Contact Us

Computer vision

""

We are a team passionate about technology and Computer Vision methods.

The Lab's missions

To develop solutions at the cutting edge of innovation, we work on a technology watch, the implementation of new algorithms via concrete use cases and the evaluation of their results.

From the processing of images (especially satellite images) and pre-processed videos, our Computer Vision laboratory has been able to provide innovative answers to several problems such as classification, detection, ensembling, and visualization.

Our research topics

Classification

Scan an area and estimate the photovoltaic potential of the buildings in it. This is done by associating the results of a detection with the solar radiation data available on the Indrabot.

Detection

A pipeline for detecting car breakdowns. By combining advanced detection algorithms based on deep learning (YOLOv5, EfficientDet...) and more classical approaches (morphological transforms, Hough transform...)

Ensembling

Improve our performance on wild deposit detection by developing ensembling methods (AND, OR, WBF, etc.)

Visualisation

Challenge Everest, which objective was to detect dangerous positions on the ski lifts of a ski resort from video files.

NOS SOLUTIONS D'IA AU SERVICE DE LA Computer vision

Our publications

Ai Abstract Art

Decentralized Physical Infrastructure Network: a…

DePINs, short for Decentralized Physical Infrastructure Networks, refer to physical infrastructure networks managed on a decentralized basis.
Unlike traditional systems based on centralized management by large groups, DePINs involve operation by individuals or small groups.

2024

Read more
Abstract AI Representation Purple

SiaGPT for ESG

In order to promote sustainability and responsible development, respecting ESG criterias to regulate a company's impact on the environment, society and governance has become essential.

2024

Read more
OpenStreetMap from Heka

OpenStreetMap: Using open data and guaranteeing …

In this article, we explore the use of OpenStreetMap for extracting geospatial data and implementing an approach to enhance the overall data quality. We delve into the key steps of data extraction including selecting the area of interest, data collection, cleaning, and preparing data for future use.

2024

Read more
See our publications

Contact us

*Required fields

This site is protected by reCAPTCHA and by the Google system.

Privacy Policy and Terms of Service apply.