Abstract
Due to the variations of aircraft types, sizes, orientations, and complexity of remote sensing images, it is still difficult to effectively obtain accurate position and type by aircraft detection, which plays an important role in intelligent air transportation and digital battlefield. Current aircraft detection methods often use horizontal detectors, which produce significant redundancy, nesting, and overlap of detection areas and negatively affect the detection performance. To address these difficulties, a framework based on RetinaNet that combines a multi-feature fusion module and a rotating anchors generation mechanism is proposed. Firstly, the multi-feature fusion module mainly realizes feature fusion in two ways. One is to extract multi-scale features by the feature pyramid, and the other is to obtain corner features for each layer of feature map, thereby enriching the feature expression of aircraft. Then, we add a rotating anchor generation mechanism in the middle of the framework to realize the arbitrary orientation detection of aircraft. In the last, the framework connects two sub-networks, one for classifying anchor boxes and the other for regressing anchor boxes to ground-truth aircraft boxes. Compared with state-of-the-art methods by conducting comprehensive experiments on a publicly available dataset to validate the proposed method performance of aircraft detection. The detection precision (P) of proposed method achieves 97.06% on the public dataset, which demonstrates the effectiveness of the proposed method.
Highlights
Object detection is one of the fundamental tasks in computer vision and has attached wide attention due to the success of deep learning [1]
We comparisons with existing object detection algorithms and demonstrate that our method is present the comparisons with existing object detection algorithms and demonstrate that a competitive aircraft detection framework for remote sensing images
Compared with the optimal HBB detection method (Faster RCNN, feature pyramid network (FPN) and RetinaNet), the aircraft detection performance of our proposed object bounding box (OBB) is improved by about 8% (8.12%), there is a slight decrease in speed performance
Summary
Object detection is one of the fundamental tasks in computer vision and has attached wide attention due to the success of deep learning [1]. Object detection in remote sensing images has become a research hotspot [2,3,4]. Aircraft detection consists of two parts: locating object regions and classifying object in the candidate regions. In order to meet the requirements of rapid and accurate aircraft detection, it is necessary to get invariant features and train a classifier with a strong generalized capability. Extensive research has focused on feature design and feature expression to get good aircraft detection results. It usually constructs rotation-invariant and scale-invariant features based on object shape, texture, and geometric features and collaborates with the general classifiers, e.g., SVM, Bayes, KNN, and other classifiers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
