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 Platform for Task Identification in Human Performed Processes
Platform-based approaches accelerate the development of Internet of Things applications. Smart camera platforms, as a specific example researched at pd|z, enable users to automatically monitor human performed processes.
Keywords: Internet of Things, Smart Camera, Machine Learning, Deep Neural Networks, Task Identification, Process Monitoring
Smart cameras (meaning cameras in combination with object detection algorithms) can cover a wide range of sensor tasks in industrial IoT (Internet of Things) applications. One specific task is the monitoring of human performed processes in domains such as assembly or order picking. Hereby, with the use of object recognition algorithms, process errors can be identified and adequate support can be provided to workers.
One way to accelerate the development of such devices is the uses of platforms, meaning ready made, generalized combinations of hard- and software. These platforms can be individualized during the set-up process to suit a certain application. Existing platforms require high efforts during set-up and require expert’s knowledge.
Smart cameras (meaning cameras in combination with object detection algorithms) can cover a wide range of sensor tasks in industrial IoT (Internet of Things) applications. One specific task is the monitoring of human performed processes in domains such as assembly or order picking. Hereby, with the use of object recognition algorithms, process errors can be identified and adequate support can be provided to workers. One way to accelerate the development of such devices is the uses of platforms, meaning ready made, generalized combinations of hard- and software. These platforms can be individualized during the set-up process to suit a certain application. Existing platforms require high efforts during set-up and require expert’s knowledge.
Starting from an existing smart camera prototype, the task is to research and implement hard- and software combinations to develop a stable smart camera platform. This shall result in a generalized smart camera approach which minimizes the set-up effort. The platform should then be tested on it’s ability to identify task sequences during varying human performed processes to gain insights on factors influencing the set-up effort. Iterating the development further until the platform can be used without expert’s knowledge is an optional goal.
Starting from an existing smart camera prototype, the task is to research and implement hard- and software combinations to develop a stable smart camera platform. This shall result in a generalized smart camera approach which minimizes the set-up effort. The platform should then be tested on it’s ability to identify task sequences during varying human performed processes to gain insights on factors influencing the set-up effort. Iterating the development further until the platform can be used without expert’s knowledge is an optional goal.
- You are highly interested in prototyping of IoT applications - Desired are interest and skills in programming (Python, C++ or MATLAB) - Experience with the training of machine learning algorithms such as YOLO will help - You are able to work independently and are eager to interact with an industrial partner ü 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.
Semester/Master Thesis
Start: From September 2019
Jonas Conrad/Felix Wang (pd|z) LEE O 219
conradj@ethz.ch
wangfe@ethz.ch
Tel.: +41 (0)44 632 36 02
pdz.ethz.ch
Jonas Conrad/Felix Wang (pd|z) LEE O 219 conradj@ethz.ch wangfe@ethz.ch