TY - JOUR
T1 - Stochastic remote sensing event classification over adaptive posture estimation via multifused data and deep belief network
AU - Gochoo, Munkhjargal
AU - Akhter, Israr
AU - Jalal, Ahmad
AU - Kim, Kibum
N1 - Funding Information:
Funding: This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education (No. 2018R1D1A1A02085645).
Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/3/1
Y1 - 2021/3/1
N2 - Advances in video capturing devices enable adaptive posture estimation (APE) and event classification of multiple human-based videos for smart systems. Accurate event classification and adaptive posture estimation are still challenging domains, although researchers work hard to find solutions. In this research article, we propose a novel method to classify stochastic remote sensing events and to perform adaptive posture estimation. We performed human silhouette extraction using the Gaussian Mixture Model (GMM) and saliency map. After that, we performed human body part detection and used a unified pseudo-2D stick model for adaptive posture estimation. Mul-tifused data that include energy, 3D Cartesian view, angular geometric, skeleton zigzag and move-able body parts were applied. Using a charged system search, we optimized our feature vector and deep belief network. We classified complex events, which were performed over sports videos in the wild (SVW), Olympic sports, UCF aerial action dataset and UT-interaction datasets. The mean accuracy of human body part detection was 83.57% over the UT-interaction, 83.00% for the Olympic sports and 83.78% for the SVW dataset. The mean event classification accuracy was 91.67% over the UT-interaction, 92.50% for Olympic sports and 89.47% for SVW dataset. These results are superior compared to existing state-of-the-art methods.
AB - Advances in video capturing devices enable adaptive posture estimation (APE) and event classification of multiple human-based videos for smart systems. Accurate event classification and adaptive posture estimation are still challenging domains, although researchers work hard to find solutions. In this research article, we propose a novel method to classify stochastic remote sensing events and to perform adaptive posture estimation. We performed human silhouette extraction using the Gaussian Mixture Model (GMM) and saliency map. After that, we performed human body part detection and used a unified pseudo-2D stick model for adaptive posture estimation. Mul-tifused data that include energy, 3D Cartesian view, angular geometric, skeleton zigzag and move-able body parts were applied. Using a charged system search, we optimized our feature vector and deep belief network. We classified complex events, which were performed over sports videos in the wild (SVW), Olympic sports, UCF aerial action dataset and UT-interaction datasets. The mean accuracy of human body part detection was 83.57% over the UT-interaction, 83.00% for the Olympic sports and 83.78% for the SVW dataset. The mean event classification accuracy was 91.67% over the UT-interaction, 92.50% for Olympic sports and 89.47% for SVW dataset. These results are superior compared to existing state-of-the-art methods.
KW - Deep belief network
KW - Event classification
KW - Human body part detection
KW - Multifused data
KW - Pseudo-2D-stick model
UR - http://www.scopus.com/inward/record.url?scp=85102237592&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102237592&partnerID=8YFLogxK
U2 - 10.3390/rs13050912
DO - 10.3390/rs13050912
M3 - Article
AN - SCOPUS:85102237592
SN - 2072-4292
VL - 13
SP - 1
EP - 29
JO - Remote Sensing
JF - Remote Sensing
IS - 5
M1 - 912
ER -