID-19 using
chest X-ray images with preprocessing algorithms,"
International journal of medical informatics, Vol. 144,
pp. 104284, Sep. 2020. Article (CrossRef Link)
[17] S. A. Hassan, et al., "Real-time uav detection based
on deep learning network,” In 2019 International
Conference on Information and Communication
Technology Convergence, pp. 630-632, Oct. 2019.
Article (CrossRef Link)
[18] J. Redmon, et al., “You only look once: Unified, real-
time object detection,” In Proceedings of the IEEE
conference on computer vision and pattern
recognition, pp. 779-788, 2016. Article (CrossRef
Link)
[19] D. Mellinger, et al., “Minimum snap trajectory
generation and control for quadrotors,” In 2011 IEEE
international conference on robotics and automation,
pp. 2520-2525, 2011. Article (CrossRef Link)
[20] D. Mellinger, et al., “Trajectory generation and
control for precise aggressive maneuvers with
quadrotors,” The International Journal of Robotics
Research, Vol. 31, No. 5, pp. 664-674, Jan. 2012.
Article (CrossRef Link)
[21] P. Checchin, et al., “Radar scan matching slam using
the fourier-mellin transform,” In Field and Service
Robotics, Vol. 62, pp. 151-161, 2010. Article
(CrossRef Link)
[22] J. Engel, et al., “LSD-SLAM: Large-scale direct
monocular SLAM,” In European conference on
computer vision, Vol. 8690, pp. 834-849, 2014.
Article (CrossRef Link)
[23] C. Mei, et al., “RSLAM: A system for large-scale
mapping in constant-time using stereo,” International
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)
IEIE Transactions on Smart Processing and Computing, vol. 10, no. 5, October 2021
397
journal of computer vision, Vol. 94, No.2, pp. 198-
214, Jun. 2011. Article (CrossRef Link)
[24] M. M uller, et al., “Quadrocopter ball juggling,” in
2011 IEEE/RSJ International Conference on
Intelligent Robots and Systems, pp. 5113–5120, Sep.
2011. Article (CrossRef Link)
[25] A. S. Huang, et al., “Visual odometry and mapping
for autonomous flight using an RGB-D camera,”
Robotics Research. Vol. 100, pp. 235–252, Aug.
2011. Article (CrossRef Link)
[26] J. F. Roberts, et al., “Quadrotor using minimal
sensing for autonomous indoor flight,” In European
Micro Air Vehicle Conference and Flight
Competition (EMAV2007), Sep. 2007. Article
(CrossRef Link)
[27] A. Bry, et al., “State estimation for aggressive flight
in GPS-denied environments using onboard sensing,”
In 2012 IEEE International Conference on Robotics
and Automation, pp. 1-8, May, 2012. Article
(CrossRef Link)
[28] A. Bachrach, et al, “Autonomous flight in unknown
indoor environments,” International Journal of Micro
Air Vehicles, Vol. 1, No. 4, pp. 217-228, Dec. 2009.
Article (CrossRef Link)
[29] M. Achtelik, et al., "Onboard IMU and monocular
vision based control for MAVs in unknown in-and
outdoor environments." 2011 IEEE International
Conference on Robotics and Automation, pp. 3056-
3063, 2011. Article (CrossRef Link)
[30] M. Blösch, et al., "Vision based MAV navigation in
unknown and unstructured environments." 2010
IEEE International Conference on Robotics and
Automation, pp. 21-28, 2010. Article (CrossRef
Link)
[31] G. Nützi, et al., "Fusion of IMU and vision for
absolute scale estimation in monocular SLAM."
Journal of intelligent & robotic systems, Vol. 61, No.
1, pp. 287-299, Nov. 2011. Article (CrossRef Link)
[32] S. Weiss, et al., “Versatile distributed pose estimation
and sensor self-calibration for an autonomous MAV,”
In 2012 IEEE International Conference on Robotics
and Automation, pp. 31-38, 2012. Article (CrossRef
Link)
[33] T. Rahim, et al., “A Deep Convolutional Neural
Network for the Detection of Polyps in Colonoscopy
Images,” Biomedical Signal Processing and Control
68 (2021): 102654.
Yeonji Choi received her BSc in
Electrical Engineering in 2019 and
received her MSc from the Department
of IT Convergence Engineering at
Kumoh National Institute of
Technology (KIT) Gumi, South Korea,
in 2021. Currently, she is working as
graduate research assistant at the
Wireless and Emerging Network System (WENS) Lab in
the Department of IT Convergence Engineering, Kumoh
National Institute of Technology (KIT), Gumi, South
Korea. Her major research interests include intelligent
control and systems, Unmanned Aerial Vehicles, and
wireless communications.
Tariq Rahim is a PhD student in the
Wireless and Emerging Network
System Laboratory (WENS Lab) of the
Department of IT Convergence
Engineering, Kumoh National Institute
of Technology, Republic of Korea. He
completed his master’s degree in
Information and Communication
Engineering from Beijing Institute of Technology, PRC, in
2017. His research interests include image and video
processing and quality of experience for high-resolution
videos.
Soo Young Shin received his BSc,
MSc, and PhD in Electrical Engi-
neering and Computer Science from
Seoul National University, Korea, in
1999, 2001, and 2006, respectively. He
was a visiting scholar for the FUN Lab
at the University of Washington,
U.S.A., from July 2006 to June 2007.
After three years working in the WiMAX Design Lab of
Samsung Electronics, he is now an associate professor for
the School of Electronics at Kumoh National Institute of
Technology, joining the institute in September 2010. His
research interests include wireless LANs, WPANs,
WBANs, wireless mesh networks, sensor networks,
coexistence among wireless networks, industrial and
military networks, cognitive radio networks, and next-
generation mobile wireless broadband networks.
Copyrights © 2021 The Institute of Electronics and Information Engineers
금오공과대학교 | IP:202.31.134.*** | Accessed 2021/11/12 09:19(KST)