摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-调查人员发布了关于人工智能的新报告。据新闻通讯社记者从马来西亚雪兰莪发回的新闻报道，研究表明：“通过语义分段网络进行的深度学习技术已被广泛用于自然灾害分析和响应，这些实现的基础依赖于卷积神经网络(CNNs)，该网络能够准确和精确地识别和定位卫星图像或其他形式的遥感数据中各自感兴趣的区域。”从而协助灾害评估、救援规划和重建工作。我们的新闻记者从马来西亚Kebangsaan大学的研究中获得了一句话：“大多数基于CNN的深度学习模型遇到了与空间信息丢失和特征表征不足有关的挑战。这是由于它们捕捉多个Iscale上下文信息的层设计不够优化，以及它们在汇集过程中没有包括最优的语义信息。在CNN的早期层中，网络编码基本的语义表示，如边和角，而随着网络向后期发展，它编码更复杂的语义特征，如复杂的几何形状。本文综述了深度学习方法在遥感图像分割中的研究进展,主要是从多个层次的特征表示中提取特征,这是因为当将简单的特征图和复杂的特征图结合起来时,分割网络通常能获得较好的结果。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ar tificial intelligence. According to news originating from Selangor, Malaysia, by NewsRx correspondents, research stated, “Deep learning techniques through seman tic segmentation networks have been widely used for natural disaster analysis an d response. The underlying base of these implementations relies on convolutional neural networks (CNNs) that can accurately and precisely identify and locate th e respective areas of interest within satellite imagery or other forms of remote sensing data, thereby assisting in disaster evaluation, rescue planning, and re storation endeavours.” Our news reporters obtained a quote from the research from Universiti Kebangsaan Malaysia: “Most CNN-based deep-learning models encounter challenges related to the loss of spatial information and insufficient feature representation. This is sue can be attributed to their suboptimal design of the layers that capture mult iscale-context information and their failure to include optimal semantic informa tion during the pooling procedures. In the early layers of CNNs, the network enc odes elementary semantic representations, such as edges and corners, whereas, as the network progresses toward the later layers, it encodes more intricate seman tic characteristics, such as complicated geometric shapes. In theory, it is adva ntageous for a segmentation network to extract features from several levels of s emantic representation. This is because segmentation networks generally yield im proved results when both simple and intricate feature maps are employed together . This study comprehensively reviews current developments in deep learning metho dologies employed to segment remote sensing images associated with natural disas ters.”
NETL
NSTL