In the rapidly evolving world of smart buildings and digital twins, a groundbreaking study led by Dr. Zhenhui Qiu from the School of Robotics at Xi’an Jiaotong-Liverpool University (XJTLU) is set to revolutionize how we construct and utilize indoor digital twins. The research, published in the prestigious “The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences” (translated as “International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences”), addresses critical challenges in creating accurate and comprehensive indoor digital models, which are vital for smart-building services such as asset tracking, space planning, and AR/VR navigation.
The study tackles a significant limitation in current LiDAR technology: the trade-off between accuracy and coverage. Fixed terrestrial laser scanners (TLSs) provide high precision but leave gaps due to occlusions, while handheld mobile laser scanners (HMLSs) offer broader coverage but suffer from geometric instability and color drift. Dr. Qiu and his team have developed an innovative solution—an adaptive voxel-based fusion pipeline that combines the strengths of both TLS and HMLS.
“Our method ensures geometric consistency and color accuracy, which are crucial for creating reliable indoor digital twins,” Dr. Qiu explains. The process involves rigidly registering the handheld point cloud to the TLS reference using Iterative Closest Point, identifying and filling gaps in the TLS data with handheld points that meet strict geometric thresholds, and correcting color bias through a global linear RGB mapping refined locally with weighted regression. The final step involves blending colors across the TLS-handheld boundary to eliminate visible seams.
The results are impressive. The method recovers 85.7% of missing surfaces, reduces the global point-to-plane RMSE by 14.8%, and improves mean color difference by 22.2%. These high-fidelity, color-consistent indoor models provide facility managers and planners with reliable data for maintenance scheduling, occupancy analysis, and long-term space optimization.
The implications for the energy sector are profound. Accurate indoor digital twins can enhance energy efficiency by optimizing space utilization and identifying areas for improvement in building design and maintenance. “This technology can help facility managers make data-driven decisions, leading to significant energy savings and improved operational efficiency,” Dr. Qiu adds.
As the demand for smart buildings continues to grow, the ability to create accurate and comprehensive indoor digital twins will become increasingly important. Dr. Qiu’s research represents a significant step forward in this field, offering a robust solution that combines the best of both TLS and HMLS technologies. The study not only advances the state-of-the-art in digital twin construction but also paves the way for future developments in smart-building services and energy management.
In an era where data-driven decision-making is key, this research underscores the potential of advanced technologies to transform the way we interact with and manage our built environment. As Dr. Qiu’s work gains traction, it is poised to shape the future of indoor digital twins, offering new opportunities for innovation and efficiency in the energy sector and beyond.