Xuesong Liu

Xuesong Liu, Tianyu Hao, Emmett J. Ientilucci

In controlled blasting operations, accurately detecting densely distributed tiny boreholes from far-view imagery is critical for operational safety and efficiency. However, existing detection methods often struggle due to small object scales, highly dense arrangements, and limited distinctive visual features of boreholes. To address these challenges, we propose an adaptive detection approach that builds upon existing architectures (e.g., YOLO) by explicitly leveraging consistent embedding representations derived through exponential moving average (EMA)-based statistical updates. Our method introduces three synergistic components: (1) adaptive augmentation utilizing dynamically updated image statistics to robustly handle illumination and texture variations; (2) embedding stabilization to ensure consistent and reliable feature extraction; and (3) contextual refinement leveraging spatial context for improved detection accuracy. The pervasive use of EMA in our method is particularly advantageous given the limited visual complexity and small scale of boreholes, allowing stable and robust representation learning even under challenging visual conditions. Experiments on a challenging proprietary quarry-site dataset demonstrate substantial improvements over baseline YOLO-based architectures, highlighting our method's effectiveness in realistic and complex industrial scenarios.

Xuesong Liu, Emmett J. Ientilucci

Efficient segmentation of smoke plumes is crucial for environmental monitoring and industrial safety, enabling the detection and mitigation of harmful emissions from activities like quarry blasts and wildfires. Accurate segmentation facilitates environmental impact assessments, timely interventions, and compliance with safety standards. However, existing models often face high computational demands and limited adaptability to diverse smoke appearances, restricting their deployment in resource-constrained environments. To address these issues, we introduce SmokeNet, a novel deep learning architecture that leverages multiscale convolutions and multiview linear attention mechanisms combined with layer-specific loss functions to handle the complex dynamics of diverse smoke plumes, ensuring efficient and accurate segmentation across varied environments. Additionally, we evaluate SmokeNet's performance and versatility using four datasets, including our quarry blast smoke dataset made available to the community. The results demonstrate that SmokeNet maintains a favorable balance between computational efficiency and segmentation accuracy, making it suitable for deployment in environmental monitoring and safety management systems. By contributing a new dataset and offering an efficient segmentation model, SmokeNet advances smoke segmentation capabilities in diverse and challenging environments.