Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI
This study evaluates the performance of You Only Look Once version 8 (YOLOv8) and a SAM-based unified and robust zero-shot visual tracker with motion-aware instance-level memory (SAMURAI) for worker detection in masonry construction environments under varying occlusion conditions. Computer vision-ba...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/7/3991 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849730863656337408 |
|---|---|
| author | Seonjun Yoon Hyunsoo Kim |
| author_facet | Seonjun Yoon Hyunsoo Kim |
| author_sort | Seonjun Yoon |
| collection | DOAJ |
| description | This study evaluates the performance of You Only Look Once version 8 (YOLOv8) and a SAM-based unified and robust zero-shot visual tracker with motion-aware instance-level memory (SAMURAI) for worker detection in masonry construction environments under varying occlusion conditions. Computer vision-based monitoring systems are widely used in construction, but traditional object detection models struggle with occlusion, limiting their effectiveness in real-world applications. The research employed a structured experimental framework to assess both models in brick transportation and brick laying tasks across three occlusion levels: non-occlusion, partial occlusion, and severe occlusion. Results demonstrate that while YOLOv8 processes frames 2.5 to 3.5 times faster (28–32 FPS versus 9–12 FPS), SAMURAI maintains significantly higher detection accuracy, particularly under severe occlusion conditions (92.67% versus 52.67%). YOLOv8’s frame-by-frame processing results in substantial performance degradation as occlusion severity increases, whereas SAMURAI’s memory-based tracking mechanism enables persistent worker identification across frames. This comparative analysis provides valuable insights for selecting appropriate monitoring technologies based on specific construction site requirements. YOLOv8 is suitable for construction environments characterized by minimal occlusions and a high demand for real-time detection, whereas SAMURAI is more applicable to scenarios with frequent and severe occlusions that require the sustained tracking of worker activity. The selection of an appropriate model should be based on an initial assessment of environmental factors such as layout complexity, object density, and expected occlusion frequency. The findings contribute to the advancement of more reliable vision-based monitoring systems for enhancing productivity assessment and safety management in dynamic construction settings. |
| format | Article |
| id | doaj-art-e826eb1788e141fba9ab09c0086122a8 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e826eb1788e141fba9ab09c0086122a82025-08-20T03:08:44ZengMDPI AGApplied Sciences2076-34172025-04-01157399110.3390/app15073991Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAISeonjun Yoon0Hyunsoo Kim1Department of Architectural Engineering, Dankook University, 152 Jukjeon-ro, Suji-gu, Yongin-si 16890, Gyeonggi-do, Republic of KoreaDepartment of Architectural Engineering, Dankook University, 152 Jukjeon-ro, Suji-gu, Yongin-si 16890, Gyeonggi-do, Republic of KoreaThis study evaluates the performance of You Only Look Once version 8 (YOLOv8) and a SAM-based unified and robust zero-shot visual tracker with motion-aware instance-level memory (SAMURAI) for worker detection in masonry construction environments under varying occlusion conditions. Computer vision-based monitoring systems are widely used in construction, but traditional object detection models struggle with occlusion, limiting their effectiveness in real-world applications. The research employed a structured experimental framework to assess both models in brick transportation and brick laying tasks across three occlusion levels: non-occlusion, partial occlusion, and severe occlusion. Results demonstrate that while YOLOv8 processes frames 2.5 to 3.5 times faster (28–32 FPS versus 9–12 FPS), SAMURAI maintains significantly higher detection accuracy, particularly under severe occlusion conditions (92.67% versus 52.67%). YOLOv8’s frame-by-frame processing results in substantial performance degradation as occlusion severity increases, whereas SAMURAI’s memory-based tracking mechanism enables persistent worker identification across frames. This comparative analysis provides valuable insights for selecting appropriate monitoring technologies based on specific construction site requirements. YOLOv8 is suitable for construction environments characterized by minimal occlusions and a high demand for real-time detection, whereas SAMURAI is more applicable to scenarios with frequent and severe occlusions that require the sustained tracking of worker activity. The selection of an appropriate model should be based on an initial assessment of environmental factors such as layout complexity, object density, and expected occlusion frequency. The findings contribute to the advancement of more reliable vision-based monitoring systems for enhancing productivity assessment and safety management in dynamic construction settings.https://www.mdpi.com/2076-3417/15/7/3991masonry workmonitoringYOLOv8 computer vision modelSAMURAI computer vision model |
| spellingShingle | Seonjun Yoon Hyunsoo Kim Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI Applied Sciences masonry work monitoring YOLOv8 computer vision model SAMURAI computer vision model |
| title | Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI |
| title_full | Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI |
| title_fullStr | Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI |
| title_full_unstemmed | Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI |
| title_short | Occlusion-Aware Worker Detection in Masonry Work: Performance Evaluation of YOLOv8 and SAMURAI |
| title_sort | occlusion aware worker detection in masonry work performance evaluation of yolov8 and samurai |
| topic | masonry work monitoring YOLOv8 computer vision model SAMURAI computer vision model |
| url | https://www.mdpi.com/2076-3417/15/7/3991 |
| work_keys_str_mv | AT seonjunyoon occlusionawareworkerdetectioninmasonryworkperformanceevaluationofyolov8andsamurai AT hyunsookim occlusionawareworkerdetectioninmasonryworkperformanceevaluationofyolov8andsamurai |