Skip to content

OrangeMold/SafeShift

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Inspiration

Having experiences in the workfield, one of our teammates was petrified by the alarming amount of overlooked security protocols that occur on a daily basis. The place was crawling with hand pallet trucks and forklifts, but they never suggested to his 16 year old self to wear steel-toe shoes. It is our duty as citizens of the world to ensure proper safety amongst all workers.

What it does

SafeShift is an advanced AI-powered system designed to detect workplace safety hazards in real-time. Our solution is fully customizable, allowing businesses to define specific safety requirements based on their industry needs. For smaller-scale companies, we offer a pre-configured version with built-in safety detections for essential protective gear, available at a more accessible rate. Whether it’s ensuring compliance with PPE regulations or identifying hazardous workplace behaviors, SafeShift provides a proactive approach to safety monitoring.

How we built it

We made an in-house machine learning algorithm and trained it on an extensive, open-source computer vision dataset. Our AI continuously improves through deep learning, ensuring accurate detection and adaptation to diverse workplace environments. It has over 3.6 million parameters.

Challenges we ran into

We were severely limited by time. Built under tight deadlines, we didn't have the resources to fully train our prototype model to its full capacity. Also, if given more time, we could train the same AI model to detect litter. This would add value by making our company more green and sustainable.

Accomplishments that we're proud of

Despite the constraints, our current model successfully detects essential PPE such as hard hats. This is just the beginning—our vision for workplace safety is clearer than ever, and we’re proud to have taken the first step toward revolutionizing safety monitoring through AI.

What we learned

Beyond technical development, we gained valuable insight into the entrepreneurial side of software engineering. Understanding profit margins, B2B partnerships, and real-world business strategies reshaped how we approach software development—not just as engineers but as innovators building a scalable and impactful solution.

What's next for SafeShift

Our goal is to integrate an expansive range of safety procedures into SafeShift. From construction sites to warehouses, factories, and beyond, we envision a future where workplace accidents become a thing of the past—because no one should have to compromise on safety.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages