A FPGA and Zernike Moments Based Near-Field Laser Imaging Detector Multi-scale Real-Time Target Recognition Algorithm

2010 ◽  
Author(s):  
Li-feng Liu ◽  
Hui-min Ma ◽  
Ming-quan Lu
Keyword(s):  
Real Time ◽  
Target Recognition ◽  
Near Field ◽  
Recognition Algorithm ◽  
Zernike Moments ◽  
Laser Imaging ◽  
Multi Scale ◽  
Imaging Detector

Target Recognition Algorithm Based on Two-Dimensional Wavelet Transform for Laser Imaging Radar

2011 ◽  
Vol 48 (4) ◽  
pp. 041001
Author(s):  
陈晓清 Chen Xiaoqing ◽  
马君国 Ma Junguo ◽  
赵宏钟 Zhao Hongzhong ◽  
付强 Fu Qiang
Keyword(s):  
Wavelet Transform ◽  
Target Recognition ◽  
Recognition Algorithm ◽  
Two Dimensional ◽  
Laser Imaging ◽  
Imaging Radar

Analysis and Improvement in Color-Based Target Recognition Algorithm of Robot

2013 ◽  
Vol 655-657 ◽  
pp. 1043-1047 ◽  
Author(s):  
Dong Bo Zhou ◽  
Ji Cai Deng ◽  
Geng Hui Wang ◽  
Qi Xin Deng
Keyword(s):  
Control System ◽  
Real Time ◽  
Humanoid Robot ◽  
Target Recognition ◽  
Robot Vision ◽  
Recognition Algorithm ◽  
Color Information ◽  
Real Time Control ◽  
Table Lookup ◽  
Time Control

In the Martial Arts arena contest of robot, Humanoid robot should recognize the target timely and accurately. So robot vision technology becomes a key of the contest. In this paper, target recognition algorithms based on color information are analyzed. According to the results, an improved algorithm based on Table Lookup method is proposed, which aimed to provide more rapidity of computing in real-time control system on the robot. It is shown in illustrative experiment that average 50% time was saved in computing when using the new algorithm instead of traditional algorithms.

Target Type Recognition Algorithm of Imaging GIF Fuze

2013 ◽  
Vol 416-417 ◽  
pp. 1170-1175
Author(s):  
Bin Liu ◽  
Yang Yu Fan ◽  
Jian Guo
Keyword(s):  
Feature Extraction ◽  
Image Segmentation ◽  
Edge Detection ◽  
Real Time ◽  
Target Recognition ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Target Type ◽  
Time Performance ◽  
Simulation Results

According to the requirement of aerial infrared target recognition, a group of image segmentation, edge detection, feature extraction, type recognition algorithms are put forward in this article after analysis and comparison of many algorithms. The simulation results show that the typical aerial target type recognition rate of this group of algorithms can reach more than 80%, so that the algorithms have higher ability of target type recognition, and its real-time performance can meet the requirement of imaging GIF fuze.

Target Recognition Algorithm Based on Combination Moments for Laser Imaging Radar

2012 ◽  
Vol 39 (6) ◽  
pp. 0609003
Author(s):  
马君国 Ma Junguo ◽  
黄孟俊 Huang Mengjun
Keyword(s):  
Target Recognition ◽  
Recognition Algorithm ◽  
Laser Imaging ◽  
Imaging Radar

SVM-based global vision system of sports competition and action recognition

2020 ◽  
pp. 1-12
Author(s):  
Changxin Sun ◽  
Di Ma
Keyword(s):  
Target Recognition ◽  
Vision System ◽  
Task Assignment ◽  
Recognition Algorithm ◽  
Control Factor ◽  
Training Time ◽  
Adaboost Algorithm ◽  
Advantages And Disadvantages ◽  
Time Control ◽  
Correlation Degree

In the research of intelligent sports vision systems, the stability and accuracy of vision system target recognition, the reasonable effectiveness of task assignment, and the advantages and disadvantages of path planning are the key factors for the vision system to successfully perform tasks. Aiming at the problem of target recognition errors caused by uneven brightness and mutations in sports competition, a dynamic template mechanism is proposed. In the target recognition algorithm, the correlation degree of data feature changes is fully considered, and the time control factor is introduced when using SVM for classification,At the same time, this study uses an unsupervised clustering method to design a classification strategy to achieve rapid target discrimination when the environmental brightness changes, which improves the accuracy of recognition. In addition, the Adaboost algorithm is selected as the machine learning method, and the algorithm is optimized from the aspects of fast feature selection and double threshold decision, which effectively improves the training time of the classifier. Finally, for complex human poses and partially occluded human targets, this paper proposes to express the entire human body through multiple parts. The experimental results show that this method can be used to detect sports players with multiple poses and partial occlusions in complex backgrounds and provides an effective technical means for detecting sports competition action characteristics in complex backgrounds.

Sign in / Sign up

Export Citation Format

Share Document