Bij Vintecc zijn we altijd op zoek naar nieuw talent. Wil jij stage lopen bij Vintecc? We geven je graag de kans om praktijkervaring op te doen.

Internships VISION

Low-Latency Logging

Goals

Enable quick inter-process communication. This entails buffering for optimal packet size, buffering on communication interruptions, fallback paths, error handling, and so on.

Sensor Fusion

Goals

Map information from different sensors (visible light, ultra-violet, infra-red, radar, lidar) onto each other in 3 dimensions.

Compare early vs. late sensor fusion for deep learning on the calibrated input.

Learning Visual Embeddings

Goals

Object re-identification (re-ID).

Classification of new classes without retraining the whole network.

Keypoint Detection

Goals

The goal of this internship is to create a Python package that can effectively train and infer on COCO datasets with keypoint annotations.

GANs for Synthetic data

Goals

The goal of this internship is to create a data augmentation workflow that seamlessly plugs into an existing Python package. This package would enable us to easily create realistic-looking datasets, starting from synthetic data.

Copy-Paste Data Augmentation

Goals

The goal of this internship is to create a data augmentation workflow that seamlessly plugs into an existing Python package. This package would enable us to easily create new datasets using real or synthetic backgrounds or objects with their masks. It would also enable us to perform the augmentation on-the-fly, in the training phase of deep learning.

3D Deep learning on Point Clouds

Goals

The goal is to create a Python package that includes tools to work with (load & store / transform / sample from / visualize) 3D point clouds. These points could include coordinates, intensity, color, normal vectors, … They can be structured or unstructured.

Another important goal is to perform semantic/instance segmentation on those 3D point clouds directly.

 

Profile / required skills

Education: an industrial engineering informatics or computer science engineering student.

Being proficient with the Python programming language (and have experience with C/C++.)

Background knowledge about computer vision and practical experience with deep learning.

Internships Controls

Path planning and control of an articulated AGV

Goals

Develop and implement a motion algorithm to dynamically park a heavy duty articulated vehicle in a clustered environment.

Profile / required skills

This thesis is open to students with a natural interest in the development of autonomous vehicles, software development and mechatronic systems and control. Hence, a background in control engineering with an analytical background is required to pass this thesis.

Basic knowledge of Matlab/Simulink, Linux, python and ROS is a plus.

Online glass cutting optimization

Goals

The goal is to create new and alternative optimization methods to optimize the glass cutting. The student can implement one or multiple algorithms of choice. An initial algorithm has already been developed (based on dynamic programming), and can be used as a benchmark. Real-world tests will evaluate the performance of the developed algorithms.

Profile / required skills

Optimization theory, constraint problem solving

Programming languages: Python (object oriented), basic database knowledge

Internship Simulation

Tuning of physics parameters

Goals

The goal of this thesis is to research and develop best practices on how to tune a virtual physical simulation to a real counterpart. Ideally, this results in a methodology on how to approach the tuning task and various methods to (possibly) automate parts of this task (auto-tuning).

Profile / required skills

• Electromechanics / Mechanics / Control & Automation/…
• System identification / Control engineering /Modelling / Mechatronics/…
• Basic skills in programming and software development

 

Job student

Vintecc staat altijd open voor jobstudenten, zowel tijdens het jaar als in de zomer.

Stel je kandidaat via onderstaand formulier!