Product Design, Manufacturing & Innovation Resources

计算机视觉领域的最新出版物和专利

计算机视觉

提示:除以下选择外,您还可以搜索和过滤我们的 2 个完整数据库:

> 免费出版物搜索工具 < 按作者、主题、关键词、日期或期刊分类。

> 免费专利搜索工具 < 适用于欧洲专利局提供的英文专利。

计算机视觉
计算机视觉技术的进步利用图像处理和机器学习来实现创新应用。 机器人技术 以及医学影像。

计算机视觉专注于从图像和视频中自动提取、分析和解释视觉信息。该学科融合了图像处理、模式识别和机器学习,以解决诸如目标检测、分割、识别和三维重建等任务。研究探索了卷积神经网络、光流、深度估计和场景理解等方面的最新进展,使其能够应用于机器人、监控、医学成像和自主系统等领域。以下收录了近期发表的学术论文和已获专利的成果。 技术 推进计算机视觉领域的方法论和应用:

这是我们最新精选的有关计算机视觉的全球英文出版物和专利,它们来自许多科学在线期刊,分类并侧重于图像分割、对象检测、特征提取、卷积神经网络、图像分类、光流、立体视觉、深度估计、图像识别、场景理解、图像重建、图像增强、模式识别、面部识别、运动跟踪、三维重建、图像注册、计算机视觉、语义分割、实例分割、视觉 SLAM、图像拼接、纹理分析、边缘检测、对象跟踪、超分辨率、图像去噪、视频分析、异常检测和图像标题。.

A method of, and system for, anomaly detection in an industrial plant

Patent published on the 2026-05-21 in WO under Ref WO2026106595 by AIR PROD & CHEM [US] (D'souza Prashanth [sa], Guha Avishek [us], Morabito Michael John [us], Arslan Erdem [us])

Abstract: A computer-implemented method of monitoring an operational area of an industrial plant, the method utilizing a monitoring system comprising a plurality of sensors located in the operational area and connected to a computer system by a network, the method being executed by at least one hardware processor and comprising the steps of: obtaining sensor measurement data representative of measured values of one or more physical parameters, the sensor measurement data being synchronously captured from [...]


Our summary: The method monitors an industrial plant using a network of sensors. It captures and processes sensor data to create feature maps. These feature maps are used to identify operational anomalies in real-time.

anomaly detection, industrial plant, sensor data, feature maps

Patent

System and method for geospatially-contextualised behavioral anomaly detection for remote worker safety

Patent published on the 2026-05-21 in WO under Ref WO2026102499 by AIRAGRI SERVICES PTY LTD [AU] (Diamond James [au], Diamond Paul [au])

Abstract: A computerised system for environment-based accident, incident, or risk detection for human subjects in outdoor environments comprises at least one user device configured to be carried or worn by a human subject. The at least one user device comprises a location determination module; a movement detection module comprising at least one of an accelerometer, gyroscope, or other motion sensor; and a communication module configured to transmit data via non- cellular-dependent protocols. The system fu[...]


Our summary: The system detects risks for remote workers in outdoor environments using user devices with location and movement sensors. It analyzes environmental data, including terrain and weather conditions, to create active monitoring zones. Behavioral anomalies are identified by comparing current movements to historical data under similar conditions.

geospatial analysis, behavioral anomaly detection, remote worker safety, environmental monitoring

Patent

Virtual reality pose estimation apparatus and method using haptic device

Patent published on the 2026-05-21 in WO under Ref WO2026106377 by UNIV NAT CHONNAM IND FOUND [KR] (Kim Myeong-jin [kr], Yong Han-bit [kr], Kim Hyeon-su [kr])

Abstract: The present invention relates to a virtual reality pose estimation apparatus and method using a haptic device. The apparatus comprises: an input unit for receiving, through a plurality of input devices, input point data for the estimation of a pose of a haptic device; a global feature extraction unit which inputs the input point data into a multilayer perceptron (MLP) model so as to extract point-wise features, and which extracts a global feature on the basis of the point-wise features; and a po[...]


Our summary: The invention details a virtual reality pose estimation system utilizing a haptic device. It includes an input unit for gathering data from multiple devices to estimate the haptic device s pose. A multilayer perceptron model extracts features from the input data, which are then processed by a hierarchical neural network for pose estimation.

virtual reality, pose estimation, haptic device, neural network

Patent

Methods and systems for network anomaly detection and remediation

Patent published on the 2026-05-21 in US under Ref US20260142992 by T MOBILE INNOVATIONS LLC [US] (Duncan Troy [us], Kumar Jyot [us], Prasad Bhanu [us], Sumanth Shrustishree [us])

Abstract: [0000] A method comprising training a predictive model system using historical data describing prior incidents that occurred in the communication network, wherein the historical data comprising prior incident data, prior subscriber usage data associated with the prior incidents, and prior performance data associated with the prior incidents, detecting an anomaly event based on current network parameters, wherein the anomaly event is an event or state occurring across one or more of network eleme[...]


Our summary: The method trains a predictive model using historical data on prior network incidents and subscriber usage. It detects anomalies based on current network parameters that indicate potential future incidents. The system then instructs remediation actions to address the detected anomalies.

anomaly detection, predictive modeling, network performance, remediation systems

Patent

Automatic selection method and system for endoscopic images

Patent published on the 2026-05-21 in US under Ref US20260141515 by INVENTEC CORP [TW] (Chou Chun-ti [tw], Chen Wei-chao [tw], Wei Chih-pin [tw], Huang Po Hsuan [tw], Cheng Jen-po [tw], Lu Chiu-jung [tw])

Abstract: [0000] An automatic selection method and system for endoscopic images are proposed. This method includes several steps performed by a computing device, which involve: obtaining multiple endoscopic images and their corresponding position markers, with each marker indicating a specific part of a human organ captured by the endoscope. Based on these position markers, multiple candidate images belonging to the same organ part are selected from the endoscopic images. An image segmentation is performe[...]


Our summary: The proposed method automates the selection of endoscopic images using position markers. It segments candidate images into non-overlapping regions based on color or symptoms. A ratio of the regions is calculated to determine the final selected image.

endoscopic images, automatic selection, image segmentation, position markers

Patent

Dashcam network with route logging and computer vision for targeted video search capabilities

Patent published on the 2026-05-21 in US under Ref US20260141557 by OWENS NICHOLAS DEMES [US] (Owens Nicholas Demes [us])

Abstract: [0000] The present invention discloses a system to assist investigations for storage and targeted search of metadata and video collected by dashcams. The invention efficiently guides video evidence search using stored route metadata versus complete footage, tackling the challenges of distributed footage across vehicles. The system enhances investigations by unlocking previously inaccessible visual evidence in a targeted manner while optimizing storage and bandwidth. Vehicles equipped with camera[...]


Our summary: The invention provides a system for targeted video search and route logging using dashcam footage. It enables efficient investigations by utilizing stored route metadata to access relevant video evidence. The system employs computer vision algorithms to analyze metadata, assisting investigators in locating specific footage based on defined parameters.

dashcam, computer vision, metadata, video search

Patent

Cross-reference attention for region-aware super-resolution of blood cell images

Published on 2026-05-01 by @OXFORD

Abstract: AbstractBlood cell image analysis plays a critical role in clinical diagnostics, as white blood cells (WBCs) provide diagnostic cues for infections, cancers, and immune disorders. While low-magnification microscopy offers a wide field of view (FOV) but insufficient resolution for meaningful assessment, high-magnification microscopy offers more detailed but narrower FOV images. To obtain a high-magnification, large FOV image, current practice relies on stitching multiple high-magnification images[...]


Our summary: This study introduces a multi-reference-based super-resolution framework for blood cell microscopy. It employs a Cross-Reference Attention Module to enhance image quality and efficiency. The method outperforms traditional stitching techniques, providing large field-of-view images with improved white blood cell detail.

super-resolution, blood cell imaging, cross-reference attention, region-aware architecture

Publication

Investigating the temporal dynamics and modeling of mid-level feature representations in humans

Published on 2026-04-27 by @MIT

Abstract: AbstractVisual perception unfolds through a hierarchy of transformations, beginning with the extraction of low-level features, such as edges, and culminating in the representation of high-level features such as object categories. While the processing of low- and high-level features is well studied, the intermediate transformations, that is, mid-level features, remain poorly understood. Here, we introduce a stimulus set of naturalistic 3D-rendered images and videos with ground-truth annotations f[...]


Our summary: This study investigates mid-level feature representations in visual perception using 3D-rendered images and videos. It identifies the processing time of these features in the brain through EEG responses. The results suggest mid-level features connect sensory and semantic processing, and CNNs can model this processing order.

mid-level features, visual perception, EEG responses, convolutional neural networks

Publication

涵盖的主题: 图像处理、机器学习、机器人、医学成像、自动提取、分析、解释、模式识别、对象检测、分割、卷积神经网络、三维重建、光流、深度估计、场景理解、监控、自主系统、ISO/IEC 30170、ISO/IEC 19578、ISO 12234、ISO/IEC 19794 和 ISO/IEC 29192。.

历史背景

1829
1850
1854
1854
1895
1899
1900
1828
1848
1850
1854
1884
1896
1900
1903

(如果日期未知或不相关,例如“流体力学”,则提供其显著出现的近似估计)

只有注册会员才能免费获得 100% 的全尺寸图片和下载。.

> 登录 <