IEEE transactions on circuits and systems for video technology, 2019-09, Vol.29 (9), p.2580-2589
2019
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- Deep CNNs for Object Detection Using Passive Millimeter Sensors
- Ist Teil von
- IEEE transactions on circuits and systems for video technology, 2019-09, Vol.29 (9), p.2580-2589
- Ort / Verlag
- New York: IEEE
- Erscheinungsjahr
- 2019
- Quelle
- IEEE Electronic Library Online
- Beschreibungen/Notizen
- Passive millimeter wave images (PMMWIs) can be used to detect and localize objects concealed under clothing. Unfortunately, the quality of the acquired images and the unknown position, shape, and size of the hidden objects render these tasks challenging. In this paper, we discuss a deep learning approach to this detection/localization problem. The effect of the nonstationary acquisition noise on different architectures is analyzed and discussed. A comparison with shallow architectures is also presented. The achieved detection accuracy defines a new state of the art in object detection on PMMWIs. The low computational training and testing costs of the solution allow its use in real-time applications.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 1051-8215eISSN: 1558-2205DOI: 10.1109/TCSVT.2017.2774927Titel-ID: cdi_proquest_journals_2285339054
- Format
- –
- Schlagworte
- Classification, Computer architecture, Convolution, deep learning, Feature extraction, Image acquisition, Image detection, Image quality, Image segmentation, Image sensors, Machine learning, millimeter wave imaging, object detection, Object recognition, Passive millimeter wave imaging, security, Sensors