A Comparison Study of Person Identification Using IR Array Sensors and LiDAR
Person identification is a critical task in applications such as security and surveillance, requiring reliable systems that perform robustly under diverse conditions. This study evaluates the Vision Transformer (ViT) and ResNet34 models across three modalities—RGB, thermal, and depth—using datasets...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548935629373440 |
|---|---|
| author | Kai Liu Mondher Bouazizi Zelin Xing Tomoaki Ohtsuki |
| author_facet | Kai Liu Mondher Bouazizi Zelin Xing Tomoaki Ohtsuki |
| author_sort | Kai Liu |
| collection | DOAJ |
| description | Person identification is a critical task in applications such as security and surveillance, requiring reliable systems that perform robustly under diverse conditions. This study evaluates the Vision Transformer (ViT) and ResNet34 models across three modalities—RGB, thermal, and depth—using datasets collected with infrared array sensors and LiDAR sensors in controlled scenarios and varying resolutions (16 × 12 to 640 × 480) to explore their effectiveness in person identification. Preprocessing techniques, including YOLO-based cropping, were employed to improve subject isolation. Results show a similar identification performance between the three modalities, in particular in high resolution (i.e., 640 × 480), with RGB image classification reaching 100.0%, depth images reaching 99.54% and thermal images reaching 97.93%. However, upon deeper investigation, thermal images show more robustness and generalizability by maintaining focus on subject-specific features even at low resolutions. In contrast, RGB data performs well at high resolutions but exhibits reliance on background features as resolution decreases. Depth data shows significant degradation at lower resolutions, suffering from scattered attention and artifacts. These findings highlight the importance of modality selection, with thermal imaging emerging as the most reliable. Future work will explore multi-modal integration, advanced preprocessing, and hybrid architectures to enhance model adaptability and address current limitations. This study highlights the potential of thermal imaging and the need for modality-specific strategies in designing robust person identification systems. |
| format | Article |
| id | doaj-art-9593e19ca51a4ece95bbcedbf22dbb49 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-9593e19ca51a4ece95bbcedbf22dbb492025-01-10T13:21:25ZengMDPI AGSensors1424-82202025-01-0125127110.3390/s25010271A Comparison Study of Person Identification Using IR Array Sensors and LiDARKai Liu0Mondher Bouazizi1Zelin Xing2Tomoaki Ohtsuki3Graduate School of Science and Technology, Keio University, Yokohama 223-8522, JapanFaculty of Science and Technology, Keio University, Yokohama 223-8522, JapanGraduate School of Science and Technology, Keio University, Yokohama 223-8522, JapanFaculty of Science and Technology, Keio University, Yokohama 223-8522, JapanPerson identification is a critical task in applications such as security and surveillance, requiring reliable systems that perform robustly under diverse conditions. This study evaluates the Vision Transformer (ViT) and ResNet34 models across three modalities—RGB, thermal, and depth—using datasets collected with infrared array sensors and LiDAR sensors in controlled scenarios and varying resolutions (16 × 12 to 640 × 480) to explore their effectiveness in person identification. Preprocessing techniques, including YOLO-based cropping, were employed to improve subject isolation. Results show a similar identification performance between the three modalities, in particular in high resolution (i.e., 640 × 480), with RGB image classification reaching 100.0%, depth images reaching 99.54% and thermal images reaching 97.93%. However, upon deeper investigation, thermal images show more robustness and generalizability by maintaining focus on subject-specific features even at low resolutions. In contrast, RGB data performs well at high resolutions but exhibits reliance on background features as resolution decreases. Depth data shows significant degradation at lower resolutions, suffering from scattered attention and artifacts. These findings highlight the importance of modality selection, with thermal imaging emerging as the most reliable. Future work will explore multi-modal integration, advanced preprocessing, and hybrid architectures to enhance model adaptability and address current limitations. This study highlights the potential of thermal imaging and the need for modality-specific strategies in designing robust person identification systems.https://www.mdpi.com/1424-8220/25/1/271person identificationdeep learningIR array sensorLiDAR |
| spellingShingle | Kai Liu Mondher Bouazizi Zelin Xing Tomoaki Ohtsuki A Comparison Study of Person Identification Using IR Array Sensors and LiDAR Sensors person identification deep learning IR array sensor LiDAR |
| title | A Comparison Study of Person Identification Using IR Array Sensors and LiDAR |
| title_full | A Comparison Study of Person Identification Using IR Array Sensors and LiDAR |
| title_fullStr | A Comparison Study of Person Identification Using IR Array Sensors and LiDAR |
| title_full_unstemmed | A Comparison Study of Person Identification Using IR Array Sensors and LiDAR |
| title_short | A Comparison Study of Person Identification Using IR Array Sensors and LiDAR |
| title_sort | comparison study of person identification using ir array sensors and lidar |
| topic | person identification deep learning IR array sensor LiDAR |
| url | https://www.mdpi.com/1424-8220/25/1/271 |
| work_keys_str_mv | AT kailiu acomparisonstudyofpersonidentificationusingirarraysensorsandlidar AT mondherbouazizi acomparisonstudyofpersonidentificationusingirarraysensorsandlidar AT zelinxing acomparisonstudyofpersonidentificationusingirarraysensorsandlidar AT tomoakiohtsuki acomparisonstudyofpersonidentificationusingirarraysensorsandlidar AT kailiu comparisonstudyofpersonidentificationusingirarraysensorsandlidar AT mondherbouazizi comparisonstudyofpersonidentificationusingirarraysensorsandlidar AT zelinxing comparisonstudyofpersonidentificationusingirarraysensorsandlidar AT tomoakiohtsuki comparisonstudyofpersonidentificationusingirarraysensorsandlidar |