Page 181 - Kaleidoscope Academic Conference Proceedings 2020
P. 181
Industry-driven digital transformation
AI-based suspicious object recognition technologies for this filtering for internet of medical things,” IEEE Access,
system, it can greatly improve the recognition rate for vol. 8, pp. 104 016–104 025, 2020.
suspicious objects. To achieve this goal, we built a suspicious
[9] C. Ledig, L. Theis, F. Huszár, J. Caballero,
object database for CNN training by GAN and active/passive
A. Cunningham, A. Acosta, A. Aitken, A. Tejani,
imagers. In the evaluation section, we prove how to get
J. Totz, Z. Wang, and W. Shi, “Photo-realistic single
an optimal recognition rate when the original images used
image super-resolution using a generative adversarial
for CNN training are not enough. This work is significant for
network,” in 2017 IEEE Conference on Computer Vision
improving the service quality of AI-based W-band suspicious
and Pattern Recognition (CVPR), 2017, pp. 105–114.
object detection systems for moving persons. Moreover, we
introduce the corresponding standardization activities.
[10] A. Tessmann, S. Kudszus, T. Feltgen, M. Riessle,
C. Sklarczyk, and W. H. Haydl, “Compact
ACKNOWLEGEMENT
single-chip w-band fmcw radar modules for
commercial high-resolution sensor applications,”
This work was supported by the Research Grant for
IEEE Transactions on Microwave Theory and
Expanding Radio Wave Resources in FY2020 of the Ministry
Techniques, vol. 50, no. 12, pp. 2995–3001, 2002.
of Internal Affairs and Communications through a Contract
for Research and Development of Radar Fundamental [11] C. Wang, C. Xu, X. Yao, and D. Tao, “Evolutionary
Technology for Advanced Recognition of Moving Objects generative adversarial networks,” IEEE Transactions on
for Security Enhancement under Grant JPJ000254. Evolutionary Computation, vol. 23, no. 6, pp. 921–934,
2019.
REFERENCES
[12] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu,
[1] T. Joshi, H. Aarya, and P. Kumar, “Suspicious object D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio,
detection,” in 2016 2nd International Conference on “Generative adversarial nets,” in Advances in neural
Advances in Computing, Communication, Automation information processing systems, 2014, pp. 2672–2680.
(ICACCA) (Fall), 2016, pp. 1–6.
[2] H. Li, M. Zhang, K. Yu, X. Qi, Q. Hua, and Y. Zhu,
“R3mr: Region growing based 3d mesh reconstruction
for big data platform,” IEEE Access, vol. 8, pp.
91 740–91 750, 2020.
[3] Q. Liu, B. Kang, K. Yu, X. Qi, J. Li, S. Wang, and H. Li,
“Contour-maintaining-based image adaption for an
efficient ambulance service in intelligent transportation
systems,” IEEE Access, vol. 8, pp. 12 644–12 654, 2020.
[4] S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn:
Towards real-time object detection with region proposal
networks,” IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 39, no. 6, pp. 1137–1149,
2017.
[5] L. Yujiri, M. Shoucri, and P. Moffa, “Passive millimeter
wave imaging,” IEEE Microwave Magazine, vol. 4,
no. 3, pp. 39–50, 2003.
[6] K. Yu, X. Qi, T. Sato, S. H. Myint, Z. Wen,
Y. Katsuyama, K. Tokuda, W. Kameyama, and T. Sato,
“Design and performance evaluation of an ai-based
w-band suspicious object detection system for moving
persons in the iot paradigm,” IEEE Access, vol. 8, pp.
81 378–81 393, 2020.
[7] H. Li, M. Zhang, K. Yu, J. Zhang, Q. Hua,
B. Wu, and Z. Yu, “Combined forecasting model of
cloud computing resource load for energy-efficient iot
system,” IEEE Access, vol. 7, pp. 149 542–149 553,
2019.
[8] H. Li, J. Fan, K. Yu, X. Qi, Z. Wen, Q. Hua, M. Zhang,
and Q. Zheng, “Medical image coloring based on gabor
– 123 –