Dense Captioning of Video Demonstrating the Upgraded Boston Dynamics Atlas Robot
Artist and programmer Gene Kogan ran the Boston Dynamics video demonstrating their upgraded Atlas robot through the Densecap captioning system, which tries to identify objects in a video. The system is both impressive and at times wildly inaccurate, labeling the robot in the resulting video as a variety of incorrect things like a person skiing, a motorcycle, or a fire hydrant.
Captions are generated by densecap on individual video frames. The video is made by a python script which merges matching captions along sequences of consecutive frames with a set of (mostly greedy) heuristics. Presumably, it would be possible to caption sequences of regions directly rather than a naive merging algorithm, but I’m not sure how :)
interestingly, densecap never mentions robots. atlas is variously described as person, motorcycle, fire hydrant, etc pic.twitter.com/roInNdoKKM
— Gene Kogan (@genekogan) July 1, 2016
Glen Tickle
Recent Posts
Useful Tips for Getting the Most Out of Common Household Items
How Chemists Discovered That Water is a Chemical Compound Rather Than an Element
Aubrey Plaza and Patti LuPone of ‘Agatha All Along’ Play a ‘Hot Ones’ Version of ‘Truth or Dare’ With Hot Wings
Pianist Adds Musical Soundtrack to Paul Rugg’s Famous ‘Relaxing With Your Dog’ Video
POV Video of a Hot Wheels Car Racing on Track Then Doing a Deep Dive Into a Swimming Pool
