Machine Learning Software Improving Smart Phone Streaming Video Editing

Machine Learning Software Is Being Used In So Many Areas.

Smart phones are not really so smart. Some of the apps are becoming pretty smart however and are starting to incorporate some level of artificial intelligence science. Voice recognition apps for example are getting better at a rapid rate which is a very popular feature for users. 

Video streaming is replacing the single picture as the favorite mode for sharing information. Faster more powerful smart phones are making this possible. How about editing for video streaming from your phone? Can artificial intelligence and machine learning improve this as well?

You may soon be able to make dramatic editing changes to photos with just a few clicks on your computer, and you might be able to get better streaming quality of videos on your smartphone thanks to preliminary research conducted at Mason Engineering and backed by Adobe Research.

Professors in the Department of Computer Science are working with Adobe on cutting-edge projects, and some have already conducted projects the company funded. Adobe has donated $120,000 to Mason Engineering.

One of the latest: Associate professor of computer science Jyh-Ming Lien’s team collaborated with Adobe researchers to develop a new photo-editing technique that allows people to modify their pictures to reflect different materials. For instance, the process makes it easier to turn a photo of a leather sofa into one covered in a plain or floral fabric.

New Features From Machine Learning Software.

Currently companies have to take photos of every version of the sofa or use a more time-consuming process to create the different images, he says.

We are using machine-learning algorithms that allow you to take an image and apply a different material to it for a new look.

This technique could be useful to online stores and graphic artists who want to generate new images with different finishes or materials.

Meanwhile, computer science professor Songqing Chen’s research team investigated ways to improve streaming video on mobile phones.

“We tried to make the media playback on the phone smoother while consuming less power,” he says.

Most internet content, including streaming video, is transmitted over HTTP/1.1, but HTTP/2 is gradually replacing HTTP 1.1 to improve user experience, Chen says.

His team looked into ways to utilize the new features offered by HTTP/2 for video streaming to mobile devices. “We have been trying to set up protocols and implement the new prototypes,” he says.

Adobe plays a very active role in the standardization of some of the video streaming techniques.

Adobe has a long list of research questions it shares with Mason Engineering researchers to form collaborations, says computer science professor Robert Simon. The company also offers internships to Mason Engineering students.

One of Simon’s PhD students, Haoliang Wang, worked on a project involving storing streaming videos in the Cloud during his internship with the company last summer. Wang’s job was to help improve an algorithm the company developed.

Adobe gives Mason Engineering interns “very challenging research assignments,” Simon says.

Truly for us it has been an excellent industrial-academic partnership not just because of how interesting the students’ jobs are during the summer, but because the Adobe researchers follow up and maintain a relationship with our students throughout the year.


Picture Source Wikipedia Commons

Machine learning software and algorithms are opening up a whole new world of possibilities for products and apps.

(Visited 96 times, 1 visits today)

Machine Learning Software Improving Smart Phone Streaming Video Editing

1 Comment

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

This site uses Akismet to reduce spam. Learn how your comment data is processed.