Airplane detection and recognition in high-resolution Remote Sensing Images (RSIs) remains a challenging task due to the factors of multiple view angles, multiple scales, multiple orientation etc. This paper proposes an Adaptive Component Discrimination Network (ACDN) for airplane detection and recognition in RSIs, which focus various scales from global to local, making full use of the overall contour as well as the dominant component features of airplanes. Firstly, a Standardization Processing Module (SPM) is proposed for image projection conversion and resolution uniform to alleviate the confusion of different types of airplane in different resolution images. Secondly, the Rotatable Bounding box-based Pyramid Network (RBPN) is utilized to extract candidate airplane coordinates and categories. Further, an adaptive aircraft component discrimination method is established for confusing few-shot airplane targets recognition, which consists of a Target Orientation Adaptive Adjustment Module (OAAM) and a Component Discrimination Module (CDM). OAAM obtains airplanes with same orientations by predicting the orientation of the slices and rotating them adaptively. All the uniformed slices are then fed into the CDM for dominant components detection, which corrects the target preclassification results, improving the classification performance. Experiments conducted on the 2020 Gaofen Challenge demonstrate the efficacy and superiority of the proposed method.
Due to the unique imaging mechanism of synthetic aperture radar (SAR), targets in SAR images often shows complex scattering characteristics, including unclear contours, incomplete scattering spots, attitude sensitivity, etc. Automatic aircraft detection is still a great challenge in SAR images. To cope with these problems, a novel approach called adaptive deformable network (ADN) combined with peak feature fusion (PFF) is proposed for aircraft detection. The PFF is designed for taking full advantage of the strong scattering features of aircraft, which consists of peak feature extraction and fusion. To fully exploit the strong scattering features of the aircraft in SAR images, peak features are extracted via the Harris detector and the eight-domain pixel detection of local maxima. Then, the saliency of aircraft under multiple imaging conditions is enhanced by multi-channel blending. All the PFF-preprocessed images are fed into the ADN for training and testing. The core components of ADN contain an adaptive spatial feature fusion (ASFF) module and a deformable convolution module (DCM). ASFF is utilized to reconcile the inconsistency across different feature scales, raising the characterization capabilities of the feature pyramid and improving the detection performance of multi-scale aircraft further. DCM is introduced to determine the 2-D offsets of feature maps adaptively, improving the geometric modeling abilities of aircraft in various shapes. The well-designed ADN is established by combining the two modules to alleviate the problems of the multi-scale targets and attitude sensitivity. Extensive experiments are conducted on the GaoFen-3 (GF3) dataset to demonstrate the effectiveness of the PFF-ADN with an average precision of 89.34%, as well as an F1-score of 91.11%. Compared with other mainstream algorithms, the proposed approach achieves state-of-the-art performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.