Deploying Computer Vision Algorithms on Embedded Devices
The mission of NAVER LABS Europe is to advance the state-of-the-art in Ambient Intelligence including autonomous vehicles, artificial intelligence, 3D mapping, augmented reality and robotics while paving the way for these innovations into NAVER products and services.
The edge computing group focuses on bringing ambient intelligence to the edge to improve the user experience while respecting their privacy. Devices such as mobile phone or SoC platforms are more and more powerful which allow the processing of the data close to where they’re generated.
The goal of this internship is to enable new type of applications by bringing advanced computer vision algorithms on devices with CPU/Memory or bandwidth constraints.
In this internship, the intern will focus on some of the following tasks in collaboration with the other team members:
- Select relevant computer vision algorithms such as object detection and classification
- Target embedded devices based on their power consumption from 10-20W (Nvidia Tegra TX2, Drive PX, AGX Xavier) to a few a few watts (Raspberry Pi) or even less (GAP8).
- Port and evaluate performances
- Develop applications demonstrating the performance of some of the embedded platforms.
Requirements and competencies expected:
- Master Students in Computer Science.
- Development skills: C/C++/C#, Java, python, with some experience of mobile platforms.
- Knowledge in computer vision and machine learning techniques is a plus
- Highly motivated.
During her/his internship the candidate will acquire a significant knowledge in advanced computer vision and machine learning techniques while working closely with researchers and engineers. Additionally, the candidate will become knowledgeable of Agile developments methodologies (eg: SCRUM, Continuous Integration)