FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety
Video face detection is a crucial first step in many facial recognition and face analysis systems. It should serve postprocessing steps as much as possible while satisfying high-accuracy real-time detection. In this paper, we first introduce the constrained aspect ratio loss (CARLoss) for better fac...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2022/8355174 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563120916135936 |
|---|---|
| author | Yue Wang Liang Hong Dewen Gu Pingping Fu |
| author_facet | Yue Wang Liang Hong Dewen Gu Pingping Fu |
| author_sort | Yue Wang |
| collection | DOAJ |
| description | Video face detection is a crucial first step in many facial recognition and face analysis systems. It should serve postprocessing steps as much as possible while satisfying high-accuracy real-time detection. In this paper, we first introduce the constrained aspect ratio loss (CARLoss) for better facial boxes regression and incorporate it into the modified FH-YOLOv4, then the IoU Tracker-based video face image deduplication algorithm is proposed on the detection level. Extensive experiments and comparative tests show the effectiveness of our method. |
| format | Article |
| id | doaj-art-e22c5924ab604d14a3b73c13c5a702d4 |
| institution | Kabale University |
| issn | 1607-887X |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-e22c5924ab604d14a3b73c13c5a702d42025-02-03T01:21:03ZengWileyDiscrete Dynamics in Nature and Society1607-887X2022-01-01202210.1155/2022/8355174FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public SafetyYue Wang0Liang Hong1Dewen Gu2Pingping Fu3School of ManagementSchool of ManagementSchool of ManagementSchool of ManagementVideo face detection is a crucial first step in many facial recognition and face analysis systems. It should serve postprocessing steps as much as possible while satisfying high-accuracy real-time detection. In this paper, we first introduce the constrained aspect ratio loss (CARLoss) for better facial boxes regression and incorporate it into the modified FH-YOLOv4, then the IoU Tracker-based video face image deduplication algorithm is proposed on the detection level. Extensive experiments and comparative tests show the effectiveness of our method.http://dx.doi.org/10.1155/2022/8355174 |
| spellingShingle | Yue Wang Liang Hong Dewen Gu Pingping Fu FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety Discrete Dynamics in Nature and Society |
| title | FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety |
| title_full | FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety |
| title_fullStr | FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety |
| title_full_unstemmed | FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety |
| title_short | FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety |
| title_sort | fh yolov4 with constrained aspect ratio loss for video face detection and public safety |
| url | http://dx.doi.org/10.1155/2022/8355174 |
| work_keys_str_mv | AT yuewang fhyolov4withconstrainedaspectratiolossforvideofacedetectionandpublicsafety AT lianghong fhyolov4withconstrainedaspectratiolossforvideofacedetectionandpublicsafety AT dewengu fhyolov4withconstrainedaspectratiolossforvideofacedetectionandpublicsafety AT pingpingfu fhyolov4withconstrainedaspectratiolossforvideofacedetectionandpublicsafety |