Real-time Textureless Object Detection and Recognition Based on an Edge-based Hierarchical Template Matching Algorithm
Chi‐Yi Tsai, Chaochun Yu · Tamkang University Institutional Repository (TKUIR) · 2018
Textureless object recognition is a difficult task in computer vision because the object-ofinterest (OOI) may not have enough texture information for extracting object features. To address this problem, this paper presents a textureless object recognition method based on the existing Line2D algorithm. The proposed method employs an edge-based hierarchical template matching method to detect and identify a wide variety of textureless objects. Given a reference template image of an OOI, a hierarchical edge-template database containing different 2D poses of the OOI was firstly created by applying affine transformation with different rotating and scaling settings to the reference template image. Next, an edge-based template matching process is performed to detect and recognize the OOI by searching matches between the hierarchical edge-template database and the input image. Finally, the position and angle posture of the OOI can be determined by the best match having the highest similarity measure. Experimental results show that the proposed method not only can efficiently recognize the type, quantity, position, and angle information of various textureless objects in the image, but also can achieve real-time performance about 24 frames per second (fps) in processing 640x480 images. Therefore, the proposed algorithm has the potential to be used in many computer vision applications.