Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Development of a Smart Camera Application for Manual Assembly Based on Synthetic Training Data
Goal of this project is the development of a deep learning based smart camera application based on synthetic training data. It will be used to automatically detect manual assembly steps and support workers during the assembly process. The setup process for the application is to be analyzed in depth to identify bottlenecks, which are to overcome.
Keywords: Machine learning, computer vision, smart camera, deep learning, neural networks, supervised learning, synthetic training data, process automation, manufacturing, manual assembly, product development
Smart cameras automatically collect information from images using computer vision algorithms. Actions and decisions can be triggered using this information. In our research, we are using deep learning models with a focus on synthetic training data to automatically analyze manual assembly scenarios.
Together with industrial partners, we research smart camera applications in the field of manual manufacturing. Using the cameras, manufacturing states can be determined automatically, and workers can be supported with information about realized, missed or upcoming tasks. Further, they can be alarmed if mistakes happen. In our research, we are focused on the application scenarios of such smart cameras, rather than the development of new computer vision approaches.
Smart cameras automatically collect information from images using computer vision algorithms. Actions and decisions can be triggered using this information. In our research, we are using deep learning models with a focus on synthetic training data to automatically analyze manual assembly scenarios. Together with industrial partners, we research smart camera applications in the field of manual manufacturing. Using the cameras, manufacturing states can be determined automatically, and workers can be supported with information about realized, missed or upcoming tasks. Further, they can be alarmed if mistakes happen. In our research, we are focused on the application scenarios of such smart cameras, rather than the development of new computer vision approaches.
Task of the project is the development of a smart camera application to support a manual assembly process. The goal is to automatically detect a defined variation of assembly accuracies and provide a user with feedback about their realization. Therefore, a pipeline to create a deep learning model is to be realized. Part of the pipeline should be the creation of synthetic training data. This is done to decrease the effort of manual training data generation. After finalizing the smart camera application, it is to be evaluated under actual industrial conditions to determine the application performance and robustness. Base of the project will be priorly realized prototypes that make us of either real or synthetic training data.
Task of the project is the development of a smart camera application to support a manual assembly process. The goal is to automatically detect a defined variation of assembly accuracies and provide a user with feedback about their realization. Therefore, a pipeline to create a deep learning model is to be realized. Part of the pipeline should be the creation of synthetic training data. This is done to decrease the effort of manual training data generation. After finalizing the smart camera application, it is to be evaluated under actual industrial conditions to determine the application performance and robustness. Base of the project will be priorly realized prototypes that make us of either real or synthetic training data.
You are highly interested in realizing applied computer vision solutions Desired are interest and skills in programming (Python is preferred) Experience with deep learning and training of neural networks such as YOLO, MobileNet etc. will help You are able to work independently and are eager to interact with an industrial partner You approach problems systematically and manage your projects methodically You are a team player, curious and come up with innovative ideas Willingness to integrate into a professional work environment
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
Master/Bachelor/Semester thesis. Earliest start: February 2023
Jonas Conrad
LEE O 219
conradj@ethz.ch
Tel.: +41 (0)44 632 36 02
pdz.ethz.ch
Jonas Conrad LEE O 219 conradj@ethz.ch Tel.: +41 (0)44 632 36 02 pdz.ethz.ch