Robot Simultaneous Localization and Mapping Using Speeded-Up Robust Features

2013 ◽  
Vol 284-287 ◽  
pp. 2142-2146 ◽  
Author(s):  
Yin Tien Wang ◽  
Chen Tung Chi ◽  
Ying Chieh Feng
Keyword(s):  
Feature Recognition ◽  
Vision System ◽  
Recognition Rate ◽  
Simultaneous Localization And Mapping ◽  
Integrated System ◽  
Detection Methods ◽  
Speeded Up Robust Features ◽  
Localization And Mapping ◽  
Environmental Map ◽  
Binocular Vision System

An algorithm for robot mapping is proposed in this paper using the method of speeded-up robust features (SURF). Since SURFs are scale- and orientation-invariant features, they have higher repeatability than that of the features obtained by other detection methods. Even in the cases of using moving camera, the SURF method can robustly extract the features from image sequences. Therefore, SURFs are suitable to be utilized as the map features in visual simultaneous localization and mapping (SLAM). In this article, the procedures of detection and matching of the SURF method are modified to improve the image processing speed and feature recognition rate. The sparse representation of SURF is also utilized to describe the environmental map in SLAM tasks. The purpose is to reduce the computation complexity in state estimation using extended Kalman filter (EKF). The EKF SLAM with SURF-based map is developed and implemented on a binocular vision system. The integrated system has been successfully validated to fulfill the basic capabilities of SLAM system.

Determination of Maize Seed Purity Based on Multi-Step Clustering

2018 ◽  
Vol 34 (4) ◽  
pp. 659-665
Author(s):  
Shuangxi Liu ◽  
Hongjian Zhang ◽  
Zhen Wang ◽  
Chunqing Zhang ◽  
Yan Li ◽  
...  
Keyword(s):  
Binocular Vision ◽  
Vision System ◽  
Recognition Rate ◽  
Model Parameters ◽  
Experimental Sample ◽  
Maize Seed ◽  
Maize Seeds ◽  
Clustering Model ◽  
Binocular Vision System

Abstract. Electrophoresis has been widely used to determine maize seed purity; however, the associated time and complexity hinder its application for maize seeds. Equipment to estimate seed purity was designed to improve the efficiency of identification of circulating maize seeds, and a multi-step clustering method was created for the determination of seed purity. The main components included a host computer, a black box, a seed transmission belt with grooves, a binocular vision system, and an under-controller. First, image information of the crown and the non-embryo side of every maize seed was collected using the binocular vision system while seeds underwent intermittent movement on the transmission belt. Second, multi-area color characteristics, which included red, green, and blue (RGB), hue, saturation, intensity (HSI), and lightness-a-b (Lab) color model parameters of maize seeds were extracted and optimized to generate 25-dimensional purity identification vectors. Finally, a multi-step clustering model was used to determine seed purity. The original center of K-mean clustering was established based on the results of self-organizing map (SOM) clustering; subsequently, maize seed purity parameters were obtained by combining the results of the second and the first clustering analyses. A result was achieved by testing three groups of samples, including 'ZHENGDAN 958' mixed with 'XIANYU 335', 'XIANYU 335' mixed with its male parent, and 'XIANYU 335' mixed with its female parent. The result showed that the correct recognition rate of 'XIANYU 335' mixed with 'ZHENGDAN 958' that had no genetic relationship could reach 100% under the condition of the experimental sample, and the accuracy of identification between 'XIANYU 335' and their respective male and female parents was 96.7% and 88.7%. This recognition rate met with the technical requirements of field inspection and provided a reliable scientific basis for the rapid determination of maize seed purity. Keywords: Identification, Maize seed, Multi-step clustering, Purity, Rapid.

Improvement of speeded-up robust features for robot visual simultaneous localization and mapping

Robotica ◽  
2013 ◽  
Vol 32 (4) ◽  
pp. 533-549 ◽  
Author(s):  
Yin-Tien Wang ◽  
Guan-Yu Lin
Keyword(s):  
State Estimation ◽  
Simultaneous Localization And Mapping ◽  
Dynamic Effect ◽  
Image Features ◽  
Actual System ◽  
Scale Invariant ◽  
Visual Landmarks ◽  
Mapping Procedure ◽  
Speeded Up Robust Features ◽  
Localization And Mapping

SUMMARYA robot mapping procedure using a modified speeded-up robust feature (SURF) is proposed for building persistent maps with visual landmarks in robot simultaneous localization and mapping (SLAM). SURFs are scale-invariant features that automatically recover the scale and orientation of image features in different scenes. However, the SURF method is not originally designed for applications in dynamic environments. The repeatability of the detected SURFs will be reduced owing to the dynamic effect. This study investigated and modified SURF algorithms to improve robustness in representing visual landmarks in robot SLAM systems. Many modifications of the SURF algorithms are proposed in this study including the orientation representation of features, the vector dimension of feature description, and the number of detected features in an image. The concept of sparse representation is also used to describe the environmental map and to reduce the computational complexity when using extended Kalman filter (EKF) for state estimation. Effective procedures of data association and map management for SURFs in SLAM are also designed to improve accuracy in robot state estimation. Experimental works were performed on an actual system with binocular vision sensors to validate the feasibility and effectiveness of the proposed algorithms. The experimental examples include the evaluation of state estimation using EKF SLAM and the implementation of indoor SLAM. In the experiments, the performance of the modified SURF algorithms was compared with the original SURF algorithms. The experimental results confirm that the modified SURF provides better repeatability and better robustness for representing the landmarks in visual SLAM systems.

Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots

2017 ◽  
Vol 34 (4) ◽  
pp. 1217-1239 ◽  
Author(s):  
Chen-Chien Hsu ◽  
Cheng-Kai Yang ◽  
Yi-Hsing Chien ◽  
Yin-Tien Wang ◽  
Wei-Yen Wang ◽  
...  
Keyword(s):  
Computational Efficiency ◽  
Simultaneous Localization And Mapping ◽  
Estimation Accuracy ◽  
Average Error ◽  
Particle State ◽  
Visual Slam ◽  
Computationally Efficient ◽  
Content Type ◽  
Speeded Up Robust Features ◽  
Localization And Mapping

Purpose FastSLAM is a popular method to solve the problem of simultaneous localization and mapping (SLAM). However, when the number of landmarks present in real environments increases, there are excessive comparisons of the measurement with all the existing landmarks in each particle. As a result, the execution speed will be too slow to achieve the objective of real-time navigation. Thus, this paper aims to improve the computational efficiency and estimation accuracy of conventional SLAM algorithms. Design/methodology/approach As an attempt to solve this problem, this paper presents a computationally efficient SLAM (CESLAM) algorithm, where odometer information is considered for updating the robot’s pose in particles. When a measurement has a maximum likelihood with the known landmark in the particle, the particle state is updated before updating the landmark estimates. Findings Simulation results show that the proposed CESLAM can overcome the problem of heavy computational burden while improving the accuracy of localization and mapping building. To practically evaluate the performance of the proposed method, a Pioneer 3-DX robot with a Kinect sensor is used to develop an RGB-D-based computationally efficient visual SLAM (CEVSLAM) based on Speeded-Up Robust Features (SURF). Experimental results confirm that the proposed CEVSLAM system is capable of successfully estimating the robot pose and building the map with satisfactory accuracy. Originality/value The proposed CESLAM algorithm overcomes the problem of the time-consuming process because of unnecessary comparisons in existing FastSLAM algorithms. Simulations show that accuracy of robot pose and landmark estimation is greatly improved by the CESLAM. Combining CESLAM and SURF, the authors establish a CEVSLAM to significantly improve the estimation accuracy and computational efficiency. Practical experiments by using a Kinect visual sensor show that the variance and average error by using the proposed CEVSLAM are smaller than those by using the other visual SLAM algorithms.

LEFT: LOCAL EDGE FEATURES TRANSFORM

2020 ◽  
pp. 11-18
Author(s):  
T. A. Tikhomirova ◽  
G. T. Fedorenko ◽  
K. M. Nazarenko ◽  
E. S. Nazarenko
Keyword(s):  
Large Scale ◽  
Vision System ◽  
Mutual Orientation ◽  
Feature Points ◽  
Scale Invariant ◽  
Actual Object ◽  
Speeded Up Robust Features ◽  
Localization And Mapping ◽  
Edge Features ◽  
Local Edge

To detect point correspondence between images or 3D scenes, local texture descriptors, such as SIFT (Scale Invariant Feature Transform), SURF (Speeded-Up Robust Features), BRIEF (Binary Robust Independent Elementary Features), and others, are usually used. Formally they provide invariance to image rotation and scale, but this properties are achieved only approximately due to discrete number of evaluable orientations and scales stored into the descriptor. Feature points preferable for such descriptors usually are not belong to actual object boundaries into 3D scenes and so are hard to be used into apipolar relationships. At the same time, linking the feature point to large-scale lines and edges is preferable for SLAM (Simultaneous Localization And Mapping) tasks, because their appearance are the most resistible to daily, seasonal and weather variations.In this paper, original feature points descriptor LEFT (Local Edge Features Transform) for edge images are proposed. LEFT accumulate directions and contrasts of alternative strait segments tangent to lines and edges in the vicinity of feature points. Due to this structure, mutual orientation of LEFT descriptors are evaluated and taken into account directly at the stage of their comparison. LEFT descriptors adapt to the shape of contours in the vicinity of feature points, so they can be used to analyze local and global geometric distortions of a various nature. The article presents the results of comparative testing of LEFT and common texture-based descriptors and considers alternative ways of representing them in a computer vision system.

A Review: Simultaneous Localization and Mapping Algorithms

2015 ◽  
Vol 73 (2) ◽  
Author(s):  
Saif Eddine Hadji ◽  
Suhail Kazi ◽  
Tang Howe Hing ◽  
Mohamed Sultan Mohamed Ali
Keyword(s):  
Autonomous Navigation ◽  
State Of The Art ◽  
Simultaneous Localization And Mapping ◽  
The State ◽  
Sensor Data ◽  
Current Position ◽  
Mapping Algorithms ◽  
The Past ◽  
Localization And Mapping ◽  
Environmental Map

Simultaneous Localization and Mapping (SLAM) involves creating an environmental map based on sensor data, while concurrently keeping track of the robot’s current position. Efficient and accurate SLAM is crucial for any mobile robot to perform robust navigation. It is also the keystone for higher-level tasks such as path planning and autonomous navigation. The past two decades have seen rapid and exciting progress in solving the SLAM problem together with many compelling implementations of SLAM methods. In this paper, we will review the two common families of SLAM algorithms: Kalman filter with its variations and particle filters. This article complements other surveys in this field by reviewing the representative algorithms and the state-of-the-art in each family. It clearly identifies the inherent relationship between the state estimation via the KF versus PF techniques, all of which are derivations of Bayes rule.

scholarly journals Indoor SLAM Using Laser and Camera with Closed-Loop Controller for NAO Humanoid Robot

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Shuhuan Wen ◽  
Kamal Mohammed Othman ◽  
Ahmad B. Rad ◽  
Yixuan Zhang ◽  
Yongsheng Zhao
Keyword(s):  
Humanoid Robot ◽  
Closed Loop ◽  
Vision System ◽  
Simultaneous Localization And Mapping ◽  
Indoor Environments ◽  
Clustering Method ◽  
The Real ◽  
Localization And Mapping

We present a SLAM with closed-loop controller method for navigation of NAO humanoid robot from Aldebaran. The method is based on the integration of laser and vision system. The camera is used to recognize the landmarks whereas the laser provides the information for simultaneous localization and mapping (SLAM ). K-means clustering method is implemented to extract data from different objects. In addition, the robot avoids the obstacles by the avoidance function. The closed-loop controller reduces the error between the real position and estimated position. Finally, simulation and experiments show that the proposed method is efficient and reliable for navigation in indoor environments.

scholarly journals A New Visual Inertial Simultaneous Localization and Mapping (SLAM) Algorithm Based on Point and Line Features

Drones ◽  
2022 ◽  
Vol 6 (1) ◽  
pp. 23
Author(s):  
Tong Zhang ◽  
Chunjiang Liu ◽  
Jiaqi Li ◽  
Minghui Pang ◽  
Mingang Wang
Keyword(s):  
Feature Extraction ◽  
Real Time ◽  
Simultaneous Localization And Mapping ◽  
Line Feature ◽  
Speeded Up Robust Features ◽  
Localization And Mapping ◽  
Line Features ◽  
Point Line ◽  
Point Feature ◽  
Weak Texture

In view of traditional point-line feature visual inertial simultaneous localization and mapping (SLAM) system, which has weak performance in accuracy so that it cannot be processed in real time under the condition of weak indoor texture and light and shade change, this paper proposes an inertial SLAM method based on point-line vision for indoor weak texture and illumination. Firstly, based on Bilateral Filtering, we apply the Speeded Up Robust Features (SURF) point feature extraction and Fast Nearest neighbor (FLANN) algorithms to improve the robustness of point feature extraction result. Secondly, we establish a minimum density threshold and length suppression parameter selection strategy of line feature, and take the geometric constraint line feature matching into consideration to improve the efficiency of processing line feature. And the parameters and biases of visual inertia are initialized based on maximum posterior estimation method. Finally, the simulation experiments are compared with the traditional tightly-coupled monocular visual–inertial odometry using point and line features (PL-VIO) algorithm. The simulation results demonstrate that the proposed an inertial SLAM method based on point-line vision for indoor weak texture and illumination can be effectively operated in real time, and its positioning accuracy is 22% higher on average and 40% higher in the scenario that illumination changes and blurred image.

A Virtual Range Finder based on Monocular Vision System in Simultaneous Localization and Mapping

2008 ◽  
Vol 41 (2) ◽  
pp. 2336-2341
Author(s):  
X.Z. Zhang ◽  
A.B. Rad ◽  
Y.K. Wong
Keyword(s):  
Vision System ◽  
Simultaneous Localization And Mapping ◽  
Monocular Vision ◽  
Range Finder ◽  
Localization And Mapping

scholarly journals Three-Dimensional Reconstruction of Welding Pool Surface by Binocular Vision

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Zunan Gu ◽  
Ji Chen ◽  
Chuansong Wu
Keyword(s):  
Binocular Vision ◽  
Image Matching ◽  
Vision System ◽  
Gas Metal Arc Welding ◽  
Three Dimensional ◽  
Welding Pool ◽  
Speeded Up Robust Features ◽  
Pool Surface ◽  
Metal Arc Welding ◽  
Binocular Vision System

AbstractCurrent research of binocular vision systems mainly need to resolve the camera’s intrinsic parameters before the reconstruction of three-dimensional (3D) objects. The classical Zhang’ calibration is hardly to calculate all errors caused by perspective distortion and lens distortion. Also, the image-matching algorithm of the binocular vision system still needs to be improved to accelerate the reconstruction speed of welding pool surfaces. In this paper, a preset coordinate system was utilized for camera calibration instead of Zhang’ calibration. The binocular vision system was modified to capture images of welding pool surfaces by suppressing the strong arc interference during gas metal arc welding. Combining and improving the algorithms of speeded up robust features, binary robust invariant scalable keypoints, and KAZE, the feature information of points (i.e., RGB values, pixel coordinates) was extracted as the feature vector of the welding pool surface. Based on the characteristics of the welding images, a mismatch-elimination algorithm was developed to increase the accuracy of image-matching algorithms. The world coordinates of matching feature points were calculated to reconstruct the 3D shape of the welding pool surface. The effectiveness and accuracy of the reconstruction of welding pool surfaces were verified by experimental results. This research proposes the development of binocular vision algorithms that can reconstruct the surface of welding pools accurately to realize intelligent welding control systems in the future.

Sign in / Sign up

Export Citation Format

Share Document