ORCNN-X: Attention-Driven Multiscale Network for Detecting Small Objects in Complex Aerial Scenes

Article Computer Science, Interdisciplinary Applications

Attention-guided multiscale neural network for defect detection in sewer pipelines

Yanfen Li et al.

Summary: This paper proposes an automatic defect detection framework that accurately identifies and localizes eight types of defects in closed-circuit television videos based on a deep neural network. The framework is robust and achieves a state-of-the-art mean average precision of 73.4%, showing potential for realistic sewer defect inspections.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Refined One-Stage Oriented Object Detection Method for Remote Sensing Images

Liping Hou et al.

Summary: This paper proposes a method for the detection of multi-class objects with arbitrary orientations in remote sensing images. It addresses the scale imbalance and angle sensitivity problems by introducing the Asymmetric Feature Pyramid Network, Dynamic Feature Alignment module, and Area-IoU regression loss. Experimental results on three publicly available datasets demonstrate the effectiveness of the proposed method.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

添加到收藏夹

Article Environmental Sciences

Point RCNN: An Angle-Free Framework for Rotated Object Detection

Qiang Zhou et al.

Summary: Rotated object detection in aerial images is challenging due to orientation variations, scale changes, and object density. Existing methods rely on angle-based detectors which suffer from boundary problems. In this study, a purely angle-free framework called Point RCNN is proposed to address this issue. Point RCNN achieved state-of-the-art performance on multiple large-scale aerial image datasets and introduced a balanced dataset strategy to handle the imbalance problem.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Fully Deformable Convolutional Network for Ship Detection in Remote Sensing Imagery

Hongwei Guo et al.

Summary: A novel method for ship detection in high spatial resolution remote sensing imagery is proposed, which utilizes deformable convolution networks to effectively extract features at different scales and orientations. Experimental results on public remote sensing datasets demonstrate the effectiveness of the proposed method in accurately detecting ships in remote sensing applications.

REMOTE SENSING (2022)

添加到收藏夹

Review Geography, Physical

A review of building detection from very high resolution optical remote sensing images

Jiayi Li et al.

Summary: This article provides a comprehensive review of the recent advancements in building extraction from very high resolution (VHR) optical remote sensing images. It categorizes the building detection methods into physical rule based methods, image segmentation based methods, and traditional and advanced machine learning methods. The article also discusses four promising research directions in building extraction and provides a better understanding of this topic for researchers.

GISCIENCE & REMOTE SENSING (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Oriented RepPoints for Aerial Object Detection

Wentong Li et al.

Summary: This paper proposes an adaptive points learning approach for aerial object detection, which captures the geometric information of arbitrary-oriented instances. Experimental results demonstrate the efficacy of the proposed method.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

ResNeSt: Split-Attention Networks

Hang Zhang et al.

Summary: The research presents a multi-branch architecture to improve representation learning in convolutional neural networks, leading to enhanced performance of deep learning models. Their approach leverages channel-wise attention to combine the strengths of feature-map attention and multi-path representation, resulting in more diverse representations.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022 (2022)

添加到收藏夹

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)

添加到收藏夹

Article Mathematics, Applied