Kitware News
Kitware Participates in DARPA Memex
Kitware is developing software extensions that aim to address complex search problems common in fields such as security and defense as part of the Defense Advanced Research Projects Agency (DARPA) Memex program.
A key use case of the technology is the ability of law enforcement to discover and address human trafficking through the Web. The prominence of websites that facilitate trafficking is increasing, necessitating new software platforms that address the scale and scope of the expanding Web. Current software and search approaches do not effectively integrate interactive and social media, text, images, and video, while taking into account the degree of importance of each piece of media, which is required for performing “deep searches.”
“The leading search providers are singularly focused on displaying ads, which has led to closed systems and stagnant interfaces,” Jeff Baumes, a Co-Principal Investigator for the project and Technical Lead at Kitware, said.
Kitware is collaborating with NASA’s Jet Propulsion Laboratory at the California Institute of Technology and Continuum Analytics LLC to create specific extensions to Apache Nutch with the goal of improving its overall technological superiority for search. The project, which was featured on 60 Minutes earlier this year, is funded by DARPA. The work seeks to integrate state-of-the-art algorithms developed by Kitware with multimedia and video analytics to provide image and video understanding support to allow for automatic detection of objects and massive deployment via Nutch.
“The objective of our project is to create rich, customizable search experiences, using open-source tools and integrating diverse content such as video and images,” Baumes said.
The project is designed to create an interactive and visual interface for initiating Nutch crawls. The plan for the interface is to use the Blaze platform to expose Nutch data and to provide a domain-specific language for the crawls. The interface is also tasked with using the Bokeh visualization library to deliver simple interactive visualization and plotting techniques for exploring crawled information. Moreover, the team intends to make improvements to media-oriented search, as well as to the user interface (UI) and the domain-specific language for search, to unleash “deep search” activities that can be easily implemented by law enforcement and analysts for quick turnaround in time-critical situations.
“Our motivation is to enable rapid search and visualization in ways that were not possible in the past,” Baumes said.
Several communities can benefit from this work. The general intelligence community can benefit from the Nutch-based crawl interface, while the Apache and Python communities can benefit from the combination of Apache, Blaze, and Bokeh capabilities. Furthermore, the project can help more academic and open-source researchers explore and improve software for detecting human trafficking in the field, as it proposes to improve the power of Nutch as a search engine framework.
“Through DARPA partnerships, our tools can be utilized by organizations that desperately need better tools to make progress against real societal problems such as human trafficking,” Baumes said.
To learn more about the work discussed in this material, please see “DARPA: Nobody’s Safe on the Internet.”
Approved for Public Release, Distribution Unlimited
tomvis Platform for S/TEM Data
Kitware has announced Phase II funding from the Department of Energy (DoE) to continue development of an open-source platform for materials reconstruction using scanning transmission electron microscopes (S/TEM), in partnership with researchers at Cornell University.
The project is a response to shortcomings in current state-of-the-art tomography software processes that involve long analysis cycle times and the use of several different file formats, making it difficult to document and publish analysis and reconstruction results in a manner that is accessible to the broader scientific community. Motivated to provide a solution, Kitware is collaborating with Cornell University to build tomviz, a fully-functional, freely-distributable S/TEM platform that provides advanced segmentation, three-dimensional (3D) visualization, and analysis optimized for materials applications.
“There are approximately 600 transmission electron microscopes in the world today, and close to 50 new microscopes are made available online each year, creating a high demand for an open-source tomography platform,” Dr. Robert Hovden, a postdoctoral researcher at Cornell University and key collaborator on the project, said.
During Phase I, the team produced a cross-platform application that reads transmission electron microscope image data, implements graphical tools for user-assisted data alignment, performs basic tomographic reconstruction, and visualizes resulting 3D volumes. The application has already been well-received, with hundreds of downloads from the scientific community.
“The application presents users with advanced, intuitive software and workflows that enable the full path of data— from collection to final, analyzed results—to be saved, shared, and even published as supporting information,” Dr. Marcus D. Hanwell, the Principal Investigator for the project and a Technical Leader at Kitware, said.
In Phase II, the team will develop an extendable, turn-key platform that is capable of fully-automated, high-throughput electron tomography of nanoscale materials. The platform will feature a modern user interface and enhanced graphical tools for editing, aligning, segmenting, visualizing, and analyzing data. It will also feature one-click tomography, making it possible to easily reconstruct experimental data and visualize it in 3D.
“As a result of the project, it will be possible to have the entire tomography process, from measurement to 3D analysis, take place on a single graphical platform,” Hanwell said. “This technology will greatly accelerate progress in materials characterization and metrology, while also promoting reproducible science.”
For additional information, please read the full announcement on our news site.
This material is based upon work supported by the Department of Energy under Award Number DE-SC0011385.
Team Members Attend CVPR 2015
Kitware was actively involved this year in the Institute of Electrical and Electronics Engineers (IEEE) Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), which took place in June. An annual event, CVPR draws over 2,000 attendees from academia and industry, providing them with opportunities to learn more about the field of computer vision through workshops, tutorials, and conference sessions. Many of Kitware’s computer vision experts participated in this year’s event, and Kitware was a conference sponsor.
Members of Kitware hold live booth demonstrations.
On the first day of the conference, Matt Leotta from Kitware joined Sameer Agarwal from Google, Pierre Moulon from FOXEL SA, Frank Dellaert from Georgia Tech, and Vincent Rabaud from Aldebaran – Softbank Group to present “Open Source SfM.” The presentation highlighted Kitware’s Motion-imagery Aerial Photogrammetry Toolkit, known as MAP-TK. MAP-TK, which is open source, provides estimations of camera flight trajectory and sparse 3D point clouds of a scene. The presentation was well attended, and it concluded with one attendee winning a Parrot Bebop Drone.
Matt Leotta presents a drone to the winning attendee, Chris Debrunner.
Later in the week, Kitware presented a poster on “Collaborative Computer Vision R&D” at the fourth annual Vision Industry and Entrepreneur Workshop, which was held in conjunction to CVPR. The poster highlighted details on Kitware’s computer vision expertise including key capabilities, customers, and collaborators, as well as information on the KitWare Image and Video Exploitation and Retrieval (KWIVER) toolkit. KWIVER is Kitware’s open-source computer vision platform. It tackles challenging image and video analysis problems, addressing various domains worldwide.
Members of Kitware were also invited to discuss “Visual Profiling: Social Media and Surveillance for Commercial Intelligence” at the IEEE Workshop on Large Scale Visual Commerce (LSVisCOM). The discussion focused on information that can be applied directly to worldwide events that occur on a regular basis.
Project Repositories Migrate to GitLab
Kitware is now using GitLab to host several of its open-source projects, including the Visualization Toolkit (VTK), ParaView, Computational Model Builder (CMB), and Simulation Modeling Toolkit (SMTK). GitLab helps unify development workflows across various projects, providing the ability for community members to contribute and review changes, such as bug fixes and new features.
Additional advantages to migrating project repositories to GitLab include a more accessible user interface (UI) for inspecting changes and posting comments, as well as a simplified code-review process, especially for topic branches with multiple commits.
To access Kitware’s project repositories on GitLab, please visit https://gitlab.kitware.com/explore, and for questions regarding the migration, please e-mail the VTK, ParaView, CMB, or SMTK mailing list.
Open-Source Framework Aims to Enable New Paradigms in Structual Design
Kitware has announced Department of Defense (DoD) funding to develop an open-source, distributed computational environment for virtual materials exploration to address a pressing need in the manufacturing community. Currently, manufacturers that heavily leverage advanced materials engineering are limited in their abilities to efficiently and inexpensively design precision parts. As a result, there is a great need for new paradigms in structural design that leverage best-of-breed tools from finite element analysis (FEA) and materials simulation codes.
“There now exist simulation codes that are able to predict materials properties with increasing levels of accuracy,” Marcus Hanwell, the project’s Principal Investigator and a Technical Leader on Kitware’s Scientific Computing team, said. “Adopting more advanced materials simulation would ultimately enable the structural design process to drive materials requirements, with the possibility of real-time materials exploration, composite design, and/or processing options that could be adjusted alongside conventional optimization strategies such as varying shape to accommodate load/rigidity requirements.”
The open-source framework will enable designers to move beyond materials as fixed design inputs to active variables that can be manipulated as part of the structural design process. This has the potential to result in a paradigm shift from whole-part design based on standard material properties tables to the use of actual variables in dynamic, active material design. The framework will also allow designers to explore materials and compositions in real time and to adjust parameters to accommodate specific requirements.
“Once designers begin to incorporate advanced materials models, it becomes possible to tailor designs to increase longevity or reduce the weight of a part without compromising structural integrity,” Hanwell said. “For example, advanced designs might specify advanced materials processing techniques such as heat treatments in specific regions to increase local performance without the added cost of manufacturing the entire part out of an expensive material.”
To advance materials simulation, Kitware’s experts in finite element modeling (FEM) and FEA will research and prototype a multiscale simulation environment that integrates advanced materials models with a classical FEA system for modeling complex systems. For this Phase I Small Business Innovation Research (SBIR) project funded by the DoD, the team will investigate different approaches using software as a rapid prototyping/research tool to critically assess the benefits and costs of each approach.
For additional information, please read the full announcement on our news site.
This material is based upon work supported by the United States Air Force under Award Number FA8650-14-M-5044.
Nature Methods Features In Vivo Cycle Profiling Paper
The paper “In vivo cell cycle profiling in xenograft tumors by quantitative intravital microscopy” was published in the June edition of Nature Methods. It presents an integrated workflow for automated in vivo cell cycle profiling that enables large-scale, unbiased, consistent, and reproducible studies of the spatiotemporal effects of chemotherapeutic drugs and experimental perturbations on cell-cycle progression in living tissues at a single-cell level. The workflow combines a high-resolution intravital imaging setup for longitudinal observation of cell fate in living tissues with a novel computational framework for automated 3D segmentation and cell-cycle state identification of individual cell nuclei with widely varying morphologies, even those embedded in a highly complex tumor environment.
The paper is authored by Kitware’s Deepak R. Chittajallu, along with Stefan Florian, Rainer H. Kohler, Yoshiko Iwamoto, James D. Orth, Ralph Weissleder, Gaudenz Danuser, and Timothy J. Mitchison. It is also available on
http://www.nature.com.
Kitware Places on Technology List
Kitware ranked sixth on the Albany Business Review’s “The List: Technology Service Companies,” which was released in the paper’s Tech Pages edition. The list ranks companies by number of employees in the Capital Region.
Kitware plans to grow its presence in the Capital Region by hiring new team members this year. Kitware has also been featured on the Albany Business Review’s “The List: Software Developers in the Albany New York Area,” “The List: Top Defense Contractors in the Capital Region,” and “The List: Technology Companies in the Capital Region.”
Employment Opportunities
Kitware is seeking talented, motivated, and creative individuals to fill open positions and join in its mission to develop and deliver state-of-the-art software products and services. In particular, Kitware is seeking to hire highly-skilled research and development engineers to join its Scientific Computing team to work on developing and improving leading solutions in visualization software. Several additional positions are available on Kitware’s Scientific Computing, Medical Computing, and Computer Vision teams.
The impact of your research at Kitware will extend far beyond the organization, as Kitware’s open-source business model will allow you to become part of the worldwide communities that surround Kitware’s projects. Kitware employees enjoy a collaborative work environment that empowers them to pursue new opportunities and to challenge the status quo through novel ideas.
In addition to providing an excellent workplace, Kitware offers comprehensive benefits including: flexible hours; a computer hardware budget; health, vision, dental, and life insurance; short- and long-term disability insurance; immigration and visa processing; a relocation bonus; tuition reimbursement; and a generous compensation plan.
For additional information, please visit Kitware’s employment website at http://www.jobs.kitware.com. Interested applicants are encouraged to submit their resumes and cover letters through the online portal.
Kitware Internships
Kitware internships provide current college students with the opportunity to gain training and hands-on experience working with leaders in their fields on cutting-edge problems. Interns assist in developing foundational research and technology across Kitware’s five solution areas.