DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images
- URL: http://arxiv.org/abs/2110.01025v1
- Date: Sun, 3 Oct 2021 15:28:14 GMT
- Title: DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images
- Authors: Feng Zhang, Xueying Wang, Shilin Zhou, Yingqian Wang
- Abstract summary: We propose a dense anchor-free rotated object detector (DARDet) for rotated object detection in aerial images.
Our DARDet directly predicts five parameters of rotated boxes at each foreground pixel of feature maps.
Our method achieves state-of-the-art performance on three commonly used aerial objects datasets.
- Score: 11.45718985586972
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Rotated object detection in aerial images has received increasing attention
for a wide range of applications. However, it is also a challenging task due to
the huge variations of scale, rotation, aspect ratio, and densely arranged
targets. Most existing methods heavily rely on a large number of pre-defined
anchors with different scales, angles, and aspect ratios, and are optimized
with a distance loss. Therefore, these methods are sensitive to anchor
hyper-parameters and easily suffer from performance degradation caused by
boundary discontinuity. To handle this problem, in this paper, we propose a
dense anchor-free rotated object detector (DARDet) for rotated object detection
in aerial images. Our DARDet directly predicts five parameters of rotated boxes
at each foreground pixel of feature maps. We design a new alignment convolution
module to extracts aligned features and introduce a PIoU loss for precise and
stable regression. Our method achieves state-of-the-art performance on three
commonly used aerial objects datasets (i.e., DOTA, HRSC2016, and UCAS-AOD)
while keeping high efficiency. Code is available at
https://github.com/zf020114/DARDet.
Related papers
- YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images [33.80392696735718]
YOLC (You Only Look Clusters) is an efficient and effective framework that builds on an anchor-free object detector, CenterNet.
To overcome the challenges posed by large-scale images and non-uniform object distribution, we introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection.
We perform extensive experiments on two aerial image datasets, including Visdrone 2019 and UAVDT, to demonstrate the effectiveness and superiority of our proposed approach.
arXiv Detail & Related papers (2024-04-09T10:03:44Z) - Adaptive Rotated Convolution for Rotated Object Detection [96.94590550217718]
We present Adaptive Rotated Convolution (ARC) module to handle rotated object detection problem.
In our ARC module, the convolution kernels rotate adaptively to extract object features with varying orientations in different images.
The proposed approach achieves state-of-the-art performance on the DOTA dataset with 81.77% mAP.
arXiv Detail & Related papers (2023-03-14T11:53:12Z) - Detecting Rotated Objects as Gaussian Distributions and Its 3-D
Generalization [81.29406957201458]
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects.
We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection.
We propose to model the rotated objects as Gaussian distributions.
We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
arXiv Detail & Related papers (2022-09-22T07:50:48Z) - Point RCNN: An Angle-Free Framework for Rotated Object Detection [13.209895262511015]
Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, and extreme density of objects.
We propose a purely angle-free framework for rotated object detection, called Point RCNN, which mainly consists of PointRPN and PointReg.
Experiments demonstrate that our Point RCNN achieves the new state-of-the-art detection performance on commonly used aerial datasets.
arXiv Detail & Related papers (2022-05-28T04:07:37Z) - Oriented Object Detection in Aerial Images Based on Area Ratio of
Parallelogram [0.0]
Rotated object detection is a challenging task in aerial images.
Existing regression-based rotation detectors suffer the problem of discontinuous boundaries.
We propose a simple effective framework to address the above challenges.
arXiv Detail & Related papers (2021-09-21T14:13:36Z) - FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas.
Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
arXiv Detail & Related papers (2021-08-27T03:07:55Z) - MRDet: A Multi-Head Network for Accurate Oriented Object Detection in
Aerial Images [51.227489316673484]
We propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors.
To obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multi-head network.
Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately.
arXiv Detail & Related papers (2020-12-24T06:36:48Z) - LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery [43.91170581467171]
State-of-the-art object detection approaches have difficulties detecting dense, small targets with arbitrary orientation in large aerial images.
We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery.
arXiv Detail & Related papers (2020-05-28T19:57:34Z) - SCRDet++: Detecting Small, Cluttered and Rotated Objects via
Instance-Level Feature Denoising and Rotation Loss Smoothing [131.04304632759033]
Small and cluttered objects are common in real-world which are challenging for detection.
In this paper, we first innovatively introduce the idea of denoising to object detection.
Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.
arXiv Detail & Related papers (2020-04-28T06:03:54Z) - On the Arbitrary-Oriented Object Detection: Classification based
Approaches Revisited [94.5455251250471]
We first show that the boundary problem suffered in existing dominant regression-based rotation detectors, is caused by angular periodicity or corner ordering.
We transform the angular prediction task from a regression problem to a classification one.
For the resulting circularly distributed angle classification problem, we first devise a Circular Smooth Label technique to handle the periodicity of angle and increase the error tolerance to adjacent angles.
arXiv Detail & Related papers (2020-03-12T03:23:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.