Automated Counting of Stacked Objects in Industrial Inspection

TL;DR

This paper introduces a novel 3D visual counting method for stacked objects in industrial inspection, combining geometric reconstruction and deep learning to accurately count occluded items in containers.

Contribution

It presents a new approach that decomposes 3D counting into geometry estimation and occupancy analysis, effectively handling occlusion and irregular stacking.

Findings

Accurately counts objects in synthetic and real-world data

Robust performance under occlusion and irregular stacking

Validates effectiveness with manually verified counts

Abstract

Visual object counting is a fundamental computer vision task in industrial inspection, where accurate, high-throughput inventory tracking and quality assurance are critical. Moreover, manufactured parts are often too light to reliably deduce their count from their weight, or too heavy to move the stack on a scale safely and practically, making automated visual counting the more robust solution in many scenarios. However, existing methods struggle with stacked 3D items in containers, pallets, or bins, where most objects are heavily occluded and only a few are directly visible. To address this important yet underexplored challenge, we propose a novel 3D counting approach that decomposes the task into two complementary subproblems: estimating the 3D geometry of the stack and its occupancy ratio from multi-view images. By combining geometric reconstruction with deep learning-based depth analysis, our method can accurately count identical manufactured parts inside containers, even when they are irregularly stacked and partially hidden. We validate our 3D counting pipeline on large-scale synthetic and diverse real-world data with manually verified total counts, demonstrating robust performance under realistic inspection conditions.