Gunho Sohn
Dr. Gunho Sohn is a distinguished Associate Professor and Department Chair at the Department of Earth and Science and Engineering at York University. He is also the Inaugural Director of the Mobility Innovation Centre (MOVE). Dr. Sohn's innovative research in urban digital twinning, which combines computer vision, and machine learning, has garnered acclaim for making urban environments smarter, safer, and more sustainable.
Sessions
The proliferation of high-resolution satellite imagery has dramatically transformed urban planning, disaster response, and environmental monitoring domains. A persistent challenge, however, is the precise extraction and delineation of building footprints, as traditional methods often yield results with irregular shapes and misalignments. To address these limitations, we present CornerRegNet, a pioneering deep neural network designed to predict oriented building corners and subsequently regularize building footprints derived from satellite imagery.
Central to CornerRegNet's design is its unique ability to harness oriented building corners as primary anchoring points. This approach significantly streamlines and refines the shape of the extracted building footprints. Using advanced multi-modal autoencoders, CornerRegNet adeptly embeds a blend of corner features, their inherent orientations, and overarching semantic context. This intricate fusion of features allows the network to capture micro-level details and macro-level building structural context.
Enhancing the accuracy of corner prediction, the model incorporates active rotating filters. These filters, combined with uniquely devised equivariant convolutions, ensure that the predicted corners are not only spatially correct but also maintain their intended orientation concerning the building's overall layout.
A pivotal component of CornerRegNet is the integrated Graph Convolution Network (GCN). This GCN is instrumental in iteratively refining the positions of corners from the preliminary footprints. Further, the in-built shape regularizer within the GCN aids in achieving architecturally consistent and coherent footprints, effectively minimizing typical extraction anomalies.
In comparative evaluations, CornerRegNet stands out, consistently outperforming contemporary models. The network's resilience in managing and regularizing building shapes is a distinguishing attribute, even under challenging scenarios marked by occlusions.
In conclusion, CornerRegNet represents a unique advancement in building footprint extraction from satellite imagery. Its unique combination of corner orientation prediction and shape regularization techniques sets new standards for accuracy, efficiency, and architectural interpretability.
This research delves into the evolving interactions between sidewalk delivery robots and pedestrians within urban environments, focusing on the dual objectives of pedestrian safety and effective robot navigation in shared spaces. A comprehensive 3D digital twin model, replicating real-world urban settings, was designed to simulate the multifaceted engagements between humans, robots, and the urban fabric. Incorporated within this simulation was the Pedestrian Aware Model (PAM), a multi-agent system, employed to mimic both robot and human movements.
Employing an agent-based modeling approach, a series of scenarios involving pedestrians, wheelchair users, and robots coexisting in sidewalk spaces were dissected. The salient revelation from this study is the non-contributory role of robots to sidewalk congestion. Through programmed safety buffer zones, robots not only ensure pedestrian safety but also facilitate streamlined navigation, hinting at a feasible harmonious integration.
Despite this, the study unearthed certain challenges. Robots were predominantly implicated in collisions, whereas pedestrians often infringed upon set distance thresholds, emphasizing the imperative for enhanced strategic measures to alleviate these risks. However, the overarching inference remains optimistic: with judicious design and continuous research, robots have the potential to integrate seamlessly with pedestrians, enriching the urban milieu. The simulation model posited in this study stands as a pivotal resource for urban planners and policymakers, guiding them in formulating strategies and policies for smooth robot-human cohabitation.
Quantitative analyses further cement the significance of this research, underscoring nuances like the importance of ample safety buffers around robots to minimize collisions and enhance sidewalk traffic fluidity. In essence, this research pioneers in illuminating the pathways for optimized robot-human coexistence in bustling urban settings.