Thesis Deep Learning for Multiple Object Tracking in Crowded Scenes
- Robert-Bosch-Straße 200, 31139 Hildesheim, Germany
- Legal Entity: Robert Bosch GmbH
Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology – with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.
The Robert Bosch GmbH is looking forward to your application!
Deep Learning (DL) is a family of machine learning methods that are able to learn abstract representations of data using artificial neural networks with multiple hierarchical layers. Object tracking is a difficult task that implies sustained visual attention in a dynamic environment. Multiple objects have to be correctly identified, and tracked over a prolonged period of time. This task is especially challenging for crowded scenes where the objects may interact or have overlapping trajectories. One recent DL paradigm called shared memory augmented neural networks (SHAMANN) has the ability to use both temporal and global context information to solve challenging tasks. The aim of this thesis is to investigate the use of such models for multiple object tracking in crowded scenes. These are the main steps:
- You deal with the literature review of (shared) memory networks, as well as state-of-the-art approaches in multiple object tracking.
- You develop and implement a method for multiple object tracking based on the shared memory augmented neural networks.
- The experimental validation and evaluation of the developed method using object tracking benchmarks and internal datasets are also part of your area of responsibility.
- Education: Studies (master) in the field of information science or other computer vision or machine learning related studies
- Personality and Working Practice: creative, desire to learn, highly motivated, self-organized and problem-solving abilities
- Experience and Knowledge: Deep Learning/Computer Vision experience, good knowledge of python is an advantage
- Languages: fluent in English
Start: according to prior agreement
Duration: 6 months
Requirement for this thesis is the enrollment at university. Please attach a motivation letter, your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.
Need further information about the job?
Cosmin Bercea (Business Department)
+49 5121 49 1539
Apply now in just 3 minutes!