Object Detection In Aerial Images

40 papers with code • 3 benchmarks • 5 datasets

Object Detection in Aerial Images is the task of detecting objects from aerial images.

( Image credit: DOTA: A Large-Scale Dataset for Object Detection in Aerial Images )

Libraries

Use these libraries to find Object Detection In Aerial Images models and implementations

Most implemented papers

R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object

yangxue0827/RotationDetection 15 Aug 2019

Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features.

DOTA: A Large-scale Dataset for Object Detection in Aerial Images

PaddlePaddle/PaddleDetection CVPR 2018

The fully annotated DOTA images contains $188, 282$ instances, each of which is labeled by an arbitrary (8 d. o. f.)

SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

SJTU-Thinklab-Det/DOTA-DOAI 28 Apr 2020

Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects.

On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited

yangxue0827/RotationDetection ECCV 2020

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.

SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects

DetectionTeamUCAS/R2CNN-Plus-Plus_Tensorflow ICCV 2019

Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects.

Align Deep Features for Oriented Object Detection

csuhan/s2anet 21 Aug 2020

However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.

Dense Label Encoding for Boundary Discontinuity Free Rotation Detection

yangxue0827/RotationDetection CVPR 2021

Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc.

DroNet: Efficient convolutional neural network detector for real-time UAV applications

gplast/DroNet 18 Jul 2018

Through the analysis we propose a CNN architecture that is capable of detecting vehicles from aerial UAV images and can operate between 5-18 frames-per-second for a variety of platforms with an overall accuracy of ~95%.

Learning RoI Transformer for Oriented Object Detection in Aerial Images

dingjiansw101/AerialDetection CVPR 2019

Object detection in aerial images is an active yet challenging task in computer vision because of the bird's-eye view perspective, the highly complex backgrounds, and the variant appearances of objects.

Learning Modulated Loss for Rotated Object Detection

Mrqianduoduo/RSDet-8P-4R 19 Nov 2019

Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function.