Editing 1425: Tasks
Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 8: | Line 8: | ||
==Explanation== | ==Explanation== | ||
− | [[Cueball]] appears to be asking [[Ponytail]] to write an app that determines if a given picture is (1) taken in a national park, and (2) a picture of a bird. The first question is generally harder for a human to answer, but easy for an app that has access to location information and a {{w|geographic information system}} (GIS). The second one is easy for a human but much harder for a computer. This illustrates {{w|Moravec's paradox}} | + | [[Cueball]] appears to be asking [[Ponytail]] to write an app that determines if a given picture is (1) taken in a national park, and (2) a picture of a bird. The first question is generally harder for a human to answer, but easy for an app that has access to location information and a {{w|geographic information system}} (GIS). The second one is easy for a human but much harder for a computer. This illustrates {{w|Moravec's paradox}} in a modern context. It turns out to be relatively easy to teach computers impressive skills like {{w|trajectory optimization}}, but hard to "give them the skills of a one-year-old when it comes to perception", as Steven Pinker wrote. |
In order to determine whether the user is in a national park, Ponytail plans to determine the user's location using the mobile device. This location will then be cross checked with a {{w|geographic information system}} (GIS) which will be able to determine whether the coordinates lie within a national park boundary. | In order to determine whether the user is in a national park, Ponytail plans to determine the user's location using the mobile device. This location will then be cross checked with a {{w|geographic information system}} (GIS) which will be able to determine whether the coordinates lie within a national park boundary. | ||
− | Determining whether an image is of a given kind of natural object is far more difficult. This task falls into the area of {{w|computer vision}}. One of the goals in computer vision is to detect and classify objects within an image. This is a very challenging task for a number of reasons. | + | Determining whether an image is of a given kind of natural object is far more difficult. This task falls into the area of {{w|computer vision}}. One of the goals in computer vision is to detect and classify objects within an image. This is a very challenging task since for a number of reasons. |
− | Firstly, humans use size, edge-assignment, movement, and stereoscopic vision when looking at a scene (not a picture of a thing, but the thing itself) to discern individual objects and then {{w|Figure- | + | :Firstly, humans use size, edge-assignment, movement, and stereoscopic vision when looking at a scene (not a picture of a thing, but of the thing itself) to discern individual objects and then categorize them as foreground or background.<ref>{{w|Figure-ground_(perception)}}</ref> A photograph, however, is a static, monoscopic image that can only provide size and edge-assignment clues. Humans are only able to discern objects from background in photographs by comparing the photo against all of the things they've seen and everything they've learning about those things over the course of their life and identifying matching patterns.<ref>{{w|Visual_perception}}</ref> Presumably, today's computers do not have nearly the processing power or wealth of data available as the human mind. |
− | Secondly, the quality of the photograph will have an impact on a computer's ability to match patterns. For example, the object in the photograph might be partially visible or occluded. In the case of a living bird, additional complications arise from the variations among individual birds of the same species and differences in pose (flying, perching in a tree, etc.). Differentiating between visually similar objects can result in false positives. For example, is it a photo of a bird in flight or a plane | + | :Secondly, the quality of the photograph will have an impact on a computer's ability to match patterns. For example, the object in the photograph might be partially visible or occluded. In the case of a living bird, additional complications arise from the variations among individual birds of the same species and differences in pose (flying, perching in a tree, etc.). Differentiating between visually similar objects can result in false positives. For example, is it a photo of a bird in flight or a plane (or superman!). Ponytail's estimate of 5 years may be overly optimistic (see [[678: Researcher Translation]]). |
− | + | Today's state-of-the-art algorithms for solving this kind of task mostly use local features (e.g. {{w|Scale-invariant feature transform|SIFT}} or {{w|SURF}} in combination with a {{w|support vector machine}} or {{w|convolutional neural network}}). | |
− | + | The title text mentions [http://dspace.mit.edu/bitstream/handle/1721.1/6125/AIM-100.pdf The Summer Vision Project] and {{w|Marvin Minsky}} of MIT. In the summer of 1966, he asked his undergraduate student {{w|Gerald Jay Sussman}} to "spend the summer linking a camera to a computer and getting the computer to describe what it saw" ([http://szeliski.org/Book/]). {{w|Seymour Papert}} drafted the plan, and it seems that Sussman was joined by {{w|Bill Gosper}}, {{w|Richard Greenblatt (programmer)|Richard Greenblatt}}, {{w|Leslie Lamport}}, Adolfo Guzman, Michael Speciner, John White, Benjamin, and Henneman. The project schedule allocated one summer for the completion of this task. The required time was obviously significantly underestimated, since dozens of research groups around the world are still working on this topic today. | |
− | |||
− | The title text mentions [http://dspace.mit.edu/bitstream/handle/1721.1/6125/AIM-100.pdf The Summer Vision Project] and {{w|Marvin Minsky}} of MIT. In the summer of 1966, he asked his undergraduate student {{w|Gerald Jay Sussman}} to | ||
− | |||
− | |||
==Transcript== | ==Transcript== | ||
− | :[Ponytail sitting at a computer with Cueball standing behind her | + | :[Ponytail sitting at a computer with Cueball standing behind her] |
:Cueball: When a user takes a photo, the app should check whether they're in a national park... | :Cueball: When a user takes a photo, the app should check whether they're in a national park... | ||
:Ponytail: Sure, easy GIS lookup. Gimme a few hours. | :Ponytail: Sure, easy GIS lookup. Gimme a few hours. | ||
:Cueball: ...and check whether the photo is of a bird. | :Cueball: ...and check whether the photo is of a bird. | ||
:Ponytail: I'll need a research team and five years. | :Ponytail: I'll need a research team and five years. | ||
+ | :In CS, it can be hard to explain the difference between the easy and the virtually impossible | ||
− | + | ==References== | |
− | + | <references/> | |
− | |||
{{comic discussion}} | {{comic discussion}} | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− |