Aerospace Information Research Institute

About: Aerospace Information Research Institute is a education organization based out in . It is known for research contribution in the topics: Environmental science & Computer science. The organization has 75 authors who have published 109 publications receiving 286 citations.

FAIR1M: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery

Abstract: With the rapid development of deep learning, many deep learning-based approaches have made great achievements in object detection tasks. It is generally known that deep learning is a data-driven approach. Data directly impact the performance of object detectors to some extent. Although existing datasets include common objects in remote sensing images, they still have some scale, category, and image limitations. Therefore, there is a strong requirement for establishing a large-scale object detection benchmark for high-resolution remote sensing images. In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 40,000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M. We collected remote sensing images with a resolution of 0.3 m to 0.8 m from different platforms, which are spread across many countries and regions. All objects in the FAIR1M dataset are annotated with respect to 5 categories and 37 subcategories by oriented bounding boxes. Compared with existing detection datasets that are dedicated to object detection, the FAIR1M dataset has 4 particular characteristics: (1) it is much larger than other existing object detection datasets both in terms of the number of instances and the number of images, (2) it provides richer fine-grained category information for objects in remote sensing images, (3) it contains geographic information such as latitude, longitude and resolution attributes, and (4) it provides better image quality due to the use of a careful data cleaning procedure. Based on the FAIR1M dataset, we propose three fine-grained object detection and recognition tasks. Moreover, we evaluate several state-of-the-art approaches to establish baselines for future research. Experimental results indicate that the FAIR1M dataset effectively represents real remote sensing applications and is quite challenging for existing methods. Considering the fine-grained characteristics, we improve the evaluation metric and introduce the idea of hierarchy detection into the algorithms. We believe that the FAIR1M dataset will contribute to the earth observation community via fine-grained object detection in large-scale real-world scenes. FAIR1M Website: http://gaofen-challenge.com/.

Characterizing Spatiotemporal Variations in the Urban Thermal Environment Related to Land Cover Changes in Karachi, Pakistan, from 2000 to 2020

Abstract: Understanding the spatiotemporal patterns of urban heat islands and the factors that influence this phenomenon can help to alleviate the heat stress exacerbated by urban warming and strengthen heat-related urban resilience, thereby contributing to the achievement of the United Nations Sustainable Development Goals. The association between surface urban heat island (SUHI) effects and land use/land cover features has been studied extensively, but the situation in tropical cities is not well-understood due to the lack of consistent data. This study aimed to explore land use/land cover (LULC) changes and their impact on the urban thermal environment in a tropical megacity—Karachi, Pakistan. Land cover maps were produced, and the land surface temperature (LST) was estimated using Landsat images from five different years over the period 2000–2020. The surface urban heat island intensity (SUHII) was then quantified based on the LST data. Statistical analyses, including geographically weighted regression (GWR) and correlation analyses, were performed in order to analyze the relationship between the land cover composition and LST. The results indicated that the built-up area of Karachi increased from 97.6 km² to 325.33 km² during the period 2000–2020. Among the different land cover types, the areas classified as built-up or bare land exhibited the highest LST, and a change from vegetation to bare land led to an increase in LST. The correlation analysis indicated that the correlation coefficients between the normalized difference built-up index (NDBI) and LST ranged from 0.14 to 0.18 between 2000 and 2020 and that NDBI plays a dominant role in influencing the LST. The GWR analysis revealed the spatial variation in the association between the land cover composition and the SUHII. Parks with large areas of medium- and high-density vegetation play a significant role in regulating the thermal environment, whereas the scattered vegetation patches in the urban core do not have a significant relationship with the LST. These findings can be used to inform adaptive land use planning that aims to mitigate the effects of the UHI and aid efforts to achieve sustainable urban growth.

Combining Random Forest and XGBoost Methods in Detecting Early and Mid-Term Winter Wheat Stripe Rust Using Canopy Level Hyperspectral Measurements

Abstract: Appropriate modeling methods and feature selection algorithms must be selected to improve the accuracy of early and mid-term remote sensing detection of wheat stripe rust. In the current study, we explored the effectiveness of the random forest (RF) algorithm combined with the extreme gradient boosting (XGboost) method for early and mid-term wheat stripe rust detection based on the vegetation indices extracted from canopy level hyperspectral measurements. Initially, 21 vegetation indices that were related to the early and mid-term winter wheat stripe rust were calculated on the basis of canopy level hyperspectral reflectance. Subsequently, the optimal vegetation index combination for disease detection was determined using correlation analysis (CA) combined with RF algorithms. Then, the disease severity detection model of early and mid-term winter wheat stripe rust was constructed using XGBoost method based on the optimal vegetation index combination. For the evaluation and comparison of the initial results, three commonly used classification methods, namely, RF, backpropagation neural network (BPNN), and support vector machine (SVM), were utilized. The vegetation index combinations determined by the single CA algorithm were also used to construct detection models. Compared with the detection models based on the vegetation index combination obtained using the single CA algorithm, the overall accuracy of the four detection models based on the optimal vegetation index combination based on CA combined with RF algorithms increased by 16.1% (XGBoost), 9.7% (RF), 8.1% (SVM), and 8.1% (BPNN). Among the eight models, the XGBoost detection model based on the optimal vegetation index combination using CA combined with RF algorithms, CA-RF-XGBoost, achieved the highest overall accuracy of 87.1% and the highest kappa coefficient of 0.798. Our results indicate that the RF combined with XGBoost can improve the detection accuracy of early and mid-term winter wheat stripe rust effectively at canopy scale.