Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching
CCTVs and telecom base stations act as sensors, and collect massive face and phone related data. When used for person localization and trajectory characterization, they each present quite different spatiotemporal characteristics: CCTV is associated with slowly sampled face ID trajectories with spati...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10844270/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576775723417600 |
|---|---|
| author | Changfeng Cao Wenchuan Zhang Hua Yang Dan Ruan |
| author_facet | Changfeng Cao Wenchuan Zhang Hua Yang Dan Ruan |
| author_sort | Changfeng Cao |
| collection | DOAJ |
| description | CCTVs and telecom base stations act as sensors, and collect massive face and phone related data. When used for person localization and trajectory characterization, they each present quite different spatiotemporal characteristics: CCTV is associated with slowly sampled face ID trajectories with spatial resolution of approximately 20 meters, while telecom readings provide fast sampled phone ID trajectories with spatial uncertainty of a few hundred meters. The face or phone trajectory can be seen as an observation of the real trajectory of a moving pedestrian. It is useful to identify the correspondence between face and phone trajectories to reconstruct the trajectory of moving persons. To this end, we propose a complementarity-oriented feature fusion mechanism (COFFM) to model and utilize the common embedding and complementarity of these two measurement modalities. Specifically, a Cycle Heterogeneous Trajectory Translation Network (CCTTN) is proposed to realize a TFE (Trajectory Feature Extractor) which captures the latent transforming relationships between the face and phone modalities. The latent features from both transforming directions are concatenated in the Feature Unifying (FU) module and fed into a binary face-phone trajectory matching discriminator (FPTPMD) to infer whether a face-phone trajectory pair corresponds to the same underlying motion trajectory. We evaluated our method on a large real-world face-phone trajectory dataset and showed promising results with the accuracy of 97.1% which exceeds the comparable similarity-based methods. The developed principle and framework generalize well to other multi-modality trajectory matching tasks. |
| format | Article |
| id | doaj-art-a79700305687475d99fa3dc313e055f7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a79700305687475d99fa3dc313e055f72025-01-31T00:00:46ZengIEEEIEEE Access2169-35362025-01-0113179111791810.1109/ACCESS.2025.353110610844270Complementarity-Oriented Feature Fusion for Face-Phone Trajectory MatchingChangfeng Cao0https://orcid.org/0009-0005-4927-1850Wenchuan Zhang1https://orcid.org/0009-0002-2334-081XHua Yang2https://orcid.org/0000-0003-2179-5343Dan Ruan3https://orcid.org/0000-0003-3400-7684Department of Big Data and Computer Science, Guizhou Normal University, Guiyang, Guizhou, ChinaDepartment of Big Data and Computer Science, Guizhou Normal University, Guiyang, Guizhou, ChinaDepartment of Big Data and Computer Science, Guizhou Normal University, Guiyang, Guizhou, ChinaDepartment of Radiation Oncology, David Geffen School, University of California at Los Angeles, Los Angeles, CA, USACCTVs and telecom base stations act as sensors, and collect massive face and phone related data. When used for person localization and trajectory characterization, they each present quite different spatiotemporal characteristics: CCTV is associated with slowly sampled face ID trajectories with spatial resolution of approximately 20 meters, while telecom readings provide fast sampled phone ID trajectories with spatial uncertainty of a few hundred meters. The face or phone trajectory can be seen as an observation of the real trajectory of a moving pedestrian. It is useful to identify the correspondence between face and phone trajectories to reconstruct the trajectory of moving persons. To this end, we propose a complementarity-oriented feature fusion mechanism (COFFM) to model and utilize the common embedding and complementarity of these two measurement modalities. Specifically, a Cycle Heterogeneous Trajectory Translation Network (CCTTN) is proposed to realize a TFE (Trajectory Feature Extractor) which captures the latent transforming relationships between the face and phone modalities. The latent features from both transforming directions are concatenated in the Feature Unifying (FU) module and fed into a binary face-phone trajectory matching discriminator (FPTPMD) to infer whether a face-phone trajectory pair corresponds to the same underlying motion trajectory. We evaluated our method on a large real-world face-phone trajectory dataset and showed promising results with the accuracy of 97.1% which exceeds the comparable similarity-based methods. The developed principle and framework generalize well to other multi-modality trajectory matching tasks.https://ieeexplore.ieee.org/document/10844270/Multi-modality trajectory matchingfeature fusiontrajectory feature extractioncommon domain embeddingpedestrian trackingtrajectory reconstruction |
| spellingShingle | Changfeng Cao Wenchuan Zhang Hua Yang Dan Ruan Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching IEEE Access Multi-modality trajectory matching feature fusion trajectory feature extraction common domain embedding pedestrian tracking trajectory reconstruction |
| title | Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching |
| title_full | Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching |
| title_fullStr | Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching |
| title_full_unstemmed | Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching |
| title_short | Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching |
| title_sort | complementarity oriented feature fusion for face phone trajectory matching |
| topic | Multi-modality trajectory matching feature fusion trajectory feature extraction common domain embedding pedestrian tracking trajectory reconstruction |
| url | https://ieeexplore.ieee.org/document/10844270/ |
| work_keys_str_mv | AT changfengcao complementarityorientedfeaturefusionforfacephonetrajectorymatching AT wenchuanzhang complementarityorientedfeaturefusionforfacephonetrajectorymatching AT huayang complementarityorientedfeaturefusionforfacephonetrajectorymatching AT danruan complementarityorientedfeaturefusionforfacephonetrajectorymatching |