Improved SURF Descriptor Based on Triangle Partition

2013 ◽  
Vol 718-720 ◽  
pp. 2296-2301 ◽  
Author(s):  
Zeng Luan ◽  
Zhai You ◽  
Xiong Wei
Keyword(s):  
Real Time ◽  
Image Matching ◽  
Weighting Function ◽  
Boundary Effect ◽  
Haar Wavelet ◽  
Local Region ◽  
Experimental Results ◽  
Time Performance ◽  
Wavelet Response ◽  
Better Than

In order to improve the robustness and real time performance of SURF based image matching algorithms, a new descriptor is proposed. We compute the new descriptor in a rectangle local region (the side set to 20s). Firstly, the local region is divided into 8 equal triangle subregion. Secondly, local region location grid is rotated to align its dominate orientation to a canonical direction. The keypoint dominate orientation and its orthogonalorientation is defined as the x and y directions of the descriptors local coordinate system.Thirdly, compute the Haar wavelet response in x and y directions within the keypoint local region. In order to reduce the boundary effect and outer noise, Haar wavelet response in the same Grid of different triangle is both assigned to each triangle in different weight, and then a gaussian weighting function is used. Compute the histogram of Haar wavelet response and absolute Haar wavelet response, so each triangle subregion constitutes a vector with 4 dimensions. Finally, a descriptor with 32 dimensions is constituted and the descriptor is normalized to achieve illumination invariance. The experimental results show that the performance of the new descriptor is even better than SURF descriptor.

Anti-Bias Association Algorithm for AIS and Radar Tracks Based on Centroid Reference Topological Characteristics

2014 ◽  
Vol 596 ◽  
pp. 511-518
Author(s):  
Lin Qi ◽  
Hai Peng Wang ◽  
Yu Liu ◽  
Cong Wang
Keyword(s):  
Real Time ◽  
Image Matching ◽  
Time Performance ◽  
Simulation Results ◽  
Topological Characteristics ◽  
System Errors ◽  
Association Algorithm

To achieve fast and accurate association for AIS and radar tracks, provide associated track-pairs for subsequent sensor bias registration and situational fusion, this paper presents an anti-bias association algorithm for AIS and radar tracks according to centroid reference topological characteristics (CRT). The algorithm describes the topological characteristics of track-points set on the basis of targets position relative to the centroid of the set to achieve AIS and radar tracks fine association in the presence of radar bias. The proposed algorithm outperforms the traditional tracks association algorithms based on image matching principle (IM) or targets reference topology feature (TRT) in terms of real-time performance, simultaneously has high correctly associated rate. Simulation results show that the falsely associated rate of this algorithm maintains 0, the correctly associated rate maintains above 85%. It can provide reliable associated track-pairs for system errors registration; while the average time-consuming of the algorithm is 1/4 and 1/417 of TRT and IM algorithm, the practicality has been significantly improved.

Sensitive Webpage Filter Based on Multiple Filtering

2012 ◽  
Vol 241-244 ◽  
pp. 2891-2896
Author(s):  
Dong Mei Wang ◽  
Ming Ma ◽  
Yan Sun
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Text Detection ◽  
Experimental Results ◽  
Skin Detection ◽  
Time Requirement ◽  
The Real ◽  
Time Performance

In order to improve the accuracy and real-time performance of webpage filtering, a sensitive webpage filter based on multiple filtering was designed. Firstly, the URL is gained from IE browser’s address bar by BHO technology; Secondly, match the webpage text with sensitive vocabulary database using SMA algorithm; Finally, use the sensitive image detecting algorithm combing face detection, skin detection, skin text detection and classification to filter sensitive images in the webpage. The Simulation experimental results showed that the sensitive webpage filter can effectively intercept and filter sensitive webpages, meeting the accuracy and the real-time requirement of webpage filtering.

Real-time digital simulator for distributed systems

SIMULATION ◽  
2021 ◽  
pp. 003754972098686
Author(s):  
Jinchao Chen ◽  
Chenglie Du ◽  
Pengcheng Han ◽  
Xiaoyan Du
Keyword(s):  
Distributed Systems ◽  
Real Time ◽  
Experimental Results ◽  
Data Driven ◽  
New Approach ◽  
Support Tool ◽  
Time Performance ◽  
Simulator Design ◽  
Data Buses ◽  
Real Time Digital Simulator

Simulation has been widely adopted as a support tool for the validation and experimentation of distributed systems. It allows different devices and applications to be evaluated and analyzed without requiring the actual presence of those machines. Although the simulation plays an important role in investigating and evaluating the behaviors of devices, it results in a serious simulator building problem as the distributed systems become more and more complicated and dynamically data driven. Most of the existing simulators are designed and developed to target a specific type of application, lacking the capabilities to be a configurable and standardized tool for researchers. To solve the adaptability and reusability problems of simulators, this paper proposes a new approach to design and implement a configurable real-time digital simulator for hardware devices that are connected via data buses in distributed systems. First, the proposed simulator uses a logic automaton to simulate the activities of a real device, and generates the incentive data for tested equipment according to the predefined XML-based files. Then with a virtual bus, the simulator can receive, handle, and send data in various network environments, improving the flexibility and adaptability of a simulator design. Experimental results show that the proposed simulator has a high real-time performance, and can meet the increasing requirements of modern simulations of distributed systems.

scholarly journals Machine-learning-based children’s pathological gait classification with low-cost gait-recognition system

2021 ◽  
Author(s):  
Linghui Xu ◽  
Jiansong Chen ◽  
Fei Wang ◽  
Yuting Chen ◽  
Wei Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Plantar Pressure ◽  
Recognition Accuracy ◽  
Low Cost ◽  
Gait Recognition ◽  
Recognition System ◽  
Experimental Results ◽  
Time Performance ◽  
Pathological Gait

Abstract Background: Pathological gaits of children may lead to terrible diseases, such as osteoarthritis or scoliosis. By monitoring the gait pattern of a child, proper therapeutic measures can be recommended to avoid the terrible consequence. However, low-cost systems for pathological gait recognition of children automatically have not been on market yet. Our goal was to design a low-cost gait-recognition system for children with only pressure information.Methods: In this study, we design a pathological gait-recognition system (PGRS) with an 8 × 8 pressure-sensor array. An intelligent gait-recognition method (IGRM) based on machine learning and pure plantar pressure information is also proposed in static and dynamic sections to realize high accuracy and good real-time performance. To verifying the recognition effect, a total of seventeen children were recruited in the experiments wearing PGRS to recognize three pathological gaits (toe in, toe out, and flat) and normal gait. Children are asked to walk naturally on level ground in the dynamic section or stand naturally and comfortably in the static section. The evaluation of the performance of recognition results included stratified 10-fold cross-validation with recall, precision, and a time cost as metrics.Results: The experimental results show that all of the IGRMs have been identified with a practically applicable degree of average accuracy either in the dynamic or static section. Experimental results indicate that the IGRM has 92.41% and 97.79% recognition accuracy respectively in the static and dynamic sections. And we find methods in the static section have less recognition accuracy due to the unnatural gesture of children when standing.Conclusions: In this study, a low-cost PGRS has been verified and realize feasibility, highly average precision, and good real-time performance of gait recognition. The experimental results reveal the potential for the computer supervision of non-pathological and pathological gaits in the plantar-pressure patterns of children and for providing feedback in the application of gait-abnormality rectification.

A Smart Wiper System Based on Feedforward-Feedback Composite Controller

2012 ◽  
Vol 472-475 ◽  
pp. 1446-1450
Author(s):  
Xian Zhong Ren ◽  
Mei Fu Luo ◽  
Ya Nan Qiu
Keyword(s):  
Real Time ◽  
Software Design ◽  
Good Accuracy ◽  
Experimental Results ◽  
Time Performance ◽  
Key Factor ◽  
Feedback Algorithm

The velocity of the wiper arms is a key factor which can influence the clarity of the windshield and the comfort of the driver’s view. So how to control the velocity of the wiper arms is important. To solve the problem, a method is elaborated based on feedforward-feedback composite controller. It introduces the hardware and software design based on the feedforward-feedback algorithm, controlling the velocity of the wiper arms by adjusting the duty of PWM. The experimental results indicate that the smart wiper system is reliable, and has good accuracy and real-time performance.

scholarly journals A Signature Identification Method Based on Strength and Strokes Direction

2011 ◽  
Vol 2-3 ◽  
pp. 223-227
Author(s):  
Hai Long Huang ◽  
Hong Wang ◽  
Li Ji
Keyword(s):  
Real Time ◽  
Mathematical Morphology ◽  
Experimental Results ◽  
Time Performance ◽  
New Methods ◽  
Identification Method ◽  
Available Information

It was much more complex and difficult for off-line signature identification attributable to the limitation of available information. To solve the problem, a signature identification method based on strength and strokes direction was proposed. The signature image acquired was gray-scaled and filtered at the stage of preprocess; then the image was two-valued with different threshold based on strength feature, the regions which grayscale was less than threshold were retained; the strokes which possess distinctive directional feature were extracted by using mathematical morphology and combining different scales/directions structure element based on strokes direction feature; at last judgement was maked for sample in accordance with corresponding feature. Experimental results showed the proposed method can enhance accurate rate effectively, improve real-time performance, which was a try beneficial to apply new methods for off-line signature identification.

A Solution for Image Matching Error in SURF

2013 ◽  
Vol 717 ◽  
pp. 523-528
Author(s):  
Xing Xiong ◽  
Byung Jae Choi
Keyword(s):  
Real Time ◽  
Image Matching ◽  
Extraction Method ◽  
Matching Error ◽  
Speeded Up Robust Features ◽  
Time Performance ◽  
Integral Images

SURF (Speeded Up Robust Features) is known to be a famous and strong but computationally still expensive.It has not attained real-time performance yet. In this paper we analysis the SURF in orientation and descriptors extraction method forresolvingsome problems. For example, matching images through the SURF algorithm spends too much time and causes some errors by integral images. We propose a novel orientation and descriptor algorithm to improve the conventional SURF. Theproposed method shows some advantages such as a faster speed.

Implementation of Multi-Core Parallel Computation for Real-Time Turning of PID Parameters Based on Genetic Algorithm

2012 ◽  
Vol 159 ◽  
pp. 132-136
Author(s):  
Shuang Shi Zhang ◽  
Xu Ben Wang ◽  
Wei Hua Wang
Keyword(s):  
Genetic Algorithm ◽  
Process Control ◽  
Real Time ◽  
Parallel Computation ◽  
Experimental Results ◽  
Parallel Genetic Algorithm ◽  
Control Computer ◽  
Process Control Computer ◽  
Better Than

The aim of the work described in this paper is to investigate the implementation of Multi-core Parallel Genetic Algorithm (McPGA) for real-time turning of PID parameters based on it using OpenMP. The performance of our scheme is discussed in comparison with that of the Sequential Genetic Algorithm (SGA) program running on the same computer. Numerical experimental results clearly show that McPGA is much better than SGA on convergence, premature and optimized speed. It can be used for PID parameter real-time turning in Industry Process Control Computer (IPC).

Research on Automatic Magnetic Deviation Compensation of Electronic Compass for Quadrotor

2013 ◽  
Vol 347-350 ◽  
pp. 995-999
Author(s):  
Wen Jian Xiao ◽  
Ping Lu
Keyword(s):  
Measurement Error ◽  
Real Time ◽  
Horizontal Plane ◽  
Magnetic Sensor ◽  
Experimental Results ◽  
Sensor Data ◽  
Automatic Compensation ◽  
Time Performance ◽  
Heading Angle ◽  
Electronic Compass

In magnetic heading measurement of quadrotor, it is necessary to compensate the magnetic deviation of the electronic magnetic compass. For the flight characteristics of quadrotor, a method using sampling data when the aircraft is in the air to achieve automatic compensation of the deviation has been proposed. Using elliptical hypothesis method one can only compensate deviation for quadrotor flying in horizontal plane by collecting the magnetic sensor data in different directions. When the quadrotor flying in any attitudes, using ellipsoid hypothesis method can obtain parameters used by magnetic deviation compensation. Using these parameters, the pitch and roll angles of quadrotor, the magnetic deviation could be compensated. Experimental results show that this method works well and has a good real time performance. The measurement error of heading angle could be less than 1 °.

Detection of Video Shot Changes Based on Image Matching

2012 ◽  
Vol 263-266 ◽  
pp. 2064-2069
Author(s):  
Zong Guo Yao ◽  
Min Qin ◽  
Guan Wang ◽  
Jin Ping Li
Keyword(s):  
Change Detection ◽  
Real Time ◽  
Image Matching ◽  
Gray Level ◽  
Key Points ◽  
Video Shot ◽  
Novel Method ◽  
Cut Detection ◽  
Tv Commercials ◽  
Better Than

In order to improve the supervision of TV commercials and reduce the illegal ones, it is necessary to develop a system to detect TV commercials in real time. One of the key points is to detect video shot changes. We put forward a novel method of image matching for shot change detection: firstly, a feature coding is introduced for describing image local gray level distribution; secondly, image matching is performed according to the feature coding; thirdly, shot changes can be detected. A preliminary system of video shot change detection is developed. Experiments show that the algorithm is better than traditional algorithms and can well meet the need of TV Video shot cut detection.

Sign in / Sign up

Export Citation Format

Share Document