Doctoral researcher– Project “Active Tracking using Bio-inspired Vision Sensors”

(Salary grade E13 TV-L, under the reserve that funds are granted, starting no later than from 1.10.2021 / for 3 years / closing date for applications 20.11.2020, Ref SCIoI-C3-36).

The Technische Universität Berlin invites applications for a PhD position for the Cluster of Excellence “Science of Intelligence”.

What are the principles of intelligence, shared by all forms of intelligence, no matter whether artificial or biological, whether robot, computer program, human, or animal? And how can we apply these principles to create intelligent technology?

Answering these questions – in an ethically responsible way – is the central scientific objective of the new Cluster of Excellence Science of Intelligence (www.scienceofintelligence.de), where researchers from a large number of analytic and synthetic disciplines – artificial intelligence, machine learning, control, robotics, computer vision, behavioural biology, psychology, educational science, neuroscience, and philosophy – join forces to create a multi-disciplinary research program across universities and research institutes in Berlin. Interdisciplinary research projects have been defined (https://www.scienceofintelligence.de/research/projects), which combine analytic and synthetic research and which address key aspects of individual, social, and collective intelligence.

Working field

Active tracking using bioinspired event-based vision – Towards improving interpretability of individual and collective behaviour

Complex behavior of animals is often analyzed from video recordings since cameras provide an economical and non-invasive way to acquire abundant data during experiments. The goal of this project is to develop an active tracking algorithm using a combination of video (i.e., frame-based) cameras and event-based cameras in order to extract meaningful motion information of individuals (in isolation or as part of groups). The project also considers the utilization of a Panda robotic arm with the above-mentioned cameras as end effectors in order to improve tracking in cases of occlusions and individuals moving out of the field of view of static cameras. Additionally, we aim to tackle the problem of analyzing the extracted motion tracks and segmenting them into different behaviors, in an unsupervised manner to minimize human bias and complement expert knowledge.

Responsibilities

Doctoral project “Active Tracking using Bio-inspired Vision Sensors”

The project focuses on investigating novel methods to track individuals in isolation or as part of a group (e.g., fish, etc.) using a combination of frame- and event-based cameras. The goal is to efficiently capture motion information and analyze it to extract behaviour information. To deal with the unconventional encoding of visual information produced by event-based cameras, we plan to explore novel neural network architectures that operate on point-based data structures and allow us to learn motion while also enabling the fusion of data from on-demand frames. The project considers the following scenarios of increasing complexity: (1) tracking of individuals using static cameras, (2) tracking with a moving camera and (3) active tracking using a robotic arm. To supplement expert interpretation of the extracted motion information given by the tracking algorithm, the project will investigate unsupervised approaches to classify behavior and actions based on simplified motion representations of complex real-world behavior. The project will be developed in collaboration with other SCIoI projects that provide experimental facilities for data recording.

Requirements

Applicants must hold a Diploma/Master’s degree in Computer Science or related engineering discipline with outstanding results. We expect high motivation and interest for interdisciplinary research, and should have proven skills/background in following topics:

  • Computer Vision and Machine Learning
  • Skills in writing efficient code (e.g. C++, Python)
  • Experience in video processing tools
  • Experience in using software libraries like Pytorch, TensorFlow, OpenCV
  • Knowledge of Robotics software (ROS) and simulation tools is a plus

Excellent English skills are required. Research experience is a plus.

 

 

Application procedure

Candidates should upload their application preferably via the portal www.scienceofintelligence.de/jobs in order to receive full consideration.

Applications should include: motivation letter, curriculum vitae, transcripts of records (for both BSc and MSc), copies of degree certificates (BSc, MSc), abstracts of Bachelor-, Master-thesis, list of publications and one selected manuscript (if applicable), two names of qualified persons who are willing to provide references, and any documents candidates feel may help us assess their competence.

 

 

 

User registration

You don't have permission to register

Reset Password