Abstract
With the improvement of the quality and resolution of remote sensing (RS) images, scene recognition tasks have played an important role in the RS community. However, due to the special bird’s eye view image acquisition mode of imaging sensors, it is still challenging to construct a discriminate representation of diverse and complex scenes to improve RS image recognition performance. Capsule networks that can learn the spatial relationship between the features in an image has a good image classification performance. However, the original capsule network is not suitable for images with a complex background. To address the above issues, this paper proposes a novel end-to-end capsule network termed DS-CapsNet, in which a new multi-scale feature enhancement module and a new Caps-SoftPool method are advanced by aggregating the advantageous attributes of the residual convolution architecture, Diverse Branch Block (DBB), Squeeze and Excitation (SE) block, and the Caps-SoftPool method. By using the residual DBB, multiscale features can be extracted and fused to recover a semantic strong feature representation. By adopting SE, the informative features are emphasized, and the less salient features are weakened. The new Caps-SoftPool method can reduce the number of parameters that are needed in order to prevent an over-fitting problem. The novel DS-CapsNet achieves a competitive and promising performance for RS image recognition by using high-quality and robust capsule representation. The extensive experiments on two challenging datasets, AID and NWPU-RESISC45, demonstrate the robustness and superiority of the proposed DS-CapsNet in scene recognition tasks.
Highlights
With the high-speed improvement of the performance of optical remote sensors, it is very economical and effective to obtain high-resolution remote sensing (RS) images [1].it is very important to understand its semantic information effectively for their extensive and deep applications in land planning, urban change, traffic control, disaster monitoring, military, agriculture, and forestry [2,3]
Aembedded representative example of Diverse Branch Block (DBB) architecture used in our model shown in Figure 6, which uses this directly into any existing as a is drop-in replacement
Our DS-CapsNet is estimated on the public RS data sets
Summary
With the high-speed improvement of the performance of optical remote sensors, it is very economical and effective to obtain high-resolution remote sensing (RS) images [1].it is very important to understand its semantic information effectively for their extensive and deep applications in land planning, urban change, traffic control, disaster monitoring, military, agriculture, and forestry [2,3]. With the high-speed improvement of the performance of optical remote sensors, it is very economical and effective to obtain high-resolution remote sensing (RS) images [1]. Compared to CNN, the biggest modification is each capsule is that it outputs an activation vector instead of a scalar value. Regarding the robustness of CNN, rotation, translation, and scale is poor, which usually reduces its performance. A vector formula allows a capsule to detect features, and allows it to learn and recognize its invariances, forming a strong but lightweight feature representation pattern
Sign-in/Register to view highlights & summary 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.
