Researchers are doing intensive work on satellite images due to the information it contains with the development of computer vision algorithms and the ease of accessibility to satellite images. Building segmentation of satellite images can be used for many potential applications such as city, agricultural, and communication network planning. However, since no dataset exists for every region, the model trained in a region must gain generality. In this study, we trained several models in China and post-processing work was done on the best model selected among them. These models are evaluated in the Chicago region of the INRIA dataset. As can be seen from the results, although state-of-art results in this area have not been achieved, the results are promising. We aim to present our initial experimental results of a building segmentation from satellite images in this study.

This paper presents the preliminary findings of a semi-supervised segmentation method for extracting roads from sattelite images. Artificial Neural Networks and image segmentation methods are among the most successful methods for extracting road data from satellite images. However, these models require large amounts of training data from different regions to achieve high accuracy rates. In cases where this data needs to be of more quantity or quality, it is a standard method to train deep neural networks by transferring knowledge from annotated data obtained from different sources. This study proposes a method that performs path segmentation with semi-supervised learning methods. A semi-supervised field adaptation method based on pseudo-labeling and Minimum Class Confusion method has been proposed, and it has been observed to increase performance in targeted datasets.

Transfer Learning methods are widely used in satellite image segmentation problems and improve performance upon classical supervised learning methods. In this study, we present a semantic segmentation method that allows us to make land cover maps by using transfer learning methods. We compare models trained in low-resolution images with insufficient data for the targeted region or zoom level. In order to boost performance on target data we experiment with models trained with unsupervised, semi-supervised and supervised transfer learning approaches, including satellite images from public datasets and other unlabeled sources. According to experimental results, transfer learning improves segmentation performance 3.4% MIoU (Mean Intersection over Union) in rural regions and 12.9% MIoU in urban regions. We observed that transfer learning is more effective when two datasets share a comparable zoom level and are labeled with identical rules; otherwise, semi-supervised learning is more effective by using the data as unlabeled. In addition, experiments showed that HRNet outperformed building segmentation approaches in multi-class segmentation.

Extracting building heights from satellite images is an active research area used in many fields such as telecommunications, city planning, etc. Many studies utilize DSM (Digital Surface Models) generated with lidars or stereo images for this purpose. Predicting the height of the buildings using only RGB images is challenging due to the insufficient amount of data, low data quality, variations of building types, different angles of light and shadow, etc. In this study, we present an instance segmentation-based building height extraction method to predict building masks with their respective heights from a single RGB satellite image. We used satellite images with building height annotations of certain cities along with an open-source satellite dataset with the transfer learning approach. We reached, the bounding box mAP 59, the mask mAP 52.6, and the average accuracy value of 70% for buildings belonging to each height class in our test set.

深度神经网络（DNNS）的端到端培训在越来越多的应用程序中产生了最先进的性能状态，但它并不能洞悉提取的功能或控制所提取的功能。我们在这里报告了一种有希望的神经启发的方法，可以用更稀疏和更强的激活进行DNN。我们使用标准的随机梯度培训，以促进HEBBIAN（“ Fire dise Coled”，“ Wire dide”）更新的端到端判别成本功能，以及剩余神经元的反Hebbian更新。我们使用激活的分裂归一化（使用强输出抑制弱输出），以及隐式$ \ ell_2 $归一化神经元权重的标准化。在CIFAR-10上进行标准图像分类任务的实验表明，相对于基线端到端训练的体系结构，我们提出的体系结构（a）导致稀疏激活（仅略有妥协准确性），（b）表现出更健壮性噪声（不接受嘈杂数据训练），（c）对对抗性扰动表现出更大的鲁棒性（没有对抗性训练）。