tion over union, the system orchestrates the detec-
tion and tracking algorithms within the ROS environ-
ment. During the experiment, the system can guide
the tracking robot to find the target robustly in real
time. Furthermore, with the stereo vision, the system
also has the ability to estimate the target’s position
using depth information which can drive the robot to
track and get close to the target. In future work, more
criteria can be chosen and tested within the system.
Furthermore, it seems promising to train a recurrent
neural network to potentially gain a better detecting
and tracking performance.
ACKNOWLEDGEMENTS
This research benefited from the support by the China
Scholarship Council (CSC, No. 201808080061) for
Wei Luo.
REFERENCES
Ahmed, N., Natarajan, T., and Rao, K. R. (1974). Discrete
cosine transform. IEEE Transactions on Computers,
C-23(1):90–93.
Bjelonic, M. (2016–2018). YOLO ROS:
Real-time object detection for ROS.
https://github.com/leggedrobotics/darknet
ros.
Chang, Y., Chung, P., and Lin, H. (2018). Deep learning
for object identification in ROS-based mobile robots.
In IEEE International Conference on Applied System
Invention (ICASI), pages 66–69, Chiba, Japan.
Fu, C., Carrio, A., and Campoy, P. (2015). Efficient vi-
sual odometry and mapping for unmanned aerial vehi-
cle using arm-based stereo vision pre-processing sys-
tem. In International Conference on Unmanned Air-
craft Systems (ICUAS), pages 957–962, Denver, USA.
Fu, C., Zhang, Y., Duan, R., and Xie, Z. (2018). Ro-
bust scalable part-based visual tracking for UAV with
background-aware correlation filter. In IEEE Interna-
tional Conference on Robotics and Biomimetics (RO-
BIO), pages 1–8, Kuala Lumpur, Malaysia.
Gode, C. S. and Khobragade, A. S. (2016). Object detection
using color clue and shape feature. In International
Conference on Wireless Communications, Signal Pro-
cessing and Networking (WiSPNET), pages 464–468,
Chennai, India.
Hamming, R. W. (1950). Error detecting and error cor-
recting codes. The Bell System Technical Journal,
29(2):147–160.
Henriques, J. F., Caseiro, R., Martins, P., and Batista, J.
(2015). High-speed tracking with kernelized corre-
lation filters. IEEE Transactions on Pattern Analysis
and Machine Intelligence (TPAMI), 37(3):583–596.
Huang, A. S., Olson, E., and Moore, D. C. (2010).
LCM: Lightweight communications and marshalling.
In IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS), pages 4057–4062, Taipei,
Taiwan.
Kalal, Z., Mikolajczyk, K., and Matas, J. (2012). Tracking-
learning-detection. IEEE Transactions on Pat-
tern Analysis and Machine Intelligence (TPAMI),
34(7):1409–1422.
Kim, D., Lee, D., Myung, H., and Choi, H. (2012). Ob-
ject detection and tracking for autonomous under-
water robots using weighted template matching. In
Oceans - Yeosu, pages 1–5, Yeosu, South Korea.
Kume, Y., Hirata, Y., Kosuge, K., Asama, H., Kaetsu, H.,
and Kawabata, K. (2001). Decentralized control of
multiple mobile robots transporting a single object in
coordination without using force/torque sensors. In
IEEE International Conference on Robotics and Au-
tomation (ICRA), volume 3, pages 3004–3009 vol.3,
Seoul, South Korea.
Li, J., Wang, J., and Mao, J. (2014). Color moving object
detection method based on automatic color clustering.
In Proceedings of the 33rd Chinese Control Confer-
ence (CCC), pages 7232–7235, Nanjing, China.
Li, K., Zhao, X., Sun, Z., and Tan, M. (2017). Robust
target detection, tracking and following for an indoor
mobile robot. In IEEE International Conference on
Robotics and Biomimetics (ROBIO), pages 593–598,
Macau, China.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu,
C.-Y., and Berg, A. C. (2016). SSD: Single shot multi-
box detector. In Leibe, B., Matas, J., Sebe, N., and
Welling, M., editors, European Conference on Com-
puter Vision (ECCV), pages 21–37, Amsterdam, the
Netherlands.
Lopez, A., Paredes, R., Quiroz, D., Trovato, G., and Cuellar,
F. (2017). Robotman: A security robot for human-
robot interaction. In 18th International Conference on
Advanced Robotics (ICAR), pages 7–12, Hong Kong.
Martins, A., Almeida, J., Almeida, C., Dias, A., Dias, N.,
Aaltonen, J., Heininen, A., Koskinen, K. T., Rossi, C.,
Dominguez, S., V
¨
or
¨
os, C., Henley, S., McLoughlin,
M., van Moerkerk, H., Tweedie, J., Bodo, B., Zaj-
zon, N., and Silva, E. (2018). UX 1 system design
- a robotic system for underwater mining exploration.
In IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS), pages 1494–1500.
Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental
improvement. CoRR, arxiv.org/abs/1804.02767.
Ren, S., He, K., Girshick, R., and Sun, J. (2017). Faster
R-CNN: Towards real-time object detection with re-
gion proposal networks. IEEE Transactions on Pat-
tern Analysis and Machine Intelligence, 39(6):1137–
1149.
Shao, L., Zhu, F., and Li, X. (2015). Transfer learning for
visual categorization: A survey. IEEE Transactions on
Neural Networks and Learning Systems, 26(5):1019–
1034.
Sharma, T. G., Kritin Valivati, N., Puthige, A., and Hari,
U. (2018). Object position estimation using stereo vi-
sion. In IEEE 8th International Advance Computing
Conference (IACC), pages 66–71, Greater Noida, In-
dia.
Stereo Vision-based Autonomous Target Detection and Tracking on an Omnidirectional Mobile Robot
275