Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark
Human pose estimation has a variety of real-life applications, including human action recognition, AI-powered personal trainers, robotics, motion capture and augmented reality, gaming, and video surveillance. However, most current human pose estimation systems are based on RGB images, which do not s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/92 |
| _version_ | 1797439769021513728 |
|---|---|
| author | Yongping Guo Ying Chen Jianzhi Deng Shuiwang Li Hui Zhou |
| author_facet | Yongping Guo Ying Chen Jianzhi Deng Shuiwang Li Hui Zhou |
| author_sort | Yongping Guo |
| collection | DOAJ |
| description | Human pose estimation has a variety of real-life applications, including human action recognition, AI-powered personal trainers, robotics, motion capture and augmented reality, gaming, and video surveillance. However, most current human pose estimation systems are based on RGB images, which do not seriously take into account personal privacy. Although identity-preserved algorithms are very desirable when human pose estimation is applied to scenarios where personal privacy does matter, developing human pose estimation algorithms based on identity-preserved modalities, such as thermal images concerned here, is very challenging due to the limited amount of training data currently available and the fact that infrared thermal images, unlike RGB images, lack rich texture cues which makes annotating training data itself impractical. In this paper, we formulate a new task with privacy protection that lies between human detection and human pose estimation by introducing a benchmark for IPHPDT (i.e., Identity-Preserved Human Posture Detection in Thermal images). This task has a threefold novel purpose: the first is to establish an identity-preserved task with thermal images; the second is to achieve more information other than the location of persons as provided by human detection for more advanced computer vision applications; the third is to avoid difficulties in collecting well-annotated data for human pose estimation in thermal images. The presented IPHPDT dataset contains four types of human postures, consisting of 75,000 images well-annotated with axis-aligned bounding boxes and postures of the persons. Based on this well-annotated IPHPDT dataset and three state-of-the-art algorithms, i.e., YOLOF (short for You Only Look One-level Feature), YOLOX (short for Exceeding YOLO Series in 2021) and TOOD (short for Task-aligned One-stage Object Detection), we establish three baseline detectors, called IPH-YOLOF, IPH-YOLOX, and IPH-TOOD. In the experiments, three baseline detectors are used to recognize four infrared human postures, and the mean average precision can reach 70.4%. The results show that the three baseline detectors can effectively perform accurate posture detection on the IPHPDT dataset. By releasing IPHPDT, we expect to encourage more future studies into human posture detection in infrared thermal images and draw more attention to this challenging task. |
| first_indexed | 2024-03-09T11:57:53Z |
| format | Article |
| id | doaj.art-b72a4f349302459682160b4469be7189 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:57:53Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b72a4f349302459682160b4469be71892023-11-30T23:07:17ZengMDPI AGSensors1424-82202022-12-012319210.3390/s23010092Identity-Preserved Human Posture Detection in Infrared Thermal Images: A BenchmarkYongping Guo0Ying Chen1Jianzhi Deng2Shuiwang Li3Hui Zhou4Guangxi 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 pose estimation has a variety of real-life applications, including human action recognition, AI-powered personal trainers, robotics, motion capture and augmented reality, gaming, and video surveillance. However, most current human pose estimation systems are based on RGB images, which do not seriously take into account personal privacy. Although identity-preserved algorithms are very desirable when human pose estimation is applied to scenarios where personal privacy does matter, developing human pose estimation algorithms based on identity-preserved modalities, such as thermal images concerned here, is very challenging due to the limited amount of training data currently available and the fact that infrared thermal images, unlike RGB images, lack rich texture cues which makes annotating training data itself impractical. In this paper, we formulate a new task with privacy protection that lies between human detection and human pose estimation by introducing a benchmark for IPHPDT (i.e., Identity-Preserved Human Posture Detection in Thermal images). This task has a threefold novel purpose: the first is to establish an identity-preserved task with thermal images; the second is to achieve more information other than the location of persons as provided by human detection for more advanced computer vision applications; the third is to avoid difficulties in collecting well-annotated data for human pose estimation in thermal images. The presented IPHPDT dataset contains four types of human postures, consisting of 75,000 images well-annotated with axis-aligned bounding boxes and postures of the persons. Based on this well-annotated IPHPDT dataset and three state-of-the-art algorithms, i.e., YOLOF (short for You Only Look One-level Feature), YOLOX (short for Exceeding YOLO Series in 2021) and TOOD (short for Task-aligned One-stage Object Detection), we establish three baseline detectors, called IPH-YOLOF, IPH-YOLOX, and IPH-TOOD. In the experiments, three baseline detectors are used to recognize four infrared human postures, and the mean average precision can reach 70.4%. The results show that the three baseline detectors can effectively perform accurate posture detection on the IPHPDT dataset. By releasing IPHPDT, we expect to encourage more future studies into human posture detection in infrared thermal images and draw more attention to this challenging task.https://www.mdpi.com/1424-8220/23/1/92identity-preservedhuman detectioninfrared thermal imageshuman posture detectionbenchmarkIPHPDT dataset |
| spellingShingle | Yongping Guo Ying Chen Jianzhi Deng Shuiwang Li Hui Zhou Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark Sensors identity-preserved human detection infrared thermal images human posture detection benchmark IPHPDT dataset |
| title | Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark |
| title_full | Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark |
| title_fullStr | Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark |
| title_full_unstemmed | Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark |
| title_short | Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark |
| title_sort | identity preserved human posture detection in infrared thermal images a benchmark |
| topic | identity-preserved human detection infrared thermal images human posture detection benchmark IPHPDT dataset |
| url | https://www.mdpi.com/1424-8220/23/1/92 |
| work_keys_str_mv | AT yongpingguo identitypreservedhumanposturedetectionininfraredthermalimagesabenchmark AT yingchen identitypreservedhumanposturedetectionininfraredthermalimagesabenchmark AT jianzhideng identitypreservedhumanposturedetectionininfraredthermalimagesabenchmark AT shuiwangli identitypreservedhumanposturedetectionininfraredthermalimagesabenchmark AT huizhou identitypreservedhumanposturedetectionininfraredthermalimagesabenchmark |