Real-time object recognition using a modified generalized Hough transform

2003 ◽  
Vol 36 (11) ◽  
pp. 2557-2570 ◽  
Author(s):  
Markus Ulrich ◽  
Carsten Steger ◽  
Albert Baumgartner
Keyword(s):  
Object Recognition ◽  
Real Time ◽  
Hough Transform ◽  
Generalized Hough Transform

Windage Yaw Angle Detection of Suspension Insulator Strings Based on Edge Feature Matching

2012 ◽  
Vol 241-244 ◽  
pp. 98-103
Author(s):  
Hai Jun Lu ◽  
Yu Xiang Lv ◽  
Wei Qing Ma ◽  
Xiao Long Zhao ◽  
Xue Lian Zheng
Keyword(s):  
Real Time ◽  
Hough Transform ◽  
Feature Matching ◽  
Matching Accuracy ◽  
A Algorithm ◽  
Generalized Hough Transform ◽  
Suspension Insulator ◽  
Depth Analysis ◽  
Yaw Angle ◽  
Edge Feature

By in-depth analysis and summary of tower suspension insulator strings images collected, a algorithm of edge feature matching of suspension insulator strings was proposed to detect the windage yaw angle in real-time. By filter, image grayscale, interframe difference and edge feature matching which based on invariance Generalized Hough Transform (IGHT) and local feature of suspension insulator strings stored in a database, the coordinates of the ends of suspension insulator strings were determined, and then the size of windage yaw angle of suspension insulator strings was calculated. The algorithm proposed can provide translation, scaling and rotation invariance, and be better matching accuracy and robustness.

Real-time pattern recognition using an optical generalized Hough transform

2015 ◽  
Vol 54 (36) ◽  
pp. 10586 ◽  
Author(s):  
Ariel Fernández ◽  
Jorge L. Flores ◽  
Julia R. Alonso ◽  
José A. Ferrari
Keyword(s):  
Pattern Recognition ◽  
Real Time ◽  
Hough Transform ◽  
Time Pattern ◽  
Generalized Hough Transform

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

INVESTIGATION ON MULTISETS MIXTURE LEARNING BASED OBJECT DETECTION

2007 ◽  
Vol 21 (08) ◽  
pp. 1339-1351 ◽  
Author(s):  
ZHI-YONG LIU ◽  
HONG QIAO ◽  
LEI XU
Keyword(s):  
Object Detection ◽  
Hough Transform ◽  
Line Segment ◽  
Reconstruction Error ◽  
Mean Square ◽  
Noise Resistance ◽  
Generalized Hough Transform ◽  
The Mean ◽  
Sample Reconstruction

By minimizing the mean square reconstruction error, multisets mixture learning (MML) provides a general approach for object detection in image. To calculate each sample reconstruction error, as the object template is represented by a set of contour points, the MML needs to inefficiently enumerate the distances between the sample and all the contour points. In this paper, we develop the line segment approximation (LSA) algorithm to calculate the reconstruction error, which is shown theoretically and experimentally to be more efficient than the enumeration method. It is also experimentally illustrated that the MML based algorithm has a better noise resistance ability than the generalized Hough transform (GHT) based counterpart.

Sign in / Sign up

Export Citation Format

Share Document