Deep Learning-Based Object Detection Techniques for Remote Sensing Images: A Survey

Abstract

Object detection in remote sensing images (RSIs) requires the locating and classifying of objects of interest, which is a hot topic in RSI analysis research. With the development of deep learning (DL) technology, which has accelerated in recent years, numerous intelligent and efficient detection algorithms have been proposed. Meanwhile, the performance of remote sensing imaging hardware has also evolved significantly. The detection technology used with high-resolution RSIs has been pushed to unprecedented heights, making important contributions in practical applications such as urban detection, building planning, and disaster prediction. However, although some scholars have authored reviews on DL-based object detection systems, the leading DL-based object detection improvement strategies have never been summarized in detail. In this paper, we first briefly review the recent history of remote sensing object detection (RSOD) techniques, including traditional methods as well as DL-based methods. Then, we systematically summarize the procedures used in DL-based detection algorithms. Most importantly, starting from the problems of complex object features, complex background information, tedious sample annotation that will be faced by high-resolution RSI object detection, we introduce a taxonomy based on various detection methods, which focuses on summarizing and classifying the existing attention mechanisms, multi-scale feature fusion, super-resolution and other major improvement strategies. We also introduce recognized open-source remote sensing detection benchmarks and evaluation metrics. Finally, based on the current state of the technology, we conclude by discussing the challenges and potential trends in the field of RSOD in order to provide a reference for researchers who have just entered the field.

Feature Enhancement-Based Ship Target Detection Method in Optical Remote Sensing Images

“…The backbone network of the algorithm in this paper uses CSPDarknet53. CSPDark-net53 includes five CSP modules, and each CSP module superimposes several residual blocks (1,2,8,8,4), and the backbone network is downsampling for the fifth time. The extracted large-size feature maps are first input into the SPP module, and the small and medium-size feature maps extracted by the fourth and third downsampling are input into EIRM, and then the three-size feature maps are used as the input of SGLPANet for feature fusion, and the feature map after feature fusion enter the detection head for detection.…”

“…Deep learning-based methods learn rich feature data for detection through convolutional neural networks [3]. The target characteristics of the traditional method rely on manual design [4], and the design is complex, universality, robustness, and accuracy need to be improved. As deep learning develops, traditional methods are gradually being replaced by deep learningbased methods.…”

RECOMM. Measuring resilient communities: An analytical and predictive tool

“…This field has been extensively studied in the past decades with significant advancement (Ref. [1][2][3] among the most comprehensive surveys). General challenges include the need for a large dataset to improve accuracy of prediction, as well as the detection of small objects in remote sensing, as also pointed out by Ref.…”

“…Our initial testing through our tool suggests that there seems to be a possible correlation between resilience as calculated through distances (as in equation Ref. [1] and some of the connectivity measures obtained through Shannon’s Entropy. The relationship between the measure of resilience, Shannon entropy, redundancy/spare capacity and resilience potential needs further exploration, and it will be subject of our continuing research.…”

“…General challenges include the need for a large dataset to improve accuracy of prediction, as well as the detection of small objects in remote sensing, as also pointed out by Ref. 1 This study is not so much affected by the latter, but we included in the limitations a point about larger datasets needed to increase the accuracy of our model.…”