MOSPPA: monitoring system for palletised packaging recognition and tracking

Abstract

The paper industry manufactures corrugated cardboard packaging, which is unassembled and stacked on pallets to be supplied to its customers. Human operators usually classify these pallets according to the physical features of the cardboard packaging. This process can be slow, causing congestion on the production line. To optimise the logistics of this process, we propose a visual recognition and tracking pipeline that monitors the palletised packaging while it is moving inside the factory on roller conveyors. Our pipeline has a two-stage architecture composed of Convolutional Neural Networks, one for oriented pallet detection and recognition, and another with which to track identified pallets. We carried out an extensive study using different methods for the pallet detection and tracking tasks and discovered that the oriented object detection approach was the most suitable. Our proposal recognises and tracks different configurations and visual appearance of palletised packaging, providing statistical data in real time with which to assist human operators in decision-making. We tested the precision-performance of the system at the Smurfit Kappa facilities. Our proposal attained an Average Precision (AP) of 0.93 at 14 Frames Per Second (FPS), losing only 1% of detections. Our system is, therefore, able to optimise and speed up the process of logistic distribution.

A Hybrid CNN-DSP Algorithm for Package Detection in Distance Maps

“…Naumann et al [34] developed an algorithm to reconstruct the 3D shape of individual parcels from a single RGB image, finding that although knowledge gained by training on synthetic data can be applied in the real world to a certain extent, reliable deployment in different real-world scenarios is still challenging. The system developed by Castaño Amoros et al [35] includes a module for detecting and recognizing separate pallets that contain unassembled corrugated cardboard packaging from top-view RGB images. Several conclusions can be drawn from the review of the datasets and models used in the discussed works in terms of the number of samples in the dataset, degree of variability, and model complexity.…”