Remote Sensing Object Detection Meets Deep Learning: A metareview of challenges and advances

Zhang, Xiangrong; Zhang, Tianyang; Wang, Guanchun; Zhu, Peng; Tang, Xu; Jia, Xiuping; Jiao, Licheng

doi:10.1109/mgrs.2023.3312347

Cited by 8 publications

(3 citation statements)

References 342 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rapid development of remote sensing technology, object detection in remote sensing images has emerged as a burgeoning research area in computer vision. Various studies have focused on utilizing deep-learning-based object detection methods in the domain of remote sensing [1][2][3][4][5][6]. However, detecting targets in these images has shown itself to be challenging due to the objects' varying scales and resolutions.…”

Section: Introductionmentioning

confidence: 99%

Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method

Liu,

Zhang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Multi-scale object detection is critical for analyzing remote sensing images. Traditional feature pyramid networks, which are aimed at accommodating objects of varying sizes through multi-level feature extraction, face significant challenges due to the diverse scale variations present in remote sensing images. This situation often forces single-level features to span a broad spectrum of object sizes, complicating accurate localization and classification. To tackle these challenges, this paper proposes an innovative algorithm that incorporates an adaptive multi-scale feature enhancement and fusion module (ASEM), which enhances remote sensing image object detection through sophisticated multi-scale feature fusion. Our method begins by employing a feature pyramid to gather coarse multi-scale features. Subsequently, it integrates a fine-grained feature extraction module at each level, utilizing atrous convolutions with varied dilation rates to refine multi-scale features, which markedly improves the information capture from widely varied object scales. Furthermore, an adaptive enhancement module is applied to the features of each level by employing an attention mechanism for feature fusion. This strategy concentrates on the features of critical scale, which significantly enhance the effectiveness of capturing essential feature information. Compared with the baseline method, namely, Rotated FasterRCNN, our method achieved an mAP of 74.21% ( 0.81%) on the DOTA-v1.0 dataset and an mAP of 84.90% (+9.2%) on the HRSC2016 dataset. These results validated the effectiveness and practicality of our method and demonstrated its significant application value in multi-scale remote sensing object detection tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method

Liu,

Zhang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…With the advancement of big data technology and artificial intelligence, the processing and analysis capabilities of remote sensing data have significantly improved. Advanced algorithms, such as deep learning, have been utilized for remote sensing image classification [29,30], object detection [31], change detection [32], and other fields, enhancing the automation and intelligence of remote sensing information extraction. In recent years, night-time light remote sensing data have been considered in economic studies.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Economic Spillover Effects under the Hierarchical Structure of Urban Agglomeration Based on Time-Series Night-Time Lights: A Case Study of the Pearl River Delta, China

Bao,

Tao,

Zhuo

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Urban agglomerations are becoming increasingly important in driving economic development in China. Accurate representation of the economic development status and spillover effects of cities within an urban agglomeration is the foundation of and an effective approach for promoting the coordinated development of that agglomeration. However, current studies of economic spillovers tend to focus on urban agglomerations as a whole, and there is a lack of scrutiny and validation of research data. Therefore, this study proposes a framework for detecting economic spillover effects within an urban agglomeration based on a prolonged night-time light dataset. Firstly, we explored the most suitable night-time light index to characterize the economic status. Then, we used this index to construct the economic network and hierarchical structure of the urban agglomeration. Finally, we explored the heterogeneity of spillover effects under the hierarchical structure. The results of a case study in the Pearl River Delta (PRD) urban agglomeration show that (1) the total night-time light in built-up areas (BNTL) has the highest Pearson correlation coefficient with GDP, which is 0.82; (2) there is an obvious hierarchical structure within the PRD; (3) there are significant and sustained economic spillover effects among the core cities, with Guangzhou–Foshan and Shenzhen–Dongguan having more obvious spillover effects; and (4) the economic spillover effects within the three metropolitan areas have different characteristics. The Guangzhou–Foshan–Zhaoqing metropolitan area is closely linked, to apparent differences in the pace of spillover effects. The Shenzhen–Dongguan–Huizhou metropolitan area has strong close linkages, with strong synchronization of spillover effects. The Zhuhai–Zhongshan–Jiangmen metropolitan area has not yet formed a stable synergistic development relationship. Overall, the framework can effectively reveal the hierarchical structure and different characteristics of economic spillovers within urban agglomerations, which can provide a scientific reference for policy making related to the coordinated development of such agglomerations.

show abstract

“…In fact, the use of RS imagery in DL has received considerable attention in recent years. DL algorithms such as Convolutional Neural Networks (CNNs), 1 YOLO versions, 2 U-Net and their derivatives 3,4 have shown remarkable success in image classification, 5 object detection 6 and semantic segmentation tasks 7 respectively. Furthermore, the latest research is based on Transformers, 8 which have been shown to perform well with satellite images for various tasks.…”

Section: Introductionmentioning

confidence: 99%

Bridging the gap: deep learning in the semantic segmentation of remote sensing data

Hadir,

Assainova,

Adjou

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

Semantic segmentation has crucial importance in various domains due to its ability to recognize and categorize objects within an image at a pixel level. This task enables a wide range of applications, such as autonomous vehicles, environmental monitoring, and remote sensing (RS). In RS, semantic segmentation plays a crucial role, acting as the basis for applications including land cover classification. Following the success of deep learning (DL) methods in computer vision, our paper addresses the intersection between DL and RS imagery. We focus on improving the efficiency of some baseline and backbone models to ensure their adaptability to the challenges posed by RS imagery. Therefore, we evaluate state-of-the-art models on two datasets and investigate their ability to accurately segment objects in RS imagery. Our research aims to open the way for more accurate and reliable semantic segmentation methods in geospatial analysis.

show abstract

Remote Sensing Object Detection Meets Deep Learning: A metareview of challenges and advances

Cited by 8 publications

References 342 publications

Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method

Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method

Estimation of Economic Spillover Effects under the Hierarchical Structure of Urban Agglomeration Based on Time-Series Night-Time Lights: A Case Study of the Pearl River Delta, China

Bridging the gap: deep learning in the semantic segmentation of remote sensing data

Contact Info

Product

Resources

About