ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments

2026-06-22

AI Summary

This work addresses the challenge of degraded depth perception in robotic systems operating in harsh construction environments—such as shotcrete applications—where high turbidity and low illumination severely impair visual sensing. To this end, the authors present the first large-scale multimodal dataset tailored to such scenarios, comprising 11,252 temporally synchronized stereo RGB image pairs and LiDAR point clouds, with 220 samples meticulously annotated. The data were acquired using a fused stereo vision and LiDAR setup under realistic, high-interference working conditions, ensuring high-fidelity synchronization. A lightweight point cloud annotation tool was also developed to support efficient labeling. This dataset fills a critical gap in industrial-grade visual perception under adverse conditions and provides substantial support for the development and evaluation of algorithms in depth estimation, stereo matching, and depth completion.

Abstract

We introduce ShotcreteDepth, a bi-modal dataset from the construction domain that captures both an active shotcreting process and general construction environments. The dataset comprises stereo RGB imagery and LiDAR point clouds acquired under harsh real-world conditions, including high turbidity and poor illumination. Such conditions adversely affect sensor measurements, leading to incomplete and noisy observations that pose significant challenges for perception systems in autonomous applications. Alongside the dataset, we release a lightweight annotation tool designed for time-efficient labeling of LiDAR point clouds. ShotcreteDepth consists of 11,252 temporally synchronized data samples, of which 220 are annotated for evaluation purposes. The dataset supports research in stereo matching, depth completion, and depth estimation under conditions that closely reflect the operational complexities found in industrial settings. Project repository: https://github.com/dtu-pas/shotcrete-depth

Problem

• shotcrete construction
• depth perception
• sensor noise
• harsh environments
• autonomous robotics

Innovation

• bi-modal dataset
• shotcrete construction
• LiDAR point clouds
• depth perception
• robust stereo matching