Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Benchmarking Multi-Scene Fire and Smoke Detection

Xiaoyi Han, Nan Pu, Zunlei Feng, Yijun Bei, Qifei Zhang, Lechao Cheng, Liang Xue

TL;DR

This work systematically gathers diverse resources from public sources to create a more comprehensive and refined FSD benchmark, and strategically expand scenes, relabel, and standardize existing public FSD datasets to ensure accuracy and consistency.

Abstract

The current irregularities in existing public Fire and Smoke Detection (FSD) datasets have become a bottleneck in the advancement of FSD technology. Upon in-depth analysis, we identify the core issue as the lack of standardized dataset construction, uniform evaluation systems, and clear performance benchmarks. To address this issue and drive innovation in FSD technology, we systematically gather diverse resources from public sources to create a more comprehensive and refined FSD benchmark. Additionally, recognizing the inadequate coverage of existing dataset scenes, we strategically expand scenes, relabel, and standardize existing public FSD datasets to ensure accuracy and consistency. We aim to establish a standardized, realistic, unified, and efficient FSD research platform that mirrors real-life scenes closely. Through our efforts, we aim to provide robust support for the breakthrough and development of FSD technology. The project is available at \href{https://xiaoyihan6.github.io/FSD/}{https://xiaoyihan6.github.io/FSD/}.

Benchmarking Multi-Scene Fire and Smoke Detection

TL;DR

This work systematically gathers diverse resources from public sources to create a more comprehensive and refined FSD benchmark, and strategically expand scenes, relabel, and standardize existing public FSD datasets to ensure accuracy and consistency.

Abstract

The current irregularities in existing public Fire and Smoke Detection (FSD) datasets have become a bottleneck in the advancement of FSD technology. Upon in-depth analysis, we identify the core issue as the lack of standardized dataset construction, uniform evaluation systems, and clear performance benchmarks. To address this issue and drive innovation in FSD technology, we systematically gather diverse resources from public sources to create a more comprehensive and refined FSD benchmark. Additionally, recognizing the inadequate coverage of existing dataset scenes, we strategically expand scenes, relabel, and standardize existing public FSD datasets to ensure accuracy and consistency. We aim to establish a standardized, realistic, unified, and efficient FSD research platform that mirrors real-life scenes closely. Through our efforts, we aim to provide robust support for the breakthrough and development of FSD technology. The project is available at \href{https://xiaoyihan6.github.io/FSD/}{https://xiaoyihan6.github.io/FSD/}.

Paper Structure

This paper contains 11 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Multi-Scene Fire and Smoke Detection Benchmark
  4. Fire and Smoke Detection Datasets Processing
  5. Baselines
  6. Experiments and Analysis
  7. Setting
  8. Basic Experiments
  9. Performance Verification
  10. Summary
  11. Conclusion

Figures (3)

  • Figure 1: Illustrations of several Fire and Smoke Detection (FSD) datasets statistics. (a) represents the statistics comparison of several FSD datasets scenes. (b) provides more detailed statistics for our benchmark. In (b), the area of the sector corresponds to the number of scenes. Additionally, the total number of scenes equals 2731, as displayed in (a).
  • Figure 2: Different Scenes in Our Benchmark MS-FSDB. (a) represents the Electric Power Station Scene. (b) represents the Indoor Clutter Scene. (c) represents the Air crush Scene. (d) represents the Residential Building Scene.
  • Figure 3: For ordinary fire and smoke, some of the difficulties encountered in detection are addressed using our method. (a) represents the false results of the general detection. (b) represents the correct results of our method. In the diagram, blue boxes represent ground truth, and red boxes represent predicted results.