Foreign objects on power transmission lines carry a significant risk of triggering large-scale power interruptions which may have serious consequences for daily life if they are not detected and handled in time. To accurately detect foreign objects on power transmission lines, this paper proposes a TL-Yolo method based on the Yolov8 framework. Firstly, we design a full-dimensional dynamic convolution (ODConv) module as a backbone network to enhance the feature extraction capability, thus retaining richer semantic content and important visual features. Secondly, we present a feature fusion framework combining a weighted bidirectional feature pyramid network (BiFPN) and multiscale attention (MSA) module to mitigate the degradation effect of multiscale feature representation in the fusion process, and efficiently capture the high-level feature information and the core visual elements. Thirdly, we utilize a lightweight GSConv cross-stage partial network (GSCSP) to facilitate efficient cross-level feature fusion, significantly reducing the complexity and computation of the model. Finally, we employ the adaptive training sample selection (ATSS) strategy to balance the positive and negative samples, and dynamically adjust the selection process of the training samples according to the current state and performance of the model, thus effectively reducing the object misdetection and omission. The experimental results show that the average detection accuracy of the TL-Yolo method reaches 91.30%, which is 4.20% higher than that of the Yolov8 method. Meanwhile, the precision and recall metrics of our method are 4.64% and 3.53% higher than those of Yolov8. The visualization results also show the superior detection performance of the TL-Yolo algorithm in real scenes. Compared with the state-of-the-art methods, our method achieves higher accuracy and speed in the detection of foreign objects on power transmission lines.

This paper is devoted to detect and classify intra-urban changes by jointly exploiting Sentinel-1 (S-1) SAR data and nighttime light data. By extracting urban extents and urban density maps from SAR data, changes in nighttime lights can be used to detect changes related to the level of activity in a specific portion of each urban areas. At the same time, changes in radar backscattering are prone to reveal changes in the two- and three-dimensional structures of the built-up. The combination of these multimodal datasets has already proved to be useful to discriminate urban change patterns at the city level. In this paper, instead, SAR datasets from S-1 are exploited, allowing the recognition of different intra-urban changes. Experimental results focus on fast growing (mega) cities in East Asia, allowing us to understand in a more detailed way how they are changing and evolving in all three dimensions. Examples for Nanjing, Shanghai, and Guangzhou (China), Saigon (Vietnam), and Vientiane (Laos) are discussed to prove this statement.

In this letter, an unsupervised 2-D and 3-D urban change detection scheme is proposed exploiting Quad-PolSAR data. Changes are extracted by segmenting the data into superpixels, to enhance the balance among change components and increase estimability of prior distributions. Positive and negative change components for built-up areas, in both the horizontal and the vertical directions, are properly extracted by assuming a multivariate Gaussian mixed model applied to a subset of polarimetric parameters at the superpixel level. The proposed method is tested on multitemporal Quad-PolSAR images and the results confirm its effectiveness. The selection of polarimetric decomposition measures that are most useful to the task is also experimentally justified.

During the last 20 years, fast urbanization activities have been highly concentrated in just few countries (e.g., China, India, and Nigeria) and have led to the emergence of large urban aggregations, with high population density. Still, very few researches have focused on this dynamic phenomenon with a global perspective using multisource remote sensing data. In this article, combining radar and spectral sensors of different spatial resolution, a novel approach based on a novel hierarchical biclustering technique is proposed and proved to be effective in discriminating the underlying change patterns without pre-estimating the number of clusters. To this aim, experimental results focused on newly emerging megalopolis in China, India, and Nigeria, as well as on the highly urbanized and stable Lombardy region in Italy, are presented. The analysis of the results allows us to understand, in a global and comparative perspective, the spatiotemporal differentiation of urban density and how cities are changing and evolving in the building volume and, to some extent, their economic level.

The strong urbanization impetus of developing countries leads to various urbanization phenomena such as building constructions, reconstructions, and demolitions. It is desirable to monitor and recognize these intraurban changes by utilizing temporal and spatial information in an automatic way. This may be useful, for example, to timely update urban information databases. The aim of this work is, therefore, to automatically extract first, and further recognize, change time series in sequences of SAR data with high-frequency acquisition. Specifically, SAR time-series segmentation and unsupervised classification are combined together to recognize areas with the same urban change pattern, by fully exploiting both the temporal and spatial dimensions. Experimental results in a fast-growing Chinese city show that the proposed approach is effective and able to characterize temporal patterns due to different kinds of intraurban changes.

In the last decade, the spatio-temporal patterns of PM_2.5 on various scales, ranging from global, continent, and country to regional levels, has been the focus of considerable studies. However, these studies on spatio-temporal variability have concentrated primarily on changes in the spatial distribution patterns of regional PM_2.5 concentrations and ignored temporal characteristics at a local site from a heterogeneous surface, such as local variability, persistence, and stability of PM_2.5 exposure. Understanding the temporal characteristics of PM_2.5 concentration changes at the local scale will help determine the local impacts of PM_2.5, such as local exposure risk and vulnerability to PM_2.5. This study aims to reveal the local characteristics of temporal variation at the scale of a prefecture-level city and its distinct-varying patterns from those at the provincial scale by using the annual satellite-derived PM_2.5 concentration product from 2000 to 2015. The evolutionary trends, stability, and persistence of annual changes were discovered with a set of time series analysis methods, such as linear regression analysis + F-test, coefficient of variation method, and Hurst index. This study uses PM_2.5 product data for a total of 16 years, from 2000 to 2015, and uses time series analysis methods, such as Theil–Sen median trend analysis + Mann–Kendall test, one-dimensional linear regression analysis + F-test, coefficient of variation method, and Hurst index, to reveal the temporal variation characteristics and spatial patterns of PM_2.5 in Jiangsu Province. The results show that the increasing trends or slopes of annual averaged PM_2.5 concentrations in Jiangsu Province are not consistent at the prefecture-level city scale, but they are consistent in northern, central and southern Jiangsu at a larger upward trend since 2000. The areas with significant increasing trends are concentrated in Xuzhou and Lianyungang and other northern cities. From the viewpoint of variability, the areas in medium and high variability are mainly aggregated in the areas north of the Yangtze River. According to the combination of persistence analysis and trend analysis, future variation in PM_2.5 concentrations indicates an inverse persistence for an increasing trend, meaning the air quality decline in Jiangsu will slow.