Distinctive Self-Similar Object Detection

TL;DR

This paper introduces a novel self-similarity based approach for detecting fire and smoke objects, leveraging fractal features to address shape variability and improve detection accuracy in practical fire prevention applications.

Contribution

It is the first to utilize the fractal self-similarity of fire and smoke for object detection, proposing a semi-supervised method with Hausdorff distance and a new evaluation framework.

Findings

Significant improvement in detection accuracy on fire and smoke datasets

Effective use of Hausdorff distance to measure self-similarity

Successful integration with YOLO and Faster R-CNN architectures

Abstract

Deep learning-based object detection has demonstrated a significant presence in the practical applications of artificial intelligence. However, objects such as fire and smoke, pose challenges to object detection because of their non-solid and various shapes, and consequently difficult to truly meet requirements in practical fire prevention and control. In this paper, we propose that the distinctive fractal feature of self-similar in fire and smoke can relieve us from struggling with their various shapes. To our best knowledge, we are the first to discuss this problem. In order to evaluate the self-similarity of the fire and smoke and improve the precision of object detection, we design a semi-supervised method that use Hausdorff distance to describe the resemblance between instances. Besides, based on the concept of self-similar, we have devised a novel methodology for evaluating this particular task in a more equitable manner. We have meticulously designed our network architecture based on well-established and representative baseline networks such as YOLO and Faster R-CNN. Our experiments have been conducted on publicly available fire and smoke detection datasets, which we have thoroughly verified to ensure the validity of our approach. As a result, we have observed significant improvements in the detection accuracy.