Camera-assisted Pick-by-feel

Abstract

In this contribution a novel system to support order pickers in warehouses is introduced. In contrast to existing solutions it utilizes the tactile perception in order to reduce the systems impact on the visual and auditive senses. Therefore, a smartwatch and a low-cost camera which are both worn by the picker are combined with activity and object recognition methods for surveying the picking process. The activity recognition is used in order to determine whether an object is picked. Then, barcode detection and a CNN (Convolutional Neural Network) based object recognition approach are employed for recognizing whether the correct item is chosen. Beside the conceptional work, implementation details and evaluation results under realistic conditions and on a publicly available dataset are presented.