Google | Machine Learning Applied to Video Analysis Algorithms


Google | Machine Learning Applied to Video Analysis Algorithms
Google Google
View Full Case Study
Contact Vendor
Feature New Record

Due to the growth of video data on Internet, automatic video analysis has gained a lot of attention from academia as well as companies such as Facebook, Twitter and Google.  Video analysis, unlike image analysis, requires incredibly high speeds of efficiency and increased confidence intervals to accuratley discern the images in the video.  Creating these algorithms, these large tech companies have had to approach the problem from a creative and unintroduced algorithimic perspective.  

Organizations and individuals looking to run recognition software on short or extensive motion pictures.

Shot detection algorithms try to find the positions in the video, where one scene is replaced by another one with different visual content. Conventional approaches for shot detection usually involve the two steps of measuring the similarity of consecutive frames and then determining the shots’ boundaries. Two simple methods for measuring the similarity of frames are sum of absolute values of pixel-wise difference of frames and the difference between the histograms of frames.  Through leveraging shot detection, Google is able to, in most cases with a 98% degree of certainty, categorize what is in the frame.

Emerging (technology has been on the market for > 2 years)

Google is able to categorize the different objects in an image.  Thus, it naturally follows that Google is able to recognize the different objects moving throughout a motion picture.  

Image distinction is an applicable piece of software across a variety of industries.  For example, for autonomous vehicles to really have an impact on civilian society, computers within those cars have to, with very high degrees of certainty be able to recognize a car from a person, a person from a side walk, etc.

Google allows for partners to use its algorithmic analysis, allowing other companies access to its invaluable technology.


Fatal error: Call to a member function getLabel() on null in /efs/ on line 9