Instead, you might be better off watching this video of the world’s tallest dog—puppies are available!—meeting the world’s shortest dog. Once again, this title appears unofficial.

Better still, there’s this video of 2007’s world’s ugliest dog. Finally, here’s a photo I like of a cat looking at a deer:

In conclusion, I haven’t put on my shoes all weekend. Coincidence?

Update: On a more substantive note, I also wrote a post once about more intelligent image editing tools (it’s the sort of post a shoe-wearer would write). A few weeks ago the New York Times ran this article that highlights some of the related free software that’s available.

The control can sense its own acceleration in all three dimension, and (when its not moving to fast) it can determine its angle relative to the ground (disclaimer: this feature will not work in space). Most importantly, it contains an infrared camera that watches for the Wii’s sensor bar, which is supposed to be placed directly below your TV screen.

Thanks to infrared camera and sensor bar, you can do fun things like move a cursor around your TV screen just by pointing at it (if only Nintendo made cable boxes). The interesting thing about the sensor bar, is that it’s really just two infrared dots, and can even be replaced with candles). By spotting these two dots, the Wiimote can tell where on your screen its pointing, as well as how far it is from your TV. Although only two dots are required for this task, the Wiimote is quite capable of seeing all sorts of stuff, provided infrared light is involved (more on that below).

The final, and perhaps greatest thing about the Wiimote, is that it’s wireless. It uses bluetooth to communicate with a Wii console. This means that it can just as easily connect to a bluetooth-enabled computer. Why is this important? Well it’s generally easier for programmer types to write software for a computer than a video game system. As a result, many intrepid individuals have taken to programming Wiimote-controlled computer software that is free for download.

Wiiinstruments, is a wonderful example. If you download this program, you get to use your Wiiremotes (as well your Wii nunchucks, which also sense acceleration) to trigger drum noises. Here’s the demo video. My housemate (pictured above) downloaded this software a weeks ago. It was an exhilarating/exhausting experience. Admittedly, tucking the nunchucks into your socks is absurd, but with Wii Fit about to reach the US, a better foot controller alternative is on the way.

Another cool piece of Wii software is Wii Loop Machine (there’s also a video), and if that’s not enough for you, nerdlogger.com has compiled a whole list of “Wiilated software” (coin the phrase people)! For my money, the most innovative use of a Wiimote comes from CS graduate student Johnny Chung Lee.

Mr. Lee (Lii?) works on human-computer interaction at CMU and had access to a bunch of interface software he was able to adapt for use with a Wiimote. In his first video, he explains how the Wiimote’s camera, combined with infrared emitting LEDs, can be used to track the position of one’s finger tips. This in turn can be used to create a multitouch interface that apple would be proud. In his second video, he uses the Wiimote’s camera to track a homemade infrared emitting pen (simply an led it a bic plastic case). Using his pen in conjunction with a projector allows him to create an electronic white board. In his third, and most awe-inspiring video, he uses the Wiimote to track his head position relative to a computer monitor. This allows his software to change the perspective of various 3D images in response to how he’s looking. It’d be hot stuff if someone wrote similar software for the macbook’s built in camera.

Second, here’s a hot video demoing some content-aware image resizing research first presented at SIGGRAPH 2007. It’s a fairly simple idea that works surprisingly well.

Normally when you shrink an image you either make the whole thing smaller, or crop some content from the sides. Ariel Shamir and Shai Avidan take a different approach which they call “seam carving”.

As the video explains, seam carving is similar to removing the least important rows and columns from the middle of an image. Instead of removing rows and columns, however, their algorithm identifies paths of unimportant pixels. These paths tend to curve around objects, so when removed, they shrink the image in way that’s not very noticeable. Basically you end up shrinking an image by removing the space between objects, but not changing the size of the objects themselves.

If you have some images you need to resize intelligently, a rather pricey photo shop plugin is available here. Alternatively, here’s a free plugin for GIMP (which is also free).

Finally, if you’re still hungry for more content-aware image editing, here’s a paper by Microsoft researcher Antonio Criminisi. Sadly there’s no flashy video, but the images in the paper do give some very impressive examples of how their algorithm automatically fills in missing regions of images. By filling in a missing region, one can also delete entire objects from a scene, remove overlaid text, or stitch together partially overlapping photos.

Our biggest success was getting good measurements from video. Our basic technique was to identify as many parallel lines and right angles in the scene as possible. From those we could infer the location of the camera, and then produce a correspondence between points in the 2D image and points in 3D space. Given this correspondence, along with the dimensions of one object in the image, we could estimate the length of everything else (e.g. the car).

It sounds complicated, but really the math involved isn’t that hard (it’s mostly linear algebra), and identifying parallel lines and right angles is something people can do manually by drawing on the image. All in all, the approach we used struck me as a useful tool that someone could either sell, or put online. Since no one from the class did this, I’m was glad to read that a company called VisualSize will offer a similar service.

Their website doesn’t have much info, but according to the TechCrunch post I read, they require users to submit two images of a scene, taken from slightly different positions. This means that instead of parallel line, they are using the difference between the two images to infer camera position and distance. This is very similar to how people use two eyes to perceive depth. The advantage of their approach (I think) is that a user doesn’t need to have measured the size of any object in the images. The disadvantage is that you need two images.

It sounds like VisualSize’s length estimates are about 1 to 5 percent accuracy (that’s about what we got). If VisualSize’s image measurements get a bit more reliable, they would be a big help to anyone who’s ever painstakingly taken measurements of a building or space. If they improve even more, they could potentially be used to automatically produce 3D models from 2D images. This would take something like google street and turn it into 3D models of cities.

Computer vision has come a long way in the last 15 years, and regardless of VisualSize’s success, more and more computer vision research is going to make its way into commercial products. Facial recognition in digital cameras is another prime example.

Update: Professor Yuan-Fang Wang from VisualSize generously shared some of their algorithm’s sample outputs with me. Many of the measurements were very impressive. Here’s the one from the TechCrunch article. Professor Wang also pointed out that their algorithm requires a single known distance in the two images, as since it is not theoretically possible to determine absolute distance without a frame of reference.