Analysis of Suitable Natural Feature Computer Vision Algorithms for Augmented Reality Services

The first step in working with object augmentation in an augmented reality system is to identify the target object, so its pose in respect to the camera can be determined for precise and accurate augmented content generation over the target object. In modern augmented reality systems natural feature detection algorithms are widely used for detecting, identifying and tracking planar textured objects. All-natural feature algorithms detect interest points or keypoints (detector) in an image (scene) and/or calculate descriptors for keypoints (extractor). Algorithms can include both parts, detection and extraction, and can have just one of them realized. There is a variety of algorithms available nowadays for developers to use. Starting from floating point descriptor-based ones as SIFT and SURF and a row of binary descriptor-based algorithms such as BRIEF, ORB, BRISK, FREAK, KAZE, A-KAZE, LATCH. In addition, there are algorithms which only detect interest points, as FAST or A-GAST. Furthermore, it is possible to use one algorithm for keypoint detection and afterwards use another for descriptor extraction. Given such a variety of available algorithms, it is necessary to analyse them by understanding their working principles, so they can be classified by their strengths and weaknesses and in what situations the use of one or another algorithm is more appropriate. Since it is possible to use combinations of algorithms, a table of possible cases is provided. For clarity we must mention that various algorithms, which are not mentioned here, are available but we take an overview of the above listed as all of them are included in the OpenCV library and are widely used in the industry.