A Novel Subpixel Industrial Chip Detection Method Based on the Dual-Edge Model for Surface Mount Equipment

Abstract

Vision-based location of industrial chips is crucial for high-speed and high-precision mounting in surface mount technology (SMT) applications. The conventional general location method requires numerous details of the chips’ physical characteristics, making it unsuitable for unknown chip locations and offline learning. In this article, we propose a general chip detection algorithm based on subpixel features from accelerated segment test (FAST) points that offers strong applicability, high precision, and high speed. The core part of our method is the extraction of subpixel boundary FAST points. The conventional subpixel calculation method uses a single-edge model that results in large deviations between calculated and actual positions when applied to actual FAST points. We propose a dual-edge subpixel model containing two groups of edges to reduce this error. Compared with the iterative calculation method in OpenCV, this method has a closing solution and faster performance. We determine model parameters using spatial moments, and present the relationship between the model and subpixel positions. Our experiments on the SMT hardware platform demonstrate that our method is robust to noise, illumination, position, and chip type, and is faster, more accurate, and more reliable than the Hanwha SM481-Plus placement machine and point registration method.