Vladimir Lebedev

Back to Home Screen

Product development & Implementation

Product development & Implementation

Functional Module: Computer Vision  for Loaders and Excavators work control

Functional Module: Computer Vision  for Loaders and Excavators work control

Budget: $100 000

Budget: $100 000

Timeline: 6 months

Timeline: 6 months

Scope & Objectives

Scope & Objectives

Scope & Objectives

In traditional fleet management system implementations, additional sensors were used to track operational cycles and technological processes. These sensors were typically installed on key machine components, such as the boom, arm, and bucket.

However, this approach lacks reliability, requires frequent maintenance, and is prone to failures, which negatively impacts the efficiency of the fleet management system.

I developed a computer vision-based solution that replaces these sensors with a camera installed in the operator’s cabin. This allows for automated tracking of work operations using machine vision algorithms. The solution is highly reliable and requires minimal maintenance, significantly improving the efficiency and sustainability of the fleet management system.

In traditional fleet management system implementations, additional sensors were used to track operational cycles and technological processes. These sensors were typically installed on key machine components, such as the boom, arm, and bucket.


However, this approach lacks reliability, requires frequent maintenance, and is prone to failures, which negatively impacts the efficiency of the fleet management system.


I developed a computer vision-based solution that replaces these sensors with a camera installed in the operator’s cabin. This allows for automated tracking

of work operations using machine vision algorithms. The solution is highly reliable and requires minimal maintenance, significantly improving the efficiency and sustainability of the fleet management system.

In traditional fleet management system implementations, additional sensors were used to track operational cycles and technological processes. These sensors were typically installed on key machine components, such as the boom, arm, and bucket.

However, this approach lacks reliability, requires frequent maintenance, and is prone to failures, which negatively impacts the efficiency of the fleet management system.

I developed a computer vision-based solution that replaces these sensors with a camera installed in the operator’s cabin. This allows for automated tracking of work operations using machine vision algorithms. The solution is highly reliable and requires minimal maintenance, significantly improving the efficiency and sustainability of the fleet management system.

I also have a publication on this topic, which I describe here

I also have a publication on this topic, which I describe here