Anchor-Free Arbitrary-Oriented Object Detector Using Box Boundary-Aware Vectors

نویسندگان

چکیده

Characterized by complicated backgrounds, various types, large size variations, and arbitrary orientations, the detection recognition of arbitrary-oriented objects in remote sensing images are challenging. To address aforementioned problem, an anchor-free object detector using box boundary-aware vectors is proposed. With idea CenterNet to detect as points, oriented achieved predicting center, vectors, size, type bounding box. In feature extraction stage designed architecture, Res2Net, a multiscale convolutional neural network, used extract maps different scales adaptively spatial fusion adopted improve detector's adaptability sizes. detector, context enhancement module with multibranch network enhance contextual information robustness backgrounds. Experiments carried on three challenging benchmarks (i.e., HRSC2016, UCAS-AOD, DOTA) our method achieves state-of-the-art performance 90.30%, 89.70%, 77.18% mAP, respectively.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Boundary-aware box refinement for object proposal generation

Object proposals have been widely used in object detection to speed up object searching. However, many of existing object proposal generators have pool localization quality, which weakens the performance of object detectors. In this paper, we present an effective approach to improve the localization quality of object proposals. We leverage the boundary-preserving property of superpixels and des...

متن کامل

Fully Convolutional Grasp Detection Network with Oriented Anchor Box

In this paper, we present a real-time approach to predict multiple grasping poses for a parallel-plate robotic gripper using RGB images. A model with oriented anchor box mechanism is proposed and a new matching strategy is used during the training process. An end-to-end fully convolutional neural network is employed in our work. The network consists of two parts: the feature extractor and multi...

متن کامل

Using Object-Oriented Frameworks

Often it is di cult to reuse a software component outside of its original context. Object-oriented frameworks can provide the context in which the component is meant to be reused and thus allow for a signi cant amount of reuse. An object-oriented framework is the reusable design of a system or subsystem implemented through a collection of concrete and abstract classes and their collaborations [...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

سال: 2022

ISSN: ['2151-1535', '1939-1404']

DOI: https://doi.org/10.1109/jstars.2022.3158905