Search

With the rapid development of artificial intelligence and computer vision, deep learning has become widely used for aircraft detection. However, aircraft detection is still a challenging task due to the small target size and dense arrangement of aircraft and the complex backgrounds in remote sensing images. Existing remote sensing aircraft detection methods were mainly designed based on algorithms employed in general object detection methods. However, these methods either tend to ignore the key structure and size information of aircraft targets or have poor detection effects on densely distributed aircraft targets. In this paper, we propose a novel multi-task aircraft detection algorithm. Firstly, a multi-task joint training method is proposed, which provides richer semantic structure features for bounding box localization through landmark detection. Secondly, a multi-task inference algorithm is introduced that utilizes landmarks to provide additional supervision for bounding box NMS (non-maximum suppression) filtering, effectively reducing false positives. Finally, a novel loss function is proposed as a constrained optimization between bounding boxes and landmarks, which further improves aircraft detection accuracy. Experiments on the UCAS-AOD dataset demonstrated the state-of-the-art precision and efficiency of our proposed method compared to existing approaches. Furthermore, our ablation study revealed that the incorporation of our designed modules could significantly enhance network performance. [ABSTRACT FROM AUTHOR]

Recognizing and classifying natural or artificial geo-objects under complex geo-scenes using remotely sensed data remains a significant challenge due to the heterogeneity in their spatial distribution and sampling bias. In this study, we propose a deep learning method of surface complexity analysis based on multiscale entropy. This method can be used to reduce sampling bias and preserve entropy-based invariance in learning for the semantic segmentation of land use and land cover (LULC) images. Our quantitative models effectively identified and extracted local surface complexity scores, demonstrating their broad applicability. We tested our method using the Gaofen-2 image dataset in mainland China and accurately estimated multiscale complexity. A downstream evaluation revealed that our approach achieved similar or better performance compared to several representative state-of-the-art deep learning methods. This highlights the innovative and significant contribution of our entropy-based complexity analysis and its applicability in improving LULC semantic segmentations through optimal stratified sampling and constrained optimization, which can also potentially be used to enhance semantic segmentation under complex geo-scenes using other machine learning methods. [ABSTRACT FROM AUTHOR]

Segmentation, which is usually the first step in object-based image analysis (OBIA), greatly influences the quality of final OBIA results. In many existing multi-scale segmentation algorithms, a common problem is that under-segmentation and over-segmentation always coexist at any scale. To address this issue, we propose a new method that integrates the newly developed constrained spectral variance difference (CSVD) and the edge penalty (EP). First, initial segments are produced by a fast scan. Second, the generated segments are merged via a global mutual best-fitting strategy using the CSVD and EP as merging criteria. Finally, very small objects are merged with their nearest neighbors to eliminate the remaining noise. A series of experiments based on three sets of remote sensing images, each with different spatial resolutions, were conducted to evaluate the effectiveness of the proposed method. Both visual and quantitative assessments were performed, and the results show that large objects were better preserved as integral entities while small objects were also still effectively delineated. The results were also found to be superior to those from eCongnition's multi-scale segmentation. [ABSTRACT FROM AUTHOR]

Pseudo-Invariant Calibration Sites (PICS) have been widely used by the remote sensing community in recent decades for post-launch absolute calibration, cross-calibration, and the monitoring of radiometric stability. The Committee on Earth Observation Satellites (CEOS) has established several official PICS for these purposes. Of these, Libya-4 is the most commonly used, due to its high uniformity and stability. The site was chosen as a large-area site for medium resolution sensors, and with high-resolution sensors now common, smaller sites are being identified. This work has identified an improved area of interest (AOI) within Libya-4 by using combined Landsat 8 and Sentinel 2 data. The Optimized Ground Target (OGT) was determined by calculating the coefficient of variation along with the use of a quasi-Newton optimization algorithm combined with the Basin–Hopping global optimization technique to constrain a search area small enough to perform a final brute-force refinement. The Coefficient of Variation CV of the proposed OGT is significantly lower than that in the original CEOS area, with differences between the CV of both zones in the order of 1% in the visible near-infrared (VNIR) bands. This new AOI has the potential to improve the cross-calibration between high-resolution sensors using the PICS methodology through an OGT with more homogeneous and stable characteristics. [ABSTRACT FROM AUTHOR]