IEICE TRANSACTIONS on Information
Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance
Summary :
We present a reconfigurable deep learning pedestrian detection system for surveillance systems that detect people with shadows in different lighting and heavily occluded conditions. This work proposes a region-based CNN, combined with CMOS and thermal cameras to obtain human features even under poor lighting conditions. The main advantage of a reconfigurable system with respect to processor-based systems is its high performance and parallelism when processing large amount of data such as video frames. We discuss the details of hardware implementation in the proposed real-time pedestrian detection algorithm on a Zynq FPGA. Simulation results show that the proposed integrated approach of R-CNN architecture with cameras provides better performance in terms of accuracy, precision, and F1-score. The performance of Zynq FPGA was compared to other works, which showed that the proposed architecture is a good trade-off in terms of quality, accuracy, speed, and resource utilization.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.9 pp.1610-1614
- Publication Date
- 2023/09/01
- Publicized
- 2023/06/09
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019EDL8132
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
M.K. JEEVARAJAN
Anna University
P. NIRMAL KUMAR
Anna University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
M.K. JEEVARAJAN, P. NIRMAL KUMAR, "Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 9, pp. 1610-1614, September 2023, doi: 10.1587/transinf.2019EDL8132.
Abstract: We present a reconfigurable deep learning pedestrian detection system for surveillance systems that detect people with shadows in different lighting and heavily occluded conditions. This work proposes a region-based CNN, combined with CMOS and thermal cameras to obtain human features even under poor lighting conditions. The main advantage of a reconfigurable system with respect to processor-based systems is its high performance and parallelism when processing large amount of data such as video frames. We discuss the details of hardware implementation in the proposed real-time pedestrian detection algorithm on a Zynq FPGA. Simulation results show that the proposed integrated approach of R-CNN architecture with cameras provides better performance in terms of accuracy, precision, and F1-score. The performance of Zynq FPGA was compared to other works, which showed that the proposed architecture is a good trade-off in terms of quality, accuracy, speed, and resource utilization.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8132/_p
Copy
@ARTICLE{e106-d_9_1610,
author={M.K. JEEVARAJAN, P. NIRMAL KUMAR, },
journal={IEICE TRANSACTIONS on Information},
title={Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance},
year={2023},
volume={E106-D},
number={9},
pages={1610-1614},
abstract={We present a reconfigurable deep learning pedestrian detection system for surveillance systems that detect people with shadows in different lighting and heavily occluded conditions. This work proposes a region-based CNN, combined with CMOS and thermal cameras to obtain human features even under poor lighting conditions. The main advantage of a reconfigurable system with respect to processor-based systems is its high performance and parallelism when processing large amount of data such as video frames. We discuss the details of hardware implementation in the proposed real-time pedestrian detection algorithm on a Zynq FPGA. Simulation results show that the proposed integrated approach of R-CNN architecture with cameras provides better performance in terms of accuracy, precision, and F1-score. The performance of Zynq FPGA was compared to other works, which showed that the proposed architecture is a good trade-off in terms of quality, accuracy, speed, and resource utilization.},
keywords={},
doi={10.1587/transinf.2019EDL8132},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance
T2 - IEICE TRANSACTIONS on Information
SP - 1610
EP - 1614
AU - M.K. JEEVARAJAN
AU - P. NIRMAL KUMAR
PY - 2023
DO - 10.1587/transinf.2019EDL8132
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2023
AB - We present a reconfigurable deep learning pedestrian detection system for surveillance systems that detect people with shadows in different lighting and heavily occluded conditions. This work proposes a region-based CNN, combined with CMOS and thermal cameras to obtain human features even under poor lighting conditions. The main advantage of a reconfigurable system with respect to processor-based systems is its high performance and parallelism when processing large amount of data such as video frames. We discuss the details of hardware implementation in the proposed real-time pedestrian detection algorithm on a Zynq FPGA. Simulation results show that the proposed integrated approach of R-CNN architecture with cameras provides better performance in terms of accuracy, precision, and F1-score. The performance of Zynq FPGA was compared to other works, which showed that the proposed architecture is a good trade-off in terms of quality, accuracy, speed, and resource utilization.
ER -
English
