All along rail roads, poles, which are supporting catenarys supplying electricity to TGVs (high speed trains), are being displaced. As part of a Testing, Inspection and Certification (TIC) assessment of such poles, Colas Rail partnered with Sicara in order to automatise one step of the project. Precisely, Colas Rail needs to get the new exact location of the rail poles on plan to then commission and direct work. We automatised the map layout in 3D generated by a LIDAR and then integrated it in a 2D software. It reduced the lead time from 15min to 45s.
Colas Rail handles railway infrastructure projects all over the world. Thanks to 80 years of expertise, Colas Rail offers solutions and products ranging from high-speed line tracks (LGV), network maintenance and urban transport (trams, metros).
Revenues in €
I enjoyed working working with Sicara as they are not only responsive, but also stimulating as they offer 'out of the box' solutions.
To represent 3D pieces of spatial data that allows to sample the surfaces and distances between catanarys, rails and poles, Colas Rail resorts to points clouds generated by laser scanners (LIDAR). Afterwards, to visualise this rail road environment in 3D, it takes 20min to load the plan, isolate the pole, and then generate its sections on a Colas Rail's in-house software. To speed up the generation while keeping its high-quality, Sicara relied on a web application automatisation.
Once the user selects the points of interest, the Python backend processed from 500,000 to 100,000,000 points to generate a 2D projection of the pole in a few seconds. Sicara then relies on a convolution filter to spot the pattern of the pole and automatise the key measurements of the 2D plan. The 2D projection is then sent back to the user who can open it and use it on its in-house software.
Related articles written by Sicara data scientists
GAN with Keras: Application to Image Deblurring
A Generative Adversarial Networks tutorial applied to Image Deblurring with the Keras library.
Set up TensorFlow with Docker + GPU in Minutes
Why Docker is the best platform to use Tensorflow with a GPU.
Edge Detection in Opencv 4.0, A 15 Minutes Tutorial
This tutorial will teach you, with examples, two OpenCV techniques in python to deal with edge detection.