相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Shaoshuai Shi et al.
Summary: This paper proposes Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on point clouds. The PV-RCNN model integrates point-based set abstraction and voxel-based sparse convolution for improved detection performance. The PV-RCNN++ framework further enhances efficiency and accuracy through sectorized proposal-centric sampling and VectorPool aggregation.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Computer Science, Interdisciplinary Applications
Xiangwen Shi et al.
Summary: In modern manufacturing, vision-based defect recognition is crucial for ensuring product quality. Deep learning-based methods have surpassed traditional approaches in accuracy and versatility. However, training deep learning models requires labeled data, which is scarce in many industrial applications. This paper presents a comparison dataset, Industrial-5(i), for defect detection methods using images of normal and abnormal products. The authors also propose a generic defect detection algorithm that performs well on new products. Their method outperforms existing few-shot segmentation methods on the Industrial-5(i) dataset, achieving significant improvements in mIoU and FB-IoU under both 1-shot and 5-shot tasks. The code is available on https://github.com/Alex-ShiLei/IndustrialNet.
COMPUTERS IN INDUSTRY
(2023)
Article
Agriculture, Multidisciplinary
Ning Wang et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Computer Science, Interdisciplinary Applications
Jaewoong Shim et al.
Summary: Virtual metrology is a method for monitoring wafer-to-wafer quality in semiconductor manufacturing using prediction models and physical metrology. This study proposes a domain-adaptive active learning method to address the issue of low prediction accuracy in the initial stage of active learning.
COMPUTERS IN INDUSTRY
(2022)
Article
Computer Science, Theory & Methods
Simone Antonelli et al.
Summary: Deep learning approaches have made significant progress in many fields with the support of large amounts of data. However, few-shot learning research is of great practical importance as it can effectively address the problem of scarce data, reducing the cost of data acquisition and achieving better generalization capability.
ACM COMPUTING SURVEYS
(2022)
Article
Automation & Control Systems
Tengfei Xue et al.
Summary: This article proposes a one-shot learning-based approach for segmenting animal videos using only one labeled frame. The approach consists of three main modules: guidance frame selection, Xception-based fully convolutional network, and postprocessing. Experimental results show that the proposed approach achieves good performance on the DAVIS 2016 animal dataset and outperforms state-of-the-art methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Agriculture, Multidisciplinary
Tianhai Wang et al.
Summary: This paper reviews the applications of machine vision in agricultural robot navigation, introduces the advantages, disadvantages, and roles of different vision sensors and algorithms, discusses the challenges faced in this field, and looks forward to future research directions.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Engineering, Civil
Guojun Wang et al.
Summary: This paper introduces an anchor-free CenterNet3D network for 3D object detection, utilizing keypoint estimation and a corner attention module. It outperforms state-of-the-art anchor-based methods on KITTI and nuScenes datasets, achieving a balance between speed and accuracy.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yasin Almalioglu et al.
Summary: Weather conditions are a challenge for autonomous vehicles. Almalioglu and colleagues use a geometry-aware learning technique to fuse visual, lidar, and radar information, enabling the use of each modality's benefits under different weather conditions.
NATURE MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Weisi Lin et al.
Summary: This paper discusses the concept of Just-Noticeable Difference (JND) and its importance in multimedia applications and services. Existing computational models for visual JND are reviewed, and research attempts for JNDs of other sensory signals and cross-modality/media efforts are surveyed. Finally, possible future directions and opportunities are analyzed.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Review
Engineering, Electrical & Electronic
Yutian Wu et al.
Summary: This article aims to review the challenges and methodologies of 3D object detection networks using LiDAR data. It begins with an overview of the 3D detection task and LiDAR sensing techniques, followed by an in-depth review of deep 3D detection networks with three kinds of LiDAR point cloud representations and their challenges. The article concludes by summarizing the evaluation metrics and performance of algorithms on three authoritative 3D detection benchmarks.
IEEE SENSORS JOURNAL
(2021)
Article
Agriculture, Multidisciplinary
Yuhan Ji et al.
Summary: This study proposed a method for obstacle detection and recognition in farmland environments using fusion point cloud data acquired from a tractor platform based on 3D/2D LiDAR and GNSS/AHRS. The method showed high accuracy, precision, recall, and F1score, meeting the operational requirements in the farmland environment.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Agriculture, Multidisciplinary
Hongzhen Xu et al.
Summary: This study used a panoramic camera and optical flow algorithm to quickly detect dynamic obstacles around agricultural machinery, improving safety and operation efficiency. By processing image frames, the detection accuracy reached 88.06%, meeting the requirements of actual farmland operations.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Computer Science, Artificial Intelligence
Ying Li et al.
Summary: This article reviews the progress of deep learning in processing LiDAR point cloud data, particularly in the field of autonomous driving, including tasks such as segmentation, detection, and classification. Despite several studies focusing on computer vision topics for autonomous vehicles, there is still a research gap in the application of DL in LiDAR point cloud data for autonomous vehicles.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Sara Grollius et al.
IEEE Transactions on Intelligent Vehicles
(2021)
Article
Automation & Control Systems
Adam Leon Kleppe et al.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2019)
Article
Computer Science, Artificial Intelligence
Zitian Chen et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Robotics
Jiadong Guo et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2019)
Article
Engineering, Civil
Zoltan Rozsa et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2018)
Article
Chemistry, Analytical
Yan Yan et al.
Article
Computer Science, Artificial Intelligence
Yulan Guo et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2016)
Article
Computer Science, Artificial Intelligence
Yulan Guo et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2013)
Article
Agriculture, Multidisciplinary
Liangliang Yang et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2012)
