Change Detection (CD) provides a research basis for environmental monitoring, urban expansion and reconstruction as well as disaster assessment, by identifying the changes of ground objects in different time periods. Traditional CD focused on the Binary Change Detection (BCD), focusing solely on the change and no-change regions. Due to the dynamic progress of earth observation satellite techniques, the spatial resolution of remote sensing images continues to increase, Multi-class Change Detection (MCD) which can reflect more detailed land change has become a hot research direction in the field of CD. Although many scholars have reviewed change detection at present, most of the work still focuses on BCD. This paper focuses on the recent progress in MCD, which includes five major aspects: challenges, datasets, methods, applications and future research direction. Specifically, the background of MCD is first introduced. Then, the major difficulties and challenges in MCD are discussed and delineated. The benchmark datasets for MCD are described, and the available open datasets are listed. Moreover, MCD is further divided into three categories and the specific techniques are described, respectively. Subsequently, the common applications of MCD are described. Finally, the relevant literature in the main journals of remote sensing in the past five years are analyzed and the development and future research direction of MCD are discussed. This review will help researchers understand this field and provide a reference for the subsequent development of MCD. Our collections of MCD benchmark datasets are available at: https://zenodo.org/record/6809804#.YsfvxXZByUk

Luojia 1-01 satellite, launched on 2 June 2018, provides a new data source of nighttime light at 130 m resolution and shows potential for mapping urban extent. In this paper, using Luojia 1-01 and VIIRS nighttime light imagery, we compared several methods for extracting urban areas, including Human Settlement Index (HSI), Simple Thresholding Segmentation (STS) and SVM supervised classification. According to the accuracy assessment, the HSI method using LJ1-01 data had the best performance in urban extent extraction, which presented the largest Kappa Coefficient value, 0.834, among all the results. For the urban areas extracted by VIIRS based HSI method, the largest Kappa Coefficient value was 0.772. In contrast, the largest Kappa Coefficient values obtained by STS method were 0.79 and 0.7512 respectively when using LJ1-01 and VIIRS data, while for SVM method the values were 0.7829 and 0.7486 when using Landsat-LJ and Landsat-VIIRS composite data respectively. The experimented results demonstrated that the utilization of nighttime light imagery can largely improve the accuracy of urban extent extraction and LJ1-01 data, with a higher resolution and more abundant spatial information, can lead to better identification results than its predecessors.

Coronavirus Disease 2019 (COVID-19) is a highly infectious virus that has created a health crisis for people all over the world. Social distancing has proved to be an effective non-pharmaceutical measure to slow down the spread of COVID-19. As unmanned aerial vehicle (UAV) is a flexible mobile platform, it is a promising option to use UAV for social distance monitoring. Therefore, we propose a lightweight pedestrian detection network to accurately detect pedestrians by human head detection in real-time and then calculate the social distancing between pedestrians on UAV images. In particular, our network follows the PeleeNet as backbone and further incorporates the multi-scale features and spatial attention to enhance the features of small objects, like human heads. The experimental results on Merge-Head dataset show that our method achieves 92.22% AP (average precision) and 76 FPS (frames per second), outperforming YOLOv3 models and SSD models and enabling real-time detection in actual applications. The ablation experiments also indicate that multi-scale feature and spatial attention significantly contribute the performance of pedestrian detection. The test results on UAV-Head dataset show that our method can also achieve high precision pedestrian detection on UAV images with 88.5% AP and 75 FPS. In addition, we have conducted a precision calibration test to obtain the transformation matrix from images (vertical images and tilted images) to real-world coordinate. Based on the accurate pedestrian detection and the transformation matrix, the social distancing monitoring between individuals is reliably achieved.

The accurate location of clouds in images is prerequisite for many high-resolution satellite imagery applications such as atmospheric correction, land cover classifications, and target recognition. Thus, we propose a novel approach for cloud detection using machine learning and multi-feature fusion based on a comparative analysis of typical spectral, textural, and other feature differences between clouds and backgrounds. To validate this method, we tested it on 102 Gao Fen-1(GF-1) and Gao Fen-2(GF-2) satellite images. The overall accuracy of our multi-feature fusion method for cloud detection was more than 91.45%, and the Kappa coefficient for all the tested images was greater than 80%. The producer and user accuracy were also higher at 93.67% and 95.67%, respectively; both of these values were higher than the values for the other tested feature fusion methods. Our results show that this novel multi-feature approach yields better accuracy than other feature fusion methods. In post-processing, we applied an object-oriented method to remove the influence of highly reflective ground objects and further improved the accuracy. Compared to traditional methods, our new method for cloud detection is accurate, exhibits good scalability, and produces consistent results when mapping clouds of different types and sizes over various land surfaces that contain natural vegetation, agriculture land, built-up areas, and water bodies.

Air temperature (Ta) is a key input in a wide range of agroclimatic applications. Moderate Resolution Imaging Spectroradiometer (MODIS) Ts (Land Surface Temperature (LST)) products are widely used to estimate daily Ta. However, only daytime LST (Ts-day) or nighttime LST (Ts-night) data have been used to estimate Tmax/Tmin (daily maximum or minimum air temperature), respectively. The relationship between Tmax and Ts-night, and the one between Tmin and Ts-day has not been studied. In this study, both the ability of Ts-night data to estimate Tmax and the ability of Ts-day data to estimate Tmin were tested and studied in the Corn Belt during the growing season (May–September) from 2008 to 2012, using MODIS daily LST products from both Terra and Aqua. The results show that using Ts-night for estimating Tmax could result in a higher accuracy than using Ts-day for a similar estimate. Combining Ts-day and Ts-night, the estimation of Tmax was improved by 0.19–1.85, 0.37–1.12 and 0.26–0.93 °C for crops, deciduous forest and developed areas, respectively, when compared with using only Ts-day or Ts-night data. The main factors influencing the Ta estimation errors spatially and temporally were analyzed and discussed, such as satellite overpassing time, air masses, irrigation, etc.

Object detection in Unmanned Aerial Vehicle (UAV) images plays fundamental roles in a wide variety of applications. As UAVs are maneuverable with high speed, multiple viewpoints, and varying altitudes, objects in UAV images are distributed with great heterogeneity, varying in size, with high density, bringing great difficulty to object detection using existing algorithms. To address the above issues, we propose a novel global density fused convolutional network (GDF-Net) optimized for object detection in UAV images. We test the effectiveness and robustness of the proposed GDF-Nets on the VisDrone dataset and the UAVDT dataset. The designed GDF-Net consists of a Backbone Network, a Global Density Model (GDM), and an Object Detection Network. Specifically, GDM refines density features via the application of dilated convolutional networks, aiming to deliver larger reception fields and to generate global density fused features. Compared with base networks, the addition of GDM improves the model performance in both recall and precision. We also find that the designed GDM facilitates the detection of objects in congested scenes with high distribution density. The presented GDF-Net framework can be instantiated to not only the base networks selected in this study but also other popular object detection models.