Hacker News Reader

Seems to work well- I just tried it on a tiger cub vid, which I've had for years and was taken with an el-cheapo digital camera: Shaky version: http://youtu.be/g5P9WwHdOSI Stabilised version http://youtu.be/wXfbRUk_1Bg

There is some motion blur (around 24 seconds, when the momma tiger lies down) which is a bit puzzling once the image has been stabilised. But hey, it's better than it was before.

View on HN

The motion blur was there in the first place, you just don't notice it because there's also _motion_. When you remove the motion (shaking, jerking the camera), you're left with just the blur.

Yes, I know. But the viewer won't know that, because they don't know where the motion was before it was stabilised.

It also looks like the stabilized video is magnified a little bit. Regardless, these tools are really neat and they are still in their infancy. It's good to see that GooTube still believes in user-generated content.

Cropping and magnifying the video is required for all methods of video stabilization, because otherwise you would see the edge of the original frame move in and out of view.

Are there any stabilization algorithms that use other frames in the past and future to fill in the gaps with (possibly anachronistic) data?

Reply on news.ycombinator.com