Feature matching via local descriptors is one of the most fundamental problems in many computer vision tasks, as well as in the remote sensing image processing community. For example, in terms of remote sensing image registration based on the feature, feature matching is a vital process to determine the quality of transform model. While in the process of feature matching, the quality of feature descriptor determines the matching result directly. At present, the most commonly used descriptor is hand-crafted by the designer’s expertise or intuition. However, it is hard to cover all the different cases, especially for remote sensing images with nonlinear grayscale deformation. Recently, deep learning shows explosive growth and improves the performance of tasks in various fields, especially in the computer vision community. Here, we created remote sensing image training patch samples, named Invar-Dataset in a novel and automatic way, then trained a deep learning convolutional neural network, named DescNet to generate a robust feature descriptor for feature matching. A special experiment was carried out to illustrate that our created training dataset was more helpful to train a network to generate a good feature descriptor. A qualitative experiment was then performed to show that feature descriptor vector learned by the DescNet could be used to register remote sensing images with large gray scale difference successfully. A quantitative experiment was then carried out to illustrate that the feature vector generated by the DescNet could acquire more matched points than those generated by hand-crafted feature Scale Invariant Feature Transform (SIFT) descriptor and other networks. On average, the matched points acquired by DescNet was almost twice those acquired by other methods. Finally, we analyzed the advantages of our created training dataset Invar-Dataset and DescNet and gave the possible development of training deep descriptor network.

Forests cover about 30.6% of the Earth’s land area and constitute a critical terrestrial ecosystem. Forest cover change (FCC) is highly relevant to the global carbon cycle, water supplies, biodiversity richness, and for understanding the rates and causes of land use change. As global ecological environment changes and population growth and ensuing human activities intensify, global forest cover (GFC) has decreased from $4128\times {10}^6\mathrm{ha}$ in 1990 to $3999\times {10}^6\mathrm{ha}$ in 2015. There was a net loss of some $129\times {10}^6\mathrm{ha}$ of forest between 1990 and 2015, which was about the size of South Africa, representing an annual net loss rate of 0.13%.¹ Yet deforestation, or forest conversion to other land use, is more complicated than that. Therefore, forest cover mapping has important practical significance and scientific value in terms of the spatial and temporal detailed change on global-scale forest.²

In the context of carbon neutrality, forest cover change detection has become a key topic of global environmental monitoring. As a large-scale monitoring technique, remote sensing has received obvious attention in various land cover observation applications. With the rapid development of deep learning, remote sensing change detection combined with deep neural network has achieved high accuracy. In this paper, the deep neural network is used to study forest cover change with Landsat images. The main research ideas are as follows. (1) A Siamese detail difference neural network is proposed, which uses a combination of concatenate weight sharing mode and subtract weight sharing mode to improve the accuracy of forest cover change detection. (2) The self-inverse network is introduced to detect the change of forest increase by using the sample data set of forest decrease, which realizes the transfer learning of the sample data set and improves the utilization rate of the sample data set. The experimental results on Landsat 8 images show that the proposed method outperforms several Siamese neural network methods in forest cover change extraction.

With the continuous advancement of technology, the number of vehicles in cities is increasing, and traffic congestion is becoming more common. To enhance the efficiency and effectiveness of urban transportation network allocation, a constraint method is introduced to improve the Nondominated Sorting Genetic Algorithm III. By dynamically adjusting and optimizing the mayfly algorithm, the two are integrated to ultimately construct a dynamic urban transportation network allocation method. Combining the advantages of both algorithms, the population and optimization objectives are dynamically adjusted to achieve multiobjective optimization, including reducing travel time, congestion, and environmental pollution. Through comparative experimental testing of performance, the findings denote that the proposed dynamic urban transportation network allocation method has the highest super volume, which is 0.758. The generational distance, inverted generational distance, and spacing are the lowest, at 0.156, 0.179, and 0.113, respectively. The experimental findings indicate that the proposed allocation method improves the efficiency and effectiveness of urban transportation network allocation through precise optimization of transportation network allocation and has strong applicability. Research provides scientific decision support for transportation planning and management by effectively finding a balance between multiple objectives in dynamic urban transportation network allocation.