Shape analysis and Polygonal approximations | Análisis de la forma y aproximaciones poligonales

Shape analysis and Polygonal approximations | Análisis de la forma y aproximaciones poligonales



People detection and tracking are essential capabilities in several fields such as: ambient intelligent systems, 
visual servoing applications , augmented reality and  human-computer interaction, video compression or robotics.
Detection and tracking in monocular images are topics widely explored in the related literature. However, the use of stereo vision for these purposes is 
an emerging research area. Stereo vision brings several advantages over monocular images. First, all the methods designed for tracking in monocular images can be applied, but with much richer per-pixel information (colour or luminance plus depth). Depth information can be employed to achieve a better tracking of people as well as a better understanding of their gestures. Besides, depth is an important piece of information for the development of robust background estimation techniques. Second, disparity information (from which depth is obtained) is relatively invariable to illumination changes.  Therefore, systems that employ stereo vision are expected to be more robust in real scenarios where sudden illumination changes might occur.Shape of objects contain important information useful to recognize them. However, this information may contain redundant data. Polygonal approximations are an important tool useful for data reduction and object recognition.

Polygonal approximations are an important research area in computer vision due to different usages in this area. As is said above, the shape of the objects contain important information, however, this information may contain a great amount of redundant data.



Use Cases

One of the main uses of polygonal approximations is the reduction of the representation of the shapes. This is done by using a polygon instead of the original shape. This polygon has associated a distortion regarding the original shape which should be minimized by the polygonal approximation algorithm.



Polygonal approximations are also used to obtain feature vectors for shape and object recognition. This methods compute the polygonal approximation of the contours of the objects and use this approximations to compute different feature vectors. This features are the input of any classification method to recognize the object.

Polygonal approximation object recognition process

Related Publications