End-to-End Airport Detection in Remote Sensing Images Combining Cascade Region Proposal Networks and Multi-Threshold Detection Networks

Abstract

Fast and accurate airport detection in remote sensing images is important for many military and civilian applications. However, traditional airport detection methods have low detection rates, high false alarm rates and slow speeds. Due to the power convolutional neural networks in object-detection systems, an end-to-end airport detection method based on convolutional neural networks is proposed in this study. First, based on the common low-level visual features of natural images and airport remote sensing images, region-based convolutional neural networks are chosen to conduct transfer learning for airport images using a limited amount of data. Second, to further improve the detection rate and reduce the false alarm rate, the concepts of "divide and conquer" and "integral loss" are introduced to establish cascade region proposal networks and multi-threshold detection networks, respectively. Third, hard example mining is used to improve the object discrimination ability and the training efficiency of the network during sample training. Additionally, a cross-optimization strategy is employed to achieve convolution layer sharing between the cascade region proposal networks and the subsequent multi-threshold detection networks, and this approach significantly decreases the detection time. The results show that the method established in this study can accurately detect various types of airports in complex backgrounds with a higher detection rate, lower false alarm rate, and shorter detection time than existing airport detection methods.

Effective Airplane Detection in Remote Sensing Images Based on Multilayer Feature Fusion and Improved Nonmaximal Suppression Algorithm

“…Aiming at the problem of the insufficient representation ability of weak and small objects and overlapping detection boxes in airplane object detection, we carried out related research that has provided an original contribution to the field. We have done similar work before [2,35]. In the literature [2], we proposed an airport detection method combining cascade region proposal networks and multithreshold detection networks, which aimed to deal with the problems of complex background and inaccurate positioning.…”

“…We have done similar work before [2,35]. In the literature [2], we proposed an airport detection method combining cascade region proposal networks and multithreshold detection networks, which aimed to deal with the problems of complex background and inaccurate positioning. In the literature [35], we proposed an airplane detection method to deal with the issue of small objects, which used multilayer feature fusion in fully convolutional neural networks.…”

“…With the rapid development of high-resolution satellite remote sensing technology, the resolution of remote sensing images has become higher, and the acquisition method has become more convenient and diversified, facilitating the detection of objects in remote sensing images [1,2]. Airplanes are a typical military and civil object in an optical remote sensing image; they have important functions in battlefield surveillance, aviation control, and transport.…”

A Postearthquake Multiple Scene Recognition Model Based on Classical SSD Method and Transfer Learning

“…Transfer learning has the advantages of low data requirements, flexibility and robustness, which can improve the PEMSR model training efficiency and accuracy. To overcome the lack of sufficient labeled samples, this paper utilizes transfer learning [42,43,46] with a pretrained model that is obtained via SSD training on the PASCAL VOC dataset. There are two types of SSD structures that are most widely used, including SSD-300 and SSD-512.…”

“…The model attempts to collect postearthquake scenes images and to label them manually for the construction of a dataset. To eliminate the negative influence of an insufficient dataset, data augmentation and transfer learning [42] are used in this model. In addition, random oversampling is utilized to overcome the problem of data imbalance.…”