GSO-Net benchmark advances visual safety checks at petrochemical sites
GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes
Computer Vision and Pattern Recognition
Summary
Keeping hazardous freight transfers safe at petrochemical hubs is very important but hard to do automatically because cameras often miss parts of the process. The authors created GSO-Net, a big collection of real video frames that show different steps and small details in the unloading process. This helps computers learn to recognize correct procedures from incomplete video. They tested current AI models and found they still struggle to see small but critical actions, especially when camera views are sparse. GSO-Net aims to help improve visual monitoring for safety in these dangerous operations.
What this means in practice
- •For logistics safety teams: Use the GSO-Net dataset to train vision systems that detect procedural compliance in hazardous freight unloading at petrochemical terminals.
- •For industrial ai developers: Develop or improve AI models for detailed state recognition in logistics systems using GSO-Net’s real-world, hierarchical video data.
Authors
Yu Xie, Bangshu Xiong, Zhibo Rao, Rui Gan, Chongxuan Liu, Zechu Ouyang
Abstract
Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints. In large infrastructure networks, cameras often operate under sparse round-robin polling, so transfer status must be inferred from incomplete observations and localized evidence. We present GSO-Net, a large-scale benchmark for visual understanding of standard operating procedures (SOPs) in petrochemical unloading scenarios. To our knowledge, GSO-Net is the first public benchmark dataset dedicated to visual SOP understanding in petrochemical hazardous-freight transfer scenarios. It contains over 50,000 independently sampled frames from 64 real expressway petrochemical logistics nodes and adopts an SOP-derived hierarchy linking 9 macroscopic procedural steps with 15 microscopic operational states. Two tasks are defined: joint detection of microscopic states and macroscopic steps as the core benchmark, and frame-level step classification as a diagnostic reference. Experiments with lightweight, transformer-based, open-vocabulary, and holistic models reveal a clear gap between object perception and transfer-stage understanding. Current models remain weak on contact-level state grounding, transient step recognition, and stage consistency, especially under sparse polling, tiny critical targets, and long-tailed operational evidence. GSO-Net provides a practical benchmark for fine-grained state perception and vision-based safety monitoring in hazardous freight transportation. The dataset is publicly available at https://github.com/yuxieHarrison/GSO-Net