Skip to main content

Leverage computer vision and satellite imagery to detect illegal wild dumps


Ensure cleanliness of your municipality and protect biodiversity


Fight against illegal wild dump proliferation 


Facilitate cleaning interventions

With which tools?

  • With automated data collection and consolidation

    Thanks to several websites offer the opportunity to civilians to declare wild dumps they crossed. We regularly scrap them to obtain GPS coordinates of the reported wild dumps. Then, we download the corresponding Google Maps tiles and use them to train our models with accurate data.

  • With state of the art detection models

    Thanks to the use of state of the art detection models like YOLOv5 or EfficientDets to compute our results, as well as ensembling methods to further improve our results.

  • With ergonomic platform to showcase results and take actions

    Thanks to our computer vision platform provides an ergonomic map where all detections are displayed with bounding boxes. The user can see the objects he wants to detect, filter the results through a confidence threshold and also download the relevant data in csv format


Request a demo

Request a demo

*Required fields

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

Privacy Policy and Terms of Service apply.

Our publications


Boosting search engine capabilities of RegReview:…

RegReview is an AI solution for compliance teams, to automate regulatory monitoring and processes, which brings together several tools, the most essential of which is a search engine operating on a compiled database of custom-built regulatory sources.

The database contains ~300k documents.


Read more
Article title

Labeling text clusters with keywords

We propose to explore several keyword extraction techniques to label text clusters obtained after a Text Clustering or a Topic Modeling pipeline. This work is following our previous articles about Topic Modeling and Text Clustering (here and here).


Read more

Synthetic data or how to share sensitive data…

For a period of six months, 5 students from Centrale Supélec and ESSEC worked collaboratively with Sia Partners on building a Python library to create fake - which we'll call synthetic - data.
But what's the point of creating fake data? How could it help organizations?


Read more