Detection of 3-dimensional textured object without depth information

We propose a feature-based approach for detection of a 3-dimensional textured object in a single image. Each object has a training set which contains various poses in the template of small size. And then multiple objects are placed in the background, some of which are mixed with untrained objects. Background of some images is complicated and textured, which makes it difficult to find target object. In this experimental environment, the proposed algorithm finds the textured object comparing with the training template set we construct. It is based on Speeded Up Robust Features (SURF) descriptor and homography matching. First, it detects feature points of textured object using SURF descriptor. And second, it matches template to object in example with homography using RANdom SAmple Consensus (RANSAC). For texture-less object, the proposed algorithm did not show the good performance. For textured objects, however, it found the object in the complicated or simple background successfully for each.