2024-03-28T11:30:32Z
https://nagoya.repo.nii.ac.jp/oai
oai:nagoya.repo.nii.ac.jp:00024555
2023-01-16T04:28:20Z
312:313:314
Human Wearable Attribute Recognition Using Probability-Map-Based Decomposition of Thermal Infrared Images
KRESNARAMAN, Brahmastro
72686
KAWANISHI, Yasutomo
72687
DEGUCHI, Daisuke
72688
TAKAHASHI, Tomokazu
72689
MEKADA, Yoshito
72690
IDE, Ichiro
72691
MURASE, Hiroshi
72692
thermal infrared
wearable attribute
recognition
decomposition
probability map
This paper addresses the attribute recognition problem, a field of research that is dominated by studies in the visible spectrum. Only a few works are available in the thermal spectrum, which is fundamentally different from the visible one. This research performs recognition specifically on wearable attributes, such as glasses and masks. Usually these attributes are relatively small in size when compared with the human body, on top of a large intra-class variation of the human body itself, therefore recognizing them is not an easy task. Our method utilizes a decomposition framework based on Robust Principal Component Analysis (RPCA) to extract the attribute information for recognition. However, because it is difficult to separate the body and the attributes without any prior knowledge, noise is also extracted along with attributes, hampering the recognition capability. We made use of prior knowledge; namely the location where the attribute is likely to be present. The knowledge is referred to as the Probability Map, incorporated as a weight in the decomposition by RPCA. Using the Probability Map, we achieve an attribute-wise decomposition. The results show a significant improvement with this approach compared to the baseline, and the proposed method achieved the highest performance in average with a 0.83 F-score.
journal article
一般社団法人電子情報通信学会
2017-03-01
application/pdf
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
3
E100
854
864
http://doi.org/10.1587/transfun.E100.A.854
https://www.ieice.org/jpn/books/transaction.html
http://hdl.handle.net/2237/26773
0916-8508
https://nagoya.repo.nii.ac.jp/record/24555/files/e100-a_3_854.pdf
eng
https://doi.org/10.1587/transfun.E100.A.854
copyright(c)2017 IEICE