Efficient Airport Detection Using Line Segment Detector and Fisher Vector Representation

Budak, Ümit; Halıcı, Uğur; Şengür, Abdulkadir; Karabatak, Murat; Xiao, Yang

doi:10.1109/lgrs.2016.2565706

Cited by 51 publications

(36 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, more and more scholars have begun to study object detection based on convolutional neural networks in remote sensing images, such as vehicle detection [2,3], oil tank detection [4], aircraft detection [5], and ship detection [6]. To date, a variety of airport detection methods have been proposed, and they can be divided into two categories: edge-based detection [7][8][9][10][11][12] and detection based on region segmentation [13,14]. Edge-based detection focuses on the characteristics of the lines at edges, and achieves airport detection through the detection of runways.…”

Section: Introductionmentioning

confidence: 99%

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

Zhu

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Zhu

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Due to the complex backgrounds and different shapes of airport, the real-time and accuracy of airport detection is faced with significant challenges. Traditional methods are mainly divided into two kinds: edge line [1] and regional segmentation [2]. The former has the characteristics of high speed and low complexity, but it is easy to be disturbed.…”

Section: Introductionmentioning

confidence: 99%

Airport Detection on Remote Sensing Images Using Fater Region-based Convolutional Neural Network

Zhu

et al. 2018

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Abstract. An airport detection method on remote sensing images based on transfer learning and hard example mining is proposed. We use Faster region-based convolutional neural network framework with end-to-end advantage instead of the sliding windows and artificial features in the existing traditional methods. Transfer learning is used to solve this problem that the number of airport remote sensing data itself is limited. Hard example mining is used to make full use of hard examples. As a result, it can improve the ability to discriminate objects and make training more efficient. The experimental results show that the proposed method can detect different types of airports accurately under complex backgrounds. Compared with other airport detection methods, the proposed method has higher detection rate 92.6%, lower falsealarm rate 15% and shorter average processing time 0.2s.

show abstract

“…It is significant to automatically access the valuable information from the huge volume of the remote sensing data [1][2][3][4][5][6][7]. Objects in remote sensing images (RSIs) have many different orientations, size, and illumination densities since RSIs are taken from the upper airspace with different imaging conditions.…”

Section: Introductionmentioning

confidence: 99%

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

et al. 2017

View full text Add to dashboard Cite

Abstract:Deep convolutional neural network (CNN) achieves outstanding performance in the field of target detection. As one of the most typical targets in remote sensing images (RSIs), airport has attracted increasing attention in recent years. However, the essential challenge for using deep CNN to detect airport is the great imbalance between the number of airports and background examples in large-scale RSIs, which may lead to over-fitting. In this paper, we develop a hard example mining and weight-balanced strategy to construct a novel end-to-end convolutional neural network for airport detection. The initial motivation of the proposed method is that backgrounds contain an overwhelming number of easy examples and a few hard examples. Therefore, we design a hard example mining layer to automatically select hard examples by their losses, and implement a new weight-balanced loss function to optimize CNN. Meanwhile, the cascade design of proposal extraction and object detection in our network releases the constraint on input image size and reduces spurious false positives. Compared with geometric characteristics and low-level manually designed features, the hard example mining based network could extract high-level features, which is more robust for airport detection in complex environment. The proposed method is validated on a multi-scale dataset with complex background collected from Google Earth. The experimental results demonstrate that our proposed method is robust, and superior to the state-of-the-art airport detection models.

show abstract

Efficient Airport Detection Using Line Segment Detector and Fisher Vector Representation

Cited by 51 publications

References 10 publications

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

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

Airport Detection on Remote Sensing Images Using Fater Region-based Convolutional Neural Network

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

Contact Info

Product

Resources

About