Motion detection is the action of sensing physical movement in a given area.

Motion can be detected by measuring change in speed or vector of an object or objects in the field of view. This can be achieved either by mechanical devices that physically interact with the field or by electronic devices that quantifies and measures changes in the given environment.

When motion detection is accomplished by natural organisms, it is called motion perception.

 Mechanical devices
A tripwire is a simple form of motion detection. If a moving object steps into the tripwire's field of view (i.e. trips the wire), then a simple sound device (e.g. bells) may alert the user. A glass filled to the brim so that surface tension causes a convex meniscus can be placed on top of an object to detect if the object has moved.

Mechanical motion detection devices can be simple to implement, but at the same time, they can be defeated easily by interrupting the devices' mechanics (e.g. by "cutting the wire" or "drinking the water"). Electronic motion sensing devices, such as motion detectors, can prevent such mechanical intervention.

 Electronic devices
The principal methods by which motion can be electronically identified are optical detection and acoustical detection. Infrared light or laser technology may be used for optical detection. Motion detection devices, such as motion detectors, have sensors that detect movement and send a signals to a sound device that produces an alarm or switch on an image recording device. There are motion detectors which employ cameras connected to a computer which stores and manages captured images to be viewed later or viewed over a computer network.

The chief applications for such detection are (a) detection of unauthorized entry, (b) detection of cessation of occupancy of an area to extinguish lighting and (c) detection of a moving object which triggers a camera to record subsequent events. The motion detector is thus a linchpin of electronic security systems, but is also a valuable tool in preventing the illumination of unoccupied spaces.

A simple algorithm for motion detection by a fixed camera compares the current image with a reference image and simply counts the number of different pixels. Since images will naturally differ due to factors such as varying lighting, camera flicker, and CCD dark currents, pre-processing is useful to reduce the number of false positive alarms.

More complex algorithms are necessary to detect motion when the camera itself is moving, or when the motion of a specific object must be detected in a field containing other movement which can be ignored. An example might be a painting surrounded by visitors in an art gallery.

 Definition and relation to other tasks
Face detection can be regarded as a specific case of object-class detection; In object-class detection, the task is to find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos, pedestrians, and cars.

Face detection can be regarded as a more general case of face localization; In face localization, the task is to find the locations and sizes of a known number of faces (usually one). In face detection, one does not have this additional information.

Early face-detection algorithms focused on the detection of frontal human faces, whereas newer algorithms attempt to solve the more general and difficult problem of multiview face detection. That is, the detection of faces that are either rotated along the axis from the face to the observer (in-plane rotation), or rotated along the vertical or left-right axis (out-of-plane rotation),or both.

 Face detection as a pattern-classification task
Many algorithms --including the ones mentioned in this article's external links section-- implement the face-detection task as a binary pattern-classification task. That is, the content of a given part of an image is transformed into features, after which a classifier trained on example faces decides whether that particular region of the image is a face, or not.

Often, a window-sliding technique is employed. That is, the abovementioned classifier is used to classify the (usually square or rectangular) portions of an image, at all locations and scales, as either faces or non-faces (background pattern).

Challenges in pattern classification for face detection
A given natural image often contains many more background patterns than face patterns. Indeed, the number of background patterns may be 1,000 to 100,000 times larger than the number of face patterns. This means that if one desires a high face-detection rate, combined with a low number of false detections in an image, one needs a very specific classifier. Publications in the field (including the two in this article's external links section) often use the rough guideline that a classifier should yield a 90% detection rate, combined with a false-positive (or type I error) rate in the order of 10-6.

Applications
Face detection is used in biometrics, often as a part of (or together with) a facial recognition system. It is also used in video surveillance, human computer interface and image database management. Some recent digital cameras use face detection for autofocus.