An information fusion framework for person localization via body pose in spectator crowds.
Saved in:
| Title: | An information fusion framework for person localization via body pose in spectator crowds. |
|---|---|
| Authors: | Shaban, Muhammad1,2 (AUTHOR) m.shaban@warwick.ac.uk, Mahmood, Arif1,2,3 (AUTHOR) arif.mahmood@itu.edu.pk, Al-Maadeed, Somaya Ali2 (AUTHOR) s_alali@qu.edu.qa, Rajpoot, Nasir1 (AUTHOR) n.m.rajpoot@warwick.ac.uk |
| Source: | Information Fusion. Nov2019, Vol. 51, p178-188. 11p. |
| Subjects: | Spectators, Crowds, Anomaly detection (Computer security), Artificial neural networks |
| Abstract: | • In low resolution crowd images, each person is localized and segmented. • For head detection in crowds, a novel Deep-CNN based head detector (DHD) is proposed. • DPM pose detection algorithm is modified to detect upper body poses in crowds. • DHD and modified DPM are integrated using a novel fusion framework. • Information fusion improved person pose detection and segmentation results. Person localization or segmentation in low resolution crowded scenes is important for person tracking and recognition, action detection and anomaly identification. Due to occlusion and lack of inter-person space, person localization becomes a difficult task. In this work, we propose a novel information fusion framework to integrate a Deep Head Detector and a body pose detector. A more accurate body pose showing limb positions will result in more accurate person localization. We propose a novel Deep Head Detector (DHD) to detect person heads in crowds. The proposed DHD is a fully convolutional neural network and it has shown improved head detection performance in crowds. We modify Deformable Parts Model (DPM) pose detector to detect multiple upper body poses in crowds. We efficiently fuse the information obtained by the proposed DHD and the modified DPM to obtain a more accurate person pose detector. The proposed framework is named as Fusion DPM (FDPM) and it has exhibited improved body pose detection performance on spectator crowds. The detected body poses are then used for more accurate person localization by segmenting each person in the crowd. [ABSTRACT FROM AUTHOR] |
| Copyright of Information Fusion is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 136242308 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: An information fusion framework for person localization via body pose in spectator crowds. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Shaban%2C+Muhammad%22">Shaban, Muhammad</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> m.shaban@warwick.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Mahmood%2C+Arif%22">Mahmood, Arif</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> arif.mahmood@itu.edu.pk</i><br /><searchLink fieldCode="AR" term="%22Al-Maadeed%2C+Somaya+Ali%22">Al-Maadeed, Somaya Ali</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> s_alali@qu.edu.qa</i><br /><searchLink fieldCode="AR" term="%22Rajpoot%2C+Nasir%22">Rajpoot, Nasir</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> n.m.rajpoot@warwick.ac.uk</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Information+Fusion%22">Information Fusion</searchLink>. Nov2019, Vol. 51, p178-188. 11p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Spectators%22">Spectators</searchLink><br /><searchLink fieldCode="DE" term="%22Crowds%22">Crowds</searchLink><br /><searchLink fieldCode="DE" term="%22Anomaly+detection+%28Computer+security%29%22">Anomaly detection (Computer security)</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: • In low resolution crowd images, each person is localized and segmented. • For head detection in crowds, a novel Deep-CNN based head detector (DHD) is proposed. • DPM pose detection algorithm is modified to detect upper body poses in crowds. • DHD and modified DPM are integrated using a novel fusion framework. • Information fusion improved person pose detection and segmentation results. Person localization or segmentation in low resolution crowded scenes is important for person tracking and recognition, action detection and anomaly identification. Due to occlusion and lack of inter-person space, person localization becomes a difficult task. In this work, we propose a novel information fusion framework to integrate a Deep Head Detector and a body pose detector. A more accurate body pose showing limb positions will result in more accurate person localization. We propose a novel Deep Head Detector (DHD) to detect person heads in crowds. The proposed DHD is a fully convolutional neural network and it has shown improved head detection performance in crowds. We modify Deformable Parts Model (DPM) pose detector to detect multiple upper body poses in crowds. We efficiently fuse the information obtained by the proposed DHD and the modified DPM to obtain a more accurate person pose detector. The proposed framework is named as Fusion DPM (FDPM) and it has exhibited improved body pose detection performance on spectator crowds. The detected body poses are then used for more accurate person localization by segmenting each person in the crowd. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Information Fusion is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=136242308 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.inffus.2018.11.011 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 11 StartPage: 178 Subjects: – SubjectFull: Spectators Type: general – SubjectFull: Crowds Type: general – SubjectFull: Anomaly detection (Computer security) Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: An information fusion framework for person localization via body pose in spectator crowds. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Shaban, Muhammad – PersonEntity: Name: NameFull: Mahmood, Arif – PersonEntity: Name: NameFull: Al-Maadeed, Somaya Ali – PersonEntity: Name: NameFull: Rajpoot, Nasir IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 11 Text: Nov2019 Type: published Y: 2019 Identifiers: – Type: issn-print Value: 15662535 Numbering: – Type: volume Value: 51 Titles: – TitleFull: Information Fusion Type: main |
| ResultId | 1 |
