{"data":{"site":{"siteMetadata":{"author":{"name":"Stefan Sietzen","contacts":{"twitter":""}},"disqusShortname":"","subtitle":"Stuff I did in my spare time and for university.","title":"Project blog by Stefan Sietzen","url":"https://portfolio.stefansietzen.at"}},"markdownRemark":{"id":"82338656-7325-52fb-bb8d-9d3398f97a11","html":"

\n \n

\n \n
\n \n

\n

During an internship at MoonVision GmbH I was tasked with researching the potential of siamese tracking for an internal project. I adapted an existing TensorFlow implementation to be able to handle multiple objects instead of just one. I also created the visualization of a heatmap displaying the location probability of the object to track. This required a deep adaption of the architecture, introducing a fourth dimension into the three dimensional computation graph, but provided valuable insight into the details of this powerful architecture.

","fields":{"slug":"/posts/siamese-tracking/","tagSlugs":["/tag/object-tracking/"]},"frontmatter":{"date":"2018-02-24T23:46:37.121Z","description":"During an internship at MoonVision GmbH I was tasked with researching the potential of siamese tracking for an internal project. I adapted an existing TensorFlow implementation to be able to handle multiple objects instead of just one. I also created the visualization of a heatmap displaying the location probability of the object to track. This required a deep adaption of the architecture, introducing a fourth dimension into the three dimensional computation graph, but provided valuable insight into the details of this powerful architecture.","tags":["Object Tracking"],"title":"Siamese multi object tracking"}}},"pageContext":{"isCreatedByStatefulCreatePages":false,"slug":"/posts/siamese-tracking/"}}