Beyond Human Detection: A Benchmark for Detecting Common Human Posture
Human detection is the task of locating all instances of human beings present in an image, which has a wide range of applications across various fields, including search and rescue, surveillance, and autonomous driving. The rapid advancement of computer vision and deep learning technologies has brou...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8061 |
| _version_ | 1797575201348648960 |
|---|---|
| author | Yongxin Li You Wu Xiaoting Chen Han Chen Depeng Kong Haihua Tang Shuiwang Li |
| author_facet | Yongxin Li You Wu Xiaoting Chen Han Chen Depeng Kong Haihua Tang Shuiwang Li |
| author_sort | Yongxin Li |
| collection | DOAJ |
| description | Human detection is the task of locating all instances of human beings present in an image, which has a wide range of applications across various fields, including search and rescue, surveillance, and autonomous driving. The rapid advancement of computer vision and deep learning technologies has brought significant improvements in human detection. However, for more advanced applications like healthcare, human–computer interaction, and scene understanding, it is crucial to obtain information beyond just the localization of humans. These applications require a deeper understanding of human behavior and state to enable effective and safe interactions with humans and the environment. This study presents a comprehensive benchmark, the Common Human Postures (CHP) dataset, aimed at promoting a more informative and more encouraging task beyond mere human detection. The benchmark dataset comprises a diverse collection of images, featuring individuals in different environments, clothing, and occlusions, performing a wide range of postures and activities. The benchmark aims to enhance research in this challenging task by designing novel and precise methods specifically for it. The CHP dataset consists of 5250 human images collected from different scenes, annotated with bounding boxes for seven common human poses. Using this well-annotated dataset, we have developed two baseline detectors, namely CHP-YOLOF and CHP-YOLOX, building upon two identity-preserved human posture detectors: IPH-YOLOF and IPH-YOLOX. We evaluate the performance of these baseline detectors through extensive experiments. The results demonstrate that these baseline detectors effectively detect human postures on the CHP dataset. By releasing the CHP dataset, we aim to facilitate further research on human pose estimation and to attract more researchers to focus on this challenging task. |
| first_indexed | 2024-03-10T21:36:21Z |
| format | Article |
| id | doaj.art-feedc853772943dbbac4f84d2e0ef067 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:36:21Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-feedc853772943dbbac4f84d2e0ef0672023-11-19T15:02:10ZengMDPI AGSensors1424-82202023-09-012319806110.3390/s23198061Beyond Human Detection: A Benchmark for Detecting Common Human PostureYongxin Li0You Wu1Xiaoting Chen2Han Chen3Depeng Kong4Haihua Tang5Shuiwang Li6Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaHuman detection is the task of locating all instances of human beings present in an image, which has a wide range of applications across various fields, including search and rescue, surveillance, and autonomous driving. The rapid advancement of computer vision and deep learning technologies has brought significant improvements in human detection. However, for more advanced applications like healthcare, human–computer interaction, and scene understanding, it is crucial to obtain information beyond just the localization of humans. These applications require a deeper understanding of human behavior and state to enable effective and safe interactions with humans and the environment. This study presents a comprehensive benchmark, the Common Human Postures (CHP) dataset, aimed at promoting a more informative and more encouraging task beyond mere human detection. The benchmark dataset comprises a diverse collection of images, featuring individuals in different environments, clothing, and occlusions, performing a wide range of postures and activities. The benchmark aims to enhance research in this challenging task by designing novel and precise methods specifically for it. The CHP dataset consists of 5250 human images collected from different scenes, annotated with bounding boxes for seven common human poses. Using this well-annotated dataset, we have developed two baseline detectors, namely CHP-YOLOF and CHP-YOLOX, building upon two identity-preserved human posture detectors: IPH-YOLOF and IPH-YOLOX. We evaluate the performance of these baseline detectors through extensive experiments. The results demonstrate that these baseline detectors effectively detect human postures on the CHP dataset. By releasing the CHP dataset, we aim to facilitate further research on human pose estimation and to attract more researchers to focus on this challenging task.https://www.mdpi.com/1424-8220/23/19/8061human detectioncommon human posture detectionCHP datasetbenchmark |
| spellingShingle | Yongxin Li You Wu Xiaoting Chen Han Chen Depeng Kong Haihua Tang Shuiwang Li Beyond Human Detection: A Benchmark for Detecting Common Human Posture Sensors human detection common human posture detection CHP dataset benchmark |
| title | Beyond Human Detection: A Benchmark for Detecting Common Human Posture |
| title_full | Beyond Human Detection: A Benchmark for Detecting Common Human Posture |
| title_fullStr | Beyond Human Detection: A Benchmark for Detecting Common Human Posture |
| title_full_unstemmed | Beyond Human Detection: A Benchmark for Detecting Common Human Posture |
| title_short | Beyond Human Detection: A Benchmark for Detecting Common Human Posture |
| title_sort | beyond human detection a benchmark for detecting common human posture |
| topic | human detection common human posture detection CHP dataset benchmark |
| url | https://www.mdpi.com/1424-8220/23/19/8061 |
| work_keys_str_mv | AT yongxinli beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT youwu beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT xiaotingchen beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT hanchen beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT depengkong beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT haihuatang beyondhumandetectionabenchmarkfordetectingcommonhumanposture AT shuiwangli beyondhumandetectionabenchmarkfordetectingcommonhumanposture |