Deep Learning-based Object Recognition for Counting Car Components to Support Handling and Packing Processes in Automotive Supply Chains

Abstract

Abstract Complex distributed supply chains, e.g., in the automotive industry, need to cope with high product variety. Digital image processing can use specific geometric and optical properties of parts and components for determining their type and thus needs no external markers. It is thus well applicable to supply chain processes that involve direct handling of many different product components and need no individual identification of items. An example of such a process is counting items of different product types during packing. In this paper, we use deep learning-based digital image processing methods in order to distinguish and count the number of objects of two different types of automotive components in standardized transport bins, detected by time-of-flight (ToF) depth sensors. Classical watershed object counting methods are adapted to depth data and support the fast generation of training data for the deep learning-based classification methods. The proposed method is applied to an automotive supply chain, and it is demonstrated that car components can be counted with good reliability during packing into transport bins. Thus, digital image processing can be useful to supplement auto-identification and sensor technologies and complete digital end-to-end monitoring of supply chains.