Jia-Rui Lin

Jia-Rui Lin

Associate Professor

Image Dataset for Indoor Fire Load Recognition

Published:

To the best of our knowledge, we developed and opened the first image dataset for the detection and segmentation of indoor fire loads. With in the dataset, there are 8858 instances in 1015 images labelled according to their materials (such as fabric, wood, plastic, etc.) and combustibility, which are quite useful for indoor fire load estimation, resilience assessment, etc. We also developed a Mask-RCNN-based method for indoor fire load recognition, ref to our paper for details. Source code and dataset are also available on github for future invesigations.

The dataset is also pubshed in IEEE DataPort, and you can cite the dataset as follows:

Lin, J.R.*, Zhou, Y.C., Yan, K.C., Hu, Z.Z. (2022). IDFire: Image Dataset for Indoor Fire Load Recognition. IEEE Dataport, doi: 10.21227/qkk3-2145

Leave a Comment

You May Also Enjoy

SODA: Site Object Detection dAtaset for Deep Learning in Construction

Published:

With collaboration with Dr. Yichuan Deng from South China University of Technology, we developed a large-scale image dataset for deep learning based site object detection, the dataset contains images taken from different view angles and ambient lighting conditions, and covers various objects such workers, equipments, materials, etc.

ART(AutoRuleTransform): Opensource Dataset and Algorithms for Automated Rule Interpretation of Building Codes

Published:

For the digitalization and automated interpretation of regulatory documents, our team developed and opensourced the first large scale dataset in Chinese for automated rule transformation. Corresponding algorithms proposed for rule interpretation are also opensourced. Various types of clauses, including simple clauses, complex clauses with multiple constraints, high-order constraints and implicit properties are considered when developing the dataset and algorithms, which laid a solid foundation for future explorations.