Abstract
Fire safety consists of a complex pipeline, and it is a very important topic of concern. One of its frontal parts are the smoke detectors, which are supposed to provide an alarm prior to a massive fire appears. As they are often difficult to reach due to high ceilings or problematic locations, an automatic inspection system would be very beneficial as it could allow faster revisions, prevent workers from dangerous work in heights, and make the whole process cheaper. In this study, we present the smoke detector recognition part of the automatic inspection system, which could easily be integrated to the drone system. As part of our research, we compare two popular convolutional-based object detectors YOLOv11 and SSD widely used on embedded devices together with the state-of-the-art transformer-based RT-DETRv2 with the backbones of different sizes. Due to a complicated way of collecting a sufficient amount of data for training in the real-world environment, we also compare several training strategies using the real and semi-synthetic data together with various augmentation methods. To achieve a robust testing, all models were evaluated on two test datasets with an expected and difficult appearance of the smoke detectors including motion blur, small resolution, or not complete objects. The best performing detector is the YOLOv11n, which reaches the average mAP@0.5 score of 0.884. Our code, pretrained models and dataset are publicly available.
Abstract (translated)
消防安全涉及复杂的管道系统，是一个非常重要的关注课题。其前端部件之一是烟雾探测器，旨在火灾大规模发生前发出警报。由于高天花板或位置特殊导致探测器往往难以触及，自动检测系统将非常有益——它能实现更快速的检修、避免工人在高空危险作业，并降低整体成本。本研究提出了可轻松集成至无人机系统的自动检测方案中的烟雾探测器识别部分。作为研究的一部分，我们比较了两种广泛用于嵌入式设备的流行卷积目标检测器YOLOv11与SSD，以及采用不同尺寸主干网络的最先进Transformer架构检测器RT-DETRv2。由于在真实环境中采集足量训练数据过程复杂，我们还对比了使用真实数据与半合成数据的多种训练策略，并结合不同数据增强方法。为进行稳健测试，所有模型在两个测试数据集上进行了评估，这些数据集包含烟雾探测器在预期及困难场景下的出现情况，如运动模糊、低分辨率或不完整物体。表现最佳的检测器是YOLOv11n，其平均mAP@0.5得分达到0.884。本研究代码、预训练模型及数据集均已公开。
URL
https://arxiv.org/abs/2603.24850
