Computer Vision Research Internship

Team Description: Kitware’s Computer Vision team is a leader in the creation of cutting-edge algorithms and software for automated image and video analysis. Our solutions embrace deep learning and add measurable value to government agencies, commercial organizations, and academic institutions worldwide. We understand the difficulties in extracting, interpreting, and utilizing information across images, video, metadata, and text, and we recognize the need for robust, affordable solutions. We seek to advance the fields of computer vision and deep learning through research and development and through collaborative projects that build on our open source software platforms, such as Kitware Image and Video Exploitation and Retrieval (KWIVER) toolkit.

About the Projects: Interns will be able to explore their own ideas to address challenging real-world computer vision problems, and will be encouraged to publish the results of their work in academic papers submitted to premier conferences. In addition, interns can also focus on contributing high-quality software to the KWIVER platform, an exciting, open source, and versatile platform for computer vision research and development. We consider the work that we do on our government contracts one of the ways that we give back to the community. We relish the opportunity to work on hard problems that have a direct impact on the health, safety and security of our community; our team members choose Kitware instead of working in large internet companies to sell web advertisements. One of our core values is to make the technology we develop as broadly available as possible.

In This Position You Will:

• Be part of Kitware's overall mission of positive social impact through work in areas such as environmental monitoring, national and global security, ethical AI, open science, scientific computing, and medical computing.
• Algorithms: Deep learning and other computer vision methods for object detection, change detection, scene classification, event/activity recognition, 3D reconstruction from aerial imagery, video/image understanding, video/image search, and indexing, etc.
• Data: Images and videos from ground, handheld, aerial, or satellite cameras.
• Infrastructure: Opportunity to work on deep learning libraries like PyTorch or Tensorflow; large-scale computer vision. framework on the cloud; or performance optimization using GPUs, parallel computing, or embedded devices such as NVIDIA’s TX2.

Required Qualificiations:

• Ph.D. students in related fields, including computer vision, machine learning, multimedia, signal processing, imaging science, and applied mathematics.
• Knowledge and experience in computer vision, machine learning, deep learning (PyTorch, Tensorflow, etc.), remote sensing or related areas.
• Proficiency in Python or C/C++.
• Due to contractual restrictions, only US Citizens will be considered for this position.