Dual-Layer Density Estimation for Multiple Object Instance Detection

This paper introduces a dual-layer density estimation-based architecture for multiple object instance detection in robot inventory management applications. The approach consists of raw scale-invariant feature transform (SIFT) feature matching and key point projection. The dominant scale ratio and a reference clustering threshold are estimated using the first layer of the density estimation. A cascade of filters is applied after feature template reconstruction and refined feature matching to eliminate false matches. Before the second layer of density estimation, the adaptive threshold is finalized by multiplying an empirical coefficient for the reference value. The coefficient is identified experimentally. Adaptive threshold-based grid voting is applied to find all candidate object instances. Error detection is eliminated using final geometric verification in accordance with Random Sample Consensus (RANSAC). The detection results of the proposed approach are evaluated on a self-built dataset collected in a supermarket. The results demonstrate that the approach provides high robustness and low latency for inventory management application.