☆ 4.8 Article

Detecting Rotated Objects as Gaussian Distributions and its 3-D Generalization

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

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

Xue Yang et al.

Summary: In this paper, we introduce the idea of denoising to object detection, enhancing the ability to detect small and cluttered objects. We also address the boundary problem caused by rotation variation by adding an IoU constant factor to the smooth L1 loss. Combining these features, our proposed detector, SCRDet++, shows effectiveness in extensive experiments on various datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Add to Collection

Article Geochemistry & Geophysics

Align Deep Features for Oriented Object Detection

Jiaming Han et al.

Summary: Significant progress has been made in the past decade on detecting objects in aerial images. We propose a single-shot alignment network (S(2)A-Net) that consists of two modules to address the misalignment issue between anchors and convolutional features, improving the consistency between classification score and localization accuracy.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Geochemistry & Geophysics

CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote-Sensing Images

Qi Ming et al.

Summary: This article discusses the role of discriminative features in object detection and proposes a critical feature capturing network (CFC-Net) to improve detection accuracy by building powerful feature representation, refining preset anchors, and optimizing label assignment.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

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

Xue Yang et al.

Summary: This paper proposes a method for arbitrary-oriented object detection, which addresses the boundary problem in existing regression-based detectors by transforming the angle prediction task into a classification problem. By designing circular smooth labels and densely coded labels, the periodicity of angles is handled and the number of model parameters is reduced. An object heading detection module is also developed. Experimental results demonstrate the effectiveness of the proposed approach.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2022)

Add to Collection

Article Geochemistry & Geophysics

Anchor-Free Oriented Proposal Generator for Object Detection

Gong Cheng et al.

Summary: This article proposes a novel anchor-free oriented proposal generator (AOPG) to address issues in oriented object detection caused by the use of horizontal boxes. The effectiveness of AOPG is demonstrated through extensive experiments, and a new dataset, DIOR-R, is released to alleviate the problem of data insufficiency.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Yongchao Xu et al.

Summary: A framework for detecting multi-oriented objects is proposed in this paper, which accurately describes multi-oriented objects by sliding bounding box vertices and introducing additional target variables, achieving superior performances on multiple object detection benchmarks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Remote Sensing

PolarDet: a fast, more precise detector for rotated target in aerial images

Pengbo Zhao et al.

Summary: This paper introduces a polar coordinate-based object detection method, PolarDet, which locates objects by center-point, directs them by four polar angles, and measures them by polar ratio system for fast, simple, and accurate detection. It achieves nearly all state-of-the-art performance on three authoritative remote sensing object detection datasets.

INTERNATIONAL JOURNAL OF REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

Sparse Label Assignment for Oriented Object Detection in Aerial Images

Qi Ming et al.

Summary: This paper proposes a sparse label assignment strategy to improve sample assignment in object detection, utilizes a position-sensitive feature pyramid network with a coordinate attention module to extract position-sensitive features, and introduces a distance rotated IoU loss to enhance bounding box regression.

REMOTE SENSING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Dense Label Encoding for Boundary Discontinuity Free Rotation Detection

Xue Yang et al.

Summary: This paper introduces a classification-based approach for rotation detection, which significantly improves detection accuracy by utilizing new encoding mechanism and loss re-weighting techniques. The method has been proven effective across various datasets including aerial images and scene text.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Learning Point-Guided Localization for Detection in Remote Sensing Images

Qing Song et al.

Summary: This article discusses the challenges of object detection in remote sensing images, introduces a new localization method, and addresses the issue of poor performance due to discontinuous regression targets.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Jingru Yi et al.

Summary: This research extends a horizontally keypoint-based object detector to oriented object detection, detecting center keypoints before regressing boundary-aware vectors for capturing oriented bounding boxes, then classifying them into horizontal and rotational categories. The proposed method outperforms baseline methods and competes well with state-of-the-art approaches.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images

Shenyi Pan et al.

Summary: While general object detection has advanced significantly, this study focuses on localizing elliptical objects, specifically knots in sawn lumber images, where a new model architecture is proposed with promising results in detecting elliptical knots.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Learning for Generic Object Detection: A Survey

Li Liu et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2020)

Add to Collection

Article Environmental Sciences

Single-Stage Rotation-Decoupled Detector for Oriented Object

Bo Zhong et al.

REMOTE SENSING (2020)

Add to Collection

Article Geography, Physical

Oriented objects as pairs of middle lines

Haoran Wei et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2020)

Add to Collection

Article Environmental Sciences

Mask OBB: A Semantic Attention-Based Mask Oriented Bounding Box Representation for Multi-Category Object Detection in Aerial Images

Jinwang Wang et al.

REMOTE SENSING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Detecting Lesion Bounding Ellipses with Gaussian Proposal Networks

Yi Li

MACHINE LEARNING IN MEDICAL IMAGING (MLMI 2019) (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

TextBoxes plus plus : A Single-Shot Oriented Scene Text Detector

Minghui Liao et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2018)

Add to Collection

Article Computer Science, Information Systems

Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Jianqi Ma et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2018)

Add to Collection

Article Environmental Sciences

Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks

Xue Yang et al.

REMOTE SENSING (2018)

Add to Collection

Article Chemistry, Analytical

SECOND: Sparsely Embedded Convolutional Detection

Yan Yan et al.

SENSORS (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

FOTS: Fast Oriented Text Spotting with a Unified Network

Xuebo Liu et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Rotation-sensitive Regression for Oriented Scene Text Detection

Minghui Liao et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

Xuepeng Shi et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

EAST: An Efficient and Accurate Scene Text Detector

Xinyu Zhou et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

© Peeref 2019-2024. All rights reserved.