Abstract
Object detection is challenging in high spatial resolution (HSR) remote sensing images that have a complex background and irregular object locations. To minimize manual annotation cost in supervised learning methods and achieve advanced detection performance, we proposed a point-based weakly supervised learning method to address the object detection challenge in HSR remote sensing images. In the study, point labels are introduced to guide candidate bounding box mining and generate pseudobounding boxes for objects. Then, pseudobounding boxes are applied to train the detection model. A progressive candidate bounding box mining strategy is proposed to refine object detection. Experiments are conducted on a comprehensive HSR dataset which contains four categories. Results indicate the proposed method achieves competitive performance compared to YOLOv5 which is trained on manual bounding box annotations. In comparison to the state-of-the-art weakly supervised learning method, our method outperforms WSDDN method with 0.62 mean average precision score.
Highlights
O WING to the rapid development of remote sensing platforms and the reduction of data collection costs, a growing number of high spatial resolution (HSR) remote sensing images are publicly available [1], [2]
In order to prevent cumbersome bounding box annotation process and to overcome the challenges raised by the aforementioned WSL methods, we propose a point-based weakly supervised learning method for detecting objects in HSR remote sensing images
HSR remote sensing images of all classes are collected from a public dataset named NWPU VHR-10 dataset [27]–[29] that were cropped from Google Earth and Vaihingen dataset
Summary
O WING to the rapid development of remote sensing platforms and the reduction of data collection costs, a growing number of high spatial resolution (HSR) remote sensing images are publicly available [1], [2]. Encouraging results are reported, there are two main problems in image-level label-based WSL methods for object detection in remote sensing images. In order to prevent cumbersome bounding box annotation process and to overcome the challenges raised by the aforementioned WSL methods, we propose a point-based weakly supervised learning method for detecting objects in HSR remote sensing images. The proposed point-based weakly supervised learning method aims to solve multiclass object detection tasks in HSR remote sensing images. We compare the proposed pointbased weakly supervised learning method to two state-of-the-art methods which are a fully supervised learning method and an LI et al.: POINT-BASED WEAKLY SUPERVISED LEARNING FOR OBJECT DETECTION IN HSR REMOTE SENSING IMAGES image-level label-based WSL method [26] to demonstrate the effectiveness of the proposed method.
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: 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.
