Abstract
Multi-class object detection in remote sensing imagery is an important and challenging topic in computer vision. Compared with the object detection of natural scenes, remote sensing object detection has some challenges such as scale diversity, arbitrary directions and densely packed objects. To resolve these problems, this paper presents a scale-aware rotated object detection. Firstly, we propose a novel feature fusion module, which takes full advantage of high-level semantic information and low-level high resolution feature. The new feature maps are more suitable for detecting objects with a large difference in scale. Meanwhile, we design a specific weighted loss, which contains an intersection-over-union (IoU) loss and a smooth L1 loss to further address the scale diversity. Besides, in order to detect oriented and densely packed objects more accurately, we propose a normalization strategy for the representation of rotating bounding box. Our method is evaluated on two public aerial datasets DOTA and HRSC2016, and achieves competitive performances. On DOTA, we boost the mean Average Precision (mAP) to 72.95% on oriented object detection.
Highlights
Multi-class object detection in aerial imagery is intended to locate objects of interest on the ground in aerial images and identifying their categories
ROTATION BRANCH When using the R2CNN structure to obtain a rotating bounding box, we find that some objects have inaccurate angle predictions
1) FPSN According to Table 2, concatenating the feature maps increases the mean Average Precision (mAP) by 0.9% compared to the baseline
Summary
Multi-class object detection in aerial imagery is intended to locate objects of interest on the ground in aerial images and identifying their categories. It has been playing an important role in computer vision over the years and can apply to many aspects such as cargo transportation and military uses. Methods of object detection based on deep convolutional neural networks (CNNs) have been greatly developed. These methods are applied to the field of remote sensing and have achieved good performances.
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.
