Abstract
Thermal images have the property of identifying objects even in low light conditions. However, person detection in thermal is tricky, due to varying person representations depending upon the surrounding temperature. Three major polarities are commonly observed in these representations i.e., 1. person warmer than the background, 2. person colder than the background and 3. person’s body temperature is similar to background. In this work, we have studied and analyzed the performance of the detection network by using the data in its original form and by harmonizing the person representation in two ways i.e., dark persons in the light background and light persons in a darker background. The data passed to each testing scenario was first pre-processed using histogram stretching to enhance the contrast. The work also presents the method to separate the three kinds of images from thermal data. The analysis is performed on publicly available outdoor AAUPD-T and OSU-T datasets. Precision, recall, and F1 score is used to evaluate network performance. The results have shown that network performance is not enhanced by performing the mentioned pre-processing. Best results are obtained by using the data in its original form.
Original language | English |
---|---|
Title of host publication | 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML) |
Publisher | IEEE |
Publication date | Aug 2021 |
Pages | 86-91 |
Article number | 9520729 |
ISBN (Print) | 978-1-6654-4384-5 |
ISBN (Electronic) | 978-1-6654-4383-8 |
DOIs | |
Publication status | Published - Aug 2021 |
Event | 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML 2021) - Chengdu, China Duration: 16 Jul 2021 → 18 Jul 2021 http://www.prml.org/prml2021.html |
Conference
Conference | 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML 2021) |
---|---|
Country/Territory | China |
City | Chengdu |
Period | 16/07/2021 → 18/07/2021 |
Internet address |