Real-Time Implementation of Human Detection in Thermal Imagery Based on CNN

Shahid, Nazeer; Yu, Gwang-Hyun; Dat, Trinh Tan; 신도성,; Kim, Jin‐Young

doi:10.14801/jkiit.2019.17.1.107

Cited by 4 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method not only increases the resolution of the image but also enhances the baseline quality of inputs for object recognition. The system was tested using two datasets that included pedestrians and six distinct types of vehicles [10].…”

Section: Literature Surveymentioning

confidence: 99%

A Hybrid Retina Net Classifier for Thermal Imaging

Teju,

Sowmya,

Kandula

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Thermal imaging is a cutting-edge technology which has the capability to detect objects in any environmental conditions, such as smoke, fog, smog, etc. This technology finds its importance mainly during nighttime since it does not require light to detect the objects. Applications of this technology span into various sectors, most importantly in border security to detect any incoming hazards. Object detection and classification are generally difficult with thermal imaging. In this paper, a one-stage deep convolution network-based object detection and classification called retina net is introduced. Existing surveys are based on object detection using infrared information obtained from the objects. This research is focused on detecting and identifying objects from thermal images and surveillance data.

show abstract

Section: Literature Surveymentioning

confidence: 99%

A Hybrid Retina Net Classifier for Thermal Imaging

Teju,

Sowmya,

Kandula

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…They report an overall accuracy of over 95% for six object classes related to land defense using the CNN-based detector. A method for real-time human detection in thermal images based on background modeling and CNN is presented in [28]. For real-time implementation, the background modeling is done by modified running Gaussian average and the CNN-based human classification is performed only for the detected foreground objects.…”

Section: Related Workmentioning

confidence: 99%