Nemo: An Open-Source Transformer-Supercharged Benchmark for Fine-Grained Wildfire Smoke Detection
Nemo: An Open-Source Transformer-Supercharged Benchmark for Fine-Grained Wildfire Smoke Detection
复制标题
DOI：
10.3390/rs14163979
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Amirhessam Yazdi;Heyang Qin;Connor B. Jordan;Lei Yang;Feng Yan
中科院分区：
文献类型：
--
作者：
Amirhessam Yazdi;Heyang Qin;Connor B. Jordan;Lei Yang;Feng Yan
基于深度学习 (DL) 的对象检测算法可以极大地造福于整个社区的灭火、推进气候智能以及减少有害烟雾颗粒引起的健康并发症。现有的基于深度学习的技术主要基于卷积网络，已被证明在野火检测方面是有效的。然而，仍有改进的空间。首先，现有方法往往具有一些商业方面，公开可用的数据和模型有限。此外，旨在在初期阶段检测野火的研究很少。此阶段的烟柱往往较小、较浅，而且通常远离视线，能见度较低。这使得寻找和标记足够的数据来训练有效的深度学习模型非常具有挑战性。最后，卷积算子固有的局部性限制了它们对图像中对象之间的远程相关性进行建模的能力。最近，编码器-解码器转换器已经成为自然语言处理之外的有趣解决方案，可以通过自注意力机制和相互注意力机制来帮助捕获全局依赖关系。我们提出 Nemo：一组不断发展的、免费的开源数据集，以标准 COCO 格式处理，以及野火烟雾和细粒度烟雾密度探测器，供研究社区使用。我们将 Facebook 的 DEtection TRansformer (DETR) 应用于野火检测，这导致了一种更简单的技术，其中检测不依赖于卷积滤波器和锚点。 Nemo 是第一个针对野火烟雾密度检测和针对早期阶段量身定制的基于 Transformer 的野火烟雾检测的开源基准。两种流行的对象检测算法（Faster R-CNN 和 RetinaNet）被用作广泛评估的替代方案和基线。我们的结果证实了基于变压器的方法在不同物体尺寸的野火烟雾检测中具有卓越的性能。此外，我们还使用来自公共 HPWREN 数据库的 95 个野火视频序列测试了我们的模型。我们的模型检测到 97.9% 的火灾处于初期阶段，80% 的火灾在开始后 5 分钟内检测到。平均而言，我们的模型在开始后 3.6 分钟内检测到野火烟雾，优于基线。
Deep-learning (DL)-based object detection algorithms can greatly benefit the community at large in fighting fires, advancing climate intelligence, and reducing health complications caused by hazardous smoke particles. Existing DL-based techniques, which are mostly based on convolutional networks, have proven to be effective in wildfire detection. However, there is still room for improvement. First, existing methods tend to have some commercial aspects, with limited publicly available data and models. In addition, studies aiming at the detection of wildfires at the incipient stage are rare. Smoke columns at this stage tend to be small, shallow, and often far from view, with low visibility. This makes finding and labeling enough data to train an efficient deep learning model very challenging. Finally, the inherent locality of convolution operators limits their ability to model long-range correlations between objects in an image. Recently, encoder–decoder transformers have emerged as interesting solutions beyond natural language processing to help capture global dependencies via self- and inter-attention mechanisms. We propose Nemo: a set of evolving, free, and open-source datasets, processed in standard COCO format, and wildfire smoke and fine-grained smoke density detectors, for use by the research community. We adapt Facebook’s DEtection TRansformer (DETR) to wildfire detection, which results in a much simpler technique, where the detection does not rely on convolution filters and anchors. Nemo is the first open-source benchmark for wildfire smoke density detection and Transformer-based wildfire smoke detection tailored to the early incipient stage. Two popular object detection algorithms (Faster R-CNN and RetinaNet) are used as alternatives and baselines for extensive evaluation. Our results confirm the superior performance of the transformer-based method in wildfire smoke detection across different object sizes. Moreover, we tested our model with 95 video sequences of wildfire starts from the public HPWREN database. Our model detected 97.9% of the fires in the incipient stage and 80% within 5 min from the start. On average, our model detected wildfire smoke within 3.6 min from the start, outperforming the baselines.