Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot

In this paper we present a vision-based approach to detect multiple persons with occlusion handling from a mobile robot in real-world scenarios under two lighting conditions, good illumination (lighted) and poor illumination (dark). We use depth and thermal information that are fused for occlusion h...

Full description

Bibliographic Details
Main Authors: Hasim, Saipol Hadi, Mamat, Rosbi, Sheikh, Usman Ullah, Mohd. Amin, Shamsuddin
Format: Article
Published: Springer Verlag 2016
Subjects:
_version_ 1796861738115661824
author Hasim, Saipol Hadi
Mamat, Rosbi
Sheikh, Usman Ullah
Mohd. Amin, Shamsuddin
author_facet Hasim, Saipol Hadi
Mamat, Rosbi
Sheikh, Usman Ullah
Mohd. Amin, Shamsuddin
author_sort Hasim, Saipol Hadi
collection ePrints
description In this paper we present a vision-based approach to detect multiple persons with occlusion handling from a mobile robot in real-world scenarios under two lighting conditions, good illumination (lighted) and poor illumination (dark). We use depth and thermal information that are fused for occlusion handling. First, a classifier is trained using thermal images of the human upper-body. This classifier is used to obtain the bounding box coordinates of human. The depth image is later fused with the region of interest obtained from the thermal image. Using the initial bounding box, occlusion handling is performed to determine the final position of human in the image. The proposed method significantly improves human detection even in crowded scene and poor illumination.
first_indexed 2024-03-05T20:00:58Z
format Article
id utm.eprints-71233
institution Universiti Teknologi Malaysia - ePrints
last_indexed 2024-03-05T20:00:58Z
publishDate 2016
publisher Springer Verlag
record_format dspace
spelling utm.eprints-712332017-11-15T03:47:19Z http://eprints.utm.my/71233/ Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot Hasim, Saipol Hadi Mamat, Rosbi Sheikh, Usman Ullah Mohd. Amin, Shamsuddin TK Electrical engineering. Electronics Nuclear engineering In this paper we present a vision-based approach to detect multiple persons with occlusion handling from a mobile robot in real-world scenarios under two lighting conditions, good illumination (lighted) and poor illumination (dark). We use depth and thermal information that are fused for occlusion handling. First, a classifier is trained using thermal images of the human upper-body. This classifier is used to obtain the bounding box coordinates of human. The depth image is later fused with the region of interest obtained from the thermal image. Using the initial bounding box, occlusion handling is performed to determine the final position of human in the image. The proposed method significantly improves human detection even in crowded scene and poor illumination. Springer Verlag 2016 Article PeerReviewed Hasim, Saipol Hadi and Mamat, Rosbi and Sheikh, Usman Ullah and Mohd. Amin, Shamsuddin (2016) Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot. Studies in Computational Intelligence, 647 . pp. 365-380. ISSN 1860-949X https://www.scopus.com/inward/record.uri?eid=2-s2.0-84991769730&doi=10.1007%2f978-3-319-33353-3_19&partnerID=40&md5=9a48d22337b4709e0eca954126e99d32
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Hasim, Saipol Hadi
Mamat, Rosbi
Sheikh, Usman Ullah
Mohd. Amin, Shamsuddin
Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title_full Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title_fullStr Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title_full_unstemmed Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title_short Depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
title_sort depth and thermal image fusion for human detection with occlusion handling under poor illumination from mobile robot
topic TK Electrical engineering. Electronics Nuclear engineering
work_keys_str_mv AT hasimsaipolhadi depthandthermalimagefusionforhumandetectionwithocclusionhandlingunderpoorilluminationfrommobilerobot
AT mamatrosbi depthandthermalimagefusionforhumandetectionwithocclusionhandlingunderpoorilluminationfrommobilerobot
AT sheikhusmanullah depthandthermalimagefusionforhumandetectionwithocclusionhandlingunderpoorilluminationfrommobilerobot
AT mohdaminshamsuddin depthandthermalimagefusionforhumandetectionwithocclusionhandlingunderpoorilluminationfrommobilerobot