Volume estimation of merchandise using multiple range cameras

The ability of fast and automatic volume measurement of merchandise is of paramount importance in logistics. In this paper, we address the problem of volume estimation of goods stacked on pallets and transported in pallet trucks. Practical requirements of this industrial application are that the load of the moving pallet truck has to be measured in real-time, and that the measurement system should be non-invasive and non-contact, as well as robust and accurate. The main contribution of this paper is the design of simple, flexible, fast and robust algorithms for volume estimation. A significant feature of these algorithms is that they can be used in industrial environments and that they perform properly even when they use the information provided by different range devices working simultaneously. In addition, we propose a novel perception system for volume measurement consisting of a heterogeneous set of range sensors based on different technologies, such as time of flight and structured light, working simultaneously. Another key point of our proposal is the investigation of the performance of these sensors in terms of precision and accuracy under a diverse set of conditions. We also analyse their interferences and performance when they operate at the same time. Then, the analysis of this study is used to determine the final configuration of the cameras for the perception system. Real experiments proof the performance and reliability of the approach and demonstrate its validity for the industrial application considered.