Anchor-free aerial object detectors have recently attracted considerable attention due to their high flexibility and computational efficiency. They are typically implemented by learning two subtasks of object detection, object localization and classification, based on two separately parallel branches in the detection head. However, without the constraints of predefined anchor boxes, anchor-free detectors are more vulnerable to spatial misalignment caused by optimization inconsistencies between these two subtasks, which significantly degrades detection performance. To address this issue, this paper proposes a novel and efficient anchor-free object detector, namely localization-classification-aligned detector (LCA-Det), which explicitly pulls closer the predictions of localization and classification, through a single-branch subtask-aligned detection head and a subtask-aligned sample assignment metric. Extensive experimental results have demonstrated the effectiveness and superiority of our proposed method for object detection in aerial imagery.
Ultra-high-definition (UHD) image super-resolution (SR) has attracted increasing attention due to the popularity of modern devices, such as smartphones, which support the capture of UHD images, e.g. 4K and 8K images. However, existing UHD SR methods process the image in the spatial domain only. This limitation hinders their ability to effectively utilize the rich details and fine-grained textures in local areas of UHD images. To address this issue, our proposed method comprehensively exploits the global and local features of UHD images by combining spatial and frequency features. Additionally, previous UHD image SR methods can only handle a fixed scaling factor, but real-world applications very often require upscaling low-resolution images with different scales. Therefore, we employ an arbitrary-scale strategy in the SR training process, enabling super-resolution of UHD images at any scale with a single trained model. Experimental results demonstrate the effectiveness and superiority of our proposed method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.