[ Tech stack ]
YOLO
The reference model family for real-time object detection.
YOLO (You Only Look Once) is a family of real-time object detection models, whose Ultralytics models (YOLOv8, YOLO11, YOLO26) cover detection, segmentation, pose estimation, classification and tracking. A model trains on a custom dataset in a few lines of Python and exports to ONNX, TensorRT, CoreML or TFLite. It's our choice for detecting or tracking objects on a video feed, including on Jetson or mobile.
[ Why YOLO at Dexon ]
What this technology does well, and why we use it.
Typical usage: Detect, count and track objects on industrial, retail or drone video feeds.
- 01
Detection, segmentation, pose, classification and tracking in one API.
- 02
Custom-dataset training in a few lines of Python, pretrained models included.
- 03
ONNX, TensorRT, CoreML and TFLite export: edge deployment on Jetson and mobile.
- 04
Real-time on GPU and embedded alike; AGPL-3.0 or Ultralytics Enterprise license.
[ Complementary technologies ]
The building blocks we often mobilise alongside
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us
Discover what the business and tech press say about us. An outside reading of our work and our innovations.
