

Ladder Walking Detection via Action Recognition for Enhancing Worker Safety in Construction
The integration of AI and human-centered technologies has opened new avenues for improving workplace safety, particularly in high-risk environments such as construction sites.
Ladder-related accidents, often caused by improper body posture or unsafe practices, remain a significant concern.
These practices commonly adopted by blue-collar workers attempting to save time during finishing tasks at height are among the most frequent unsafe practices on construction sites.
They significantly increase the risk of falls, and research indicates that even falls from relatively low heights are the leading cause of injury among construction workers. Such behaviors may result in falls from height, and research shows that falls from relatively low heights are the most common cause of injuries among construction workers.
Due to the limited availability of real-world ladder-walking data and the challenges of safely simulating such behaviors, we curated a dataset from YouTube videos, which, while not ideal for direct safety guidance, provides valuable insights into ladder-walking techniques.
Using the MMAction2 framework, we propose a comprehensive methodology that involves experimenting with multiple state-of-the-art models, selected for their effectiveness in recognizing human motion and detecting safety-critical actions in workplace environments (e.g., Temporal Segment Networks and SlowFast), optimizing hyperparameters, and evaluating performance using metrics such as accuracy.
Our approach leverages action recognition to enable real-time detection of unsafe ladder behaviors, thereby reducing the risk of accidents in hazardous construction environments. This work enhances construction safety by providing a scalable, automated solution for hazard mitigation.
Additionally, it highlights the broader potential of AI technologies in occupational health monitoring and risk prevention within the construction industry.
SMART Work Design and Modern Sociotechnical Theory. A marriage made in heaven?
SEISMEC Online Workshop: Human Centric Industry 5.0 – Concepts and Solutions.
Watch the full recording and follow our journey!
Can you bring the HR professional into dialogue with the organisational designer?
SEISMEC Newswave Issue #2 (Autumn 2024)
Flyer
Trifold Brochure
Rollup
Enhanced Defect Detection in Airport Runway Infrastructure Using Image-Text Pairing
SEISMEC Newswave Issue #1 (Summer 2024)
08/07/2024
A Framework for Vision-Based 3D Inspections for Maintenance Activities and Digital Twin Integration
A Conceptual Framework for Workforce Skills for Industry 5.0: Implications for Research, Policy and Practice
CAPS Self assessment: Aiming for Human- centricity through CAPS
Official slide deck
Piloting the shift to human-centric industry – SEISMEC advocates for a multidimensional transformation that hinges on fair and trustworthy technology, ethical incentives, capacity building and democratisation as key enablers to fundamentally change the way workers see themselves and are seen within their organisations.
Reviewing workplace innovation as a plea for a practical approach
Connecting the SMART work design approach to sociotechnical design principles
First press release
Ladder Walking Detection via Action Recognition for Enhancing Worker Safety in Construction
The integration of AI and human-centered technologies has opened new avenues for improving workplace safety, particularly in high-risk environments such as construction sites.
Ladder-related accidents, often caused by improper body posture or unsafe practices, remain a significant concern.
These practices commonly adopted by blue-collar workers attempting to save time during finishing tasks at height are among the most frequent unsafe practices on construction sites.
They significantly increase the risk of falls, and research indicates that even falls from relatively low heights are the leading cause of injury among construction workers. Such behaviors may result in falls from height, and research shows that falls from relatively low heights are the most common cause of injuries among construction workers.
Due to the limited availability of real-world ladder-walking data and the challenges of safely simulating such behaviors, we curated a dataset from YouTube videos, which, while not ideal for direct safety guidance, provides valuable insights into ladder-walking techniques.
Using the MMAction2 framework, we propose a comprehensive methodology that involves experimenting with multiple state-of-the-art models, selected for their effectiveness in recognizing human motion and detecting safety-critical actions in workplace environments (e.g., Temporal Segment Networks and SlowFast), optimizing hyperparameters, and evaluating performance using metrics such as accuracy.
Our approach leverages action recognition to enable real-time detection of unsafe ladder behaviors, thereby reducing the risk of accidents in hazardous construction environments. This work enhances construction safety by providing a scalable, automated solution for hazard mitigation.
Additionally, it highlights the broader potential of AI technologies in occupational health monitoring and risk prevention within the construction industry.
SMART Work Design and Modern Sociotechnical Theory. A marriage made in heaven?
SEISMEC Online Workshop: Human Centric Industry 5.0 – Concepts and Solutions.
Watch the full recording and follow our journey!
Can you bring the HR professional into dialogue with the organisational designer?
SEISMEC Newswave Issue #2 (Autumn 2024)
Flyer
Trifold Brochure
Rollup
Enhanced Defect Detection in Airport Runway Infrastructure Using Image-Text Pairing
SEISMEC Newswave Issue #1 (Summer 2024)
08/07/2024
A Framework for Vision-Based 3D Inspections for Maintenance Activities and Digital Twin Integration
A Conceptual Framework for Workforce Skills for Industry 5.0: Implications for Research, Policy and Practice
CAPS Self assessment: Aiming for Human- centricity through CAPS
Official slide deck
Piloting the shift to human-centric industry – SEISMEC advocates for a multidimensional transformation that hinges on fair and trustworthy technology, ethical incentives, capacity building and democratisation as key enablers to fundamentally change the way workers see themselves and are seen within their organisations.
Reviewing workplace innovation as a plea for a practical approach
Connecting the SMART work design approach to sociotechnical design principles
First press release
15/10/2024
Flyer
Rollup
Trifold Brochure
Official slide deck
Piloting the shift to human-centric industry – SEISMEC advocates for a multidimensional transformation that hinges on fair and trustworthy technology, ethical incentives, capacity building and democratisation as key enablers to fundamentally change the way workers see themselves and are seen within their organisations.
First press release
Ladder Walking Detection via Action Recognition for Enhancing Worker Safety in Construction
The integration of AI and human-centered technologies has opened new avenues for improving workplace safety, particularly in high-risk environments such as construction sites.
Ladder-related accidents, often caused by improper body posture or unsafe practices, remain a significant concern.
These practices commonly adopted by blue-collar workers attempting to save time during finishing tasks at height are among the most frequent unsafe practices on construction sites.
They significantly increase the risk of falls, and research indicates that even falls from relatively low heights are the leading cause of injury among construction workers. Such behaviors may result in falls from height, and research shows that falls from relatively low heights are the most common cause of injuries among construction workers.
Due to the limited availability of real-world ladder-walking data and the challenges of safely simulating such behaviors, we curated a dataset from YouTube videos, which, while not ideal for direct safety guidance, provides valuable insights into ladder-walking techniques.
Using the MMAction2 framework, we propose a comprehensive methodology that involves experimenting with multiple state-of-the-art models, selected for their effectiveness in recognizing human motion and detecting safety-critical actions in workplace environments (e.g., Temporal Segment Networks and SlowFast), optimizing hyperparameters, and evaluating performance using metrics such as accuracy.
Our approach leverages action recognition to enable real-time detection of unsafe ladder behaviors, thereby reducing the risk of accidents in hazardous construction environments. This work enhances construction safety by providing a scalable, automated solution for hazard mitigation.
Additionally, it highlights the broader potential of AI technologies in occupational health monitoring and risk prevention within the construction industry.
SMART Work Design and Modern Sociotechnical Theory. A marriage made in heaven?
Can you bring the HR professional into dialogue with the organisational designer?
Enhanced Defect Detection in Airport Runway Infrastructure Using Image-Text Pairing
08/07/2024
A Framework for Vision-Based 3D Inspections for Maintenance Activities and Digital Twin Integration
A Conceptual Framework for Workforce Skills for Industry 5.0: Implications for Research, Policy and Practice
CAPS Self assessment: Aiming for Human- centricity through CAPS
Reviewing workplace innovation as a plea for a practical approach
Connecting the SMART work design approach to sociotechnical design principles
19/06/2025
SEISMEC Newswave Issue #3 (June 2025)
SEISMEC Newswave Issue #2 (Autumn 2024)
SEISMEC Newswave Issue #1 (Summer 2024)
Inaugural issue of SEISMEC’s Newswave, our official project newsletter.
SEISMEC Online Workshop: Human Centric Industry 5.0 – Concepts and Solutions.
Watch the full recording and follow our journey!
First press release
Official slide deck
Piloting the shift to human-centric industry – SEISMEC advocates for a multidimensional transformation that hinges on fair and trustworthy technology, ethical incentives, capacity building and democratisation as key enablers to fundamentally change the way workers see themselves and are seen within their organisations.