Synchronous AR assembly assistance and monitoring system based on ego-centric vision

Abstract

Purpose Aiming at presenting an interaction-free assembly assistance tool, the purpose of this paper is to propose a synchronous augmented reality (AR) assembly assistance and monitoring system. The system monitors operator’s hands activity and process completeness to recognize the assembly state, then display the AR contents contextually. Design/methodology/approach An assembly behavior recognition method is proposed based on gesture recognition. An assembly completeness inspection method is proposed based on SURF feature matching. Assembly state and AR display state are solved by a novel sequential hybrid AR display control strategy. A synchronous multi-channel AR view output strategy is proposed based on QR matrix decomposition. Findings A prototype system has been developed, and case study is performed on an industrial product. Experiments are performed to verify the feasibility, efficiency and recognition accuracy of the proposed methods. Research limitations/implications The proposed system assists users to perform assembly tasks with automatic visual guidance and vision monitoring, avoiding distractions caused by redundant human–computer interactions. Practical implications All methods are integrated to work on only one head-worn device, making the proposed system portable and cheaper. The vision processing pipelines and the view output channels are reconfigurable for customization. Originality/value This paper proposes an interaction-free AR assembly assistance and monitoring system. Assembly behavior recognition and assembly completeness inspection methods are integrated to monitor the assembly state. A sequential hybrid AR display control strategy is proposed to contextually update the AR contents. A synchronous multi-channel AR view output strategy is proposed to fulfill different visualization needs.