Abstract
Object detection in remote sensing images plays an important role in both military and civilian remote sensing applications. Objects in remote sensing images are different from those in natural images. They have the characteristics of scale diversity, arbitrary directivity, and dense arrangement, which causes difficulties in object detection. For objects with a large aspect ratio and that are oblique and densely arranged, using an oriented bounding box can help to avoid deleting some correct detection bounding boxes by mistake. The classic rotational region convolutional neural network (R2CNN) has advantages for text detection. However, R2CNN has poor performance in the detection of slender objects with arbitrary directivity in remote sensing images, and its fault tolerance rate is low. In order to solve this problem, this paper proposes an improved R2CNN based on a double detection head structure and a three-point regression method, namely, TPR-R2CNN. The proposed network modifies the original R2CNN network structure by applying a double fully connected (2-fc) detection head and classification fusion. One detection head is for classification and horizontal bounding box regression, the other is for classification and oriented bounding box regression. The three-point regression method (TPR) is proposed for oriented bounding box regression, which determines the positions of the oriented bounding box by regressing the coordinates of the center point and the first two vertices. The proposed network was validated on the DOTA-v1.5 and HRSC2016 datasets, and it achieved a mean average precision (mAP) of 3.90% and 15.27%, respectively, from feature pyramid network (FPN) baselines with a ResNet-50 backbone.
Highlights
Object detection of remote sensing images plays an important role in military and national defense
This paper compared them with the network with a double detection head and classification fusion
We reproduced the R2CNN network based on our deep learning frame, so that the R2CNN in Tables 3–5 only had one difference of regression method with three-point regression method (TPR)-R2CNN
Summary
Object detection of remote sensing images plays an important role in military and national defense. The categories and positions of military objects can be obtained, and the battlefield situation and environment can be evaluated. Since the 1990s, remote sensing image object detection has played an important role in civilian fields, such as the detection of vehicles and buildings, serving urban road planning, parking lot site selection, and traffic management. Convolutional neural networks have moved object detection to a new level. Since traditional object detection methods perform badly both in detection precision and rate, researchers have begun to study object detection methods based on deep learning. The core of deep learning-based object detection methods is the convolutional neural network
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.
