TY - GEN
T1 - A real-time visual tracking and distance measuring algorithm based on SSD
AU - Zhang, Tongpo
AU - Kong, Zejian
AU - Guo, Tiantian
AU - Lopez-Benitez, Migue
AU - Lim, Enggee
AU - Ma, Fei
AU - Yu, Limin
N1 - Funding Information:
This research was partially funded by the Research Enhancement Fund of XJTLU (REF-19-01-04), National Natural Science Foundation of China (NSFC) (Grant No. 61501380),and by AI University Research Center (AI-URC) and XJTLU Laboratory for Intelligent Computation and Financial Technology through XJTLU Key Programme Special Fund (KSF-P-02), and Jiangsu Data Science and Cognitive Computational Engineering Research Centre..
Publisher Copyright:
© 2022 IEEE.
PY - 2022/4/22
Y1 - 2022/4/22
N2 - Real-time visual tracking and distance measuring algorithms are of critical importance in industry areas. In this paper, we propose a novel method to meet the needs. This algorithm can measure the distance of the tracking object with high accuracy in real-time. First, we compare the ability of the traditional visual tracking algorithms with deep learning visual tracking methods. Furthermore, three deep learning visual tracking methods are compared and evaluated to find the most suitable one that can meet the real-time requirement of tracking targets. Then we create a real-time visual tracking and distance measuring algorithm based on SSD. We raise two methods for distance measuring measurement algorithms and both of the methods are tested. The experiments are implemented to validate the performance of the designed approach. From the experimental results, we confirmed the designed real-time visual tracking and distance measuring algorithm based on SSD performed successfully.
AB - Real-time visual tracking and distance measuring algorithms are of critical importance in industry areas. In this paper, we propose a novel method to meet the needs. This algorithm can measure the distance of the tracking object with high accuracy in real-time. First, we compare the ability of the traditional visual tracking algorithms with deep learning visual tracking methods. Furthermore, three deep learning visual tracking methods are compared and evaluated to find the most suitable one that can meet the real-time requirement of tracking targets. Then we create a real-time visual tracking and distance measuring algorithm based on SSD. We raise two methods for distance measuring measurement algorithms and both of the methods are tested. The experiments are implemented to validate the performance of the designed approach. From the experimental results, we confirmed the designed real-time visual tracking and distance measuring algorithm based on SSD performed successfully.
KW - object detection
KW - real-time distance measurement
KW - SSD algorithm
UR - http://www.scopus.com/inward/record.url?scp=85136990166&partnerID=8YFLogxK
U2 - 10.1109/CTISC54888.2022.9849795
DO - 10.1109/CTISC54888.2022.9849795
M3 - Conference Proceeding
AN - SCOPUS:85136990166
T3 - CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications
BT - CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications
A2 - Gerogianni, Vassilis C.
A2 - Yue, Yong
A2 - Kamareddine, Fairouz
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022
Y2 - 22 April 2022 through 24 April 2022
ER -