scholarly journals Feature points selection with flocks of features constraint for visual simultaneous localization and mapping

2016 ◽  
Vol 14 (1) ◽  
pp. 172988141666678
Author(s):  
Hong Liu ◽  
Zhi Wang ◽  
Pengjin Chen
Keyword(s):  
Mobile Robots ◽  
Simultaneous Localization And Mapping ◽  
Selection Method ◽  
Feature Point ◽  
Feature Points ◽  
Point Selection ◽  
Localization Accuracy ◽  
Surrounding Environment ◽  
Localization And Mapping ◽  
Crucial Problem

Simultaneous localization and mapping is a crucial problem for mobile robots, which estimates the surrounding environment (the map) and, at the same time, computes the robot location in it. Most researchers working on simultaneous localization and mapping focus on localization accuracy. In visual simultaneous localization and mapping , localization is to calculate the robot’s position relative to the landmarks, which corresponds to the feature points in images. Therefore, feature points are of importance to localization accuracy and should be selected carefully. This article proposes a feature point selection method to improve the localization accuracy. First, theoretical and numerical analyses are conducted to demonstrate the importance of distribution of feature points. Then, an algorithm using flocks of features is proposed to select feature points. Experimental results show that the proposed flocks of features selector implemented in visual simultaneous localization and mapping enhances the accuracy of both localization and mapping, verifying the necessity of feature point selection.

scholarly journals A Grid Feature-Point Selection Method for Large-Scale Street View Image Retrieval Based on Deep Local Features

2020 ◽  
Vol 12 (23) ◽  
pp. 3978
Author(s):  
Tianyou Chu ◽  
Yumin Chen ◽  
Liheng Huang ◽  
Zhiqiang Xu ◽  
Huangyuan Tan
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Local Features ◽  
Selection Method ◽  
Image Features ◽  
Feature Point ◽  
Feature Points ◽  
Point Selection ◽  
Retrieval Task ◽  
Street View

Street view image retrieval aims to estimate the image locations by querying the nearest neighbor images with the same scene from a large-scale reference dataset. Query images usually have no location information and are represented by features to search for similar results. The deep local features (DELF) method shows great performance in the landmark retrieval task, but the method extracts many features so that the feature file is too large to load into memory when training the features index. The memory size is limited, and removing the part of features simply causes a great retrieval precision loss. Therefore, this paper proposes a grid feature-point selection method (GFS) to reduce the number of feature points in each image and minimize the precision loss. Convolutional Neural Networks (CNNs) are constructed to extract dense features, and an attention module is embedded into the network to score features. GFS divides the image into a grid and selects features with local region high scores. Product quantization and an inverted index are used to index the image features to improve retrieval efficiency. The retrieval performance of the method is tested on a large-scale Hong Kong street view dataset, and the results show that the GFS reduces feature points by 32.27–77.09% compared with the raw feature. In addition, GFS has a 5.27–23.59% higher precision than other methods.

Introduction to Simultaneous Localization and Mapping

2019 ◽  
Vol 31 (3) ◽  
pp. 367-374 ◽  
Author(s):  
Takashi Tsubouchi ◽  
Keyword(s):  
Mobile Robots ◽  
Simultaneous Localization And Mapping ◽  
Position Estimation ◽  
Computer Implementation ◽  
Major Topic ◽  
The Core ◽  
Surrounding Environment ◽  
Localization And Mapping ◽  
Actual Environment ◽  
World Information

Simultaneous localization and mapping (SLAM) forms the core of the technology that supports mobile robots. With SLAM, when a robot is moving in an actual environment, real world information is imported to a computer on the robot via a sensor, and robot’s physical location and a map of its surrounding environment of the robot are created. SLAM is a major topic in mobile robot research. Although the information, supported by a mathematical description, is derived from a space in reality, it is formulated based on a probability theory when being handled. Therefore, this concept contributes not only to the research and development concerning mobile robots, but also to the training of mathematics and computer implementation, aimed mainly at position estimation and map creation for the mobile robots. This article focuses on the SLAM technology, including a brief overview of its history, insights from the author, and, finally, introduction of a specific example that the author was involved.

TSLAM: Tethered simultaneous localization and mapping for mobile robots

2017 ◽  
Vol 36 (12) ◽  
pp. 1363-1386 ◽  
Author(s):  
Patrick McGarey ◽  
Kirk MacTavish ◽  
François Pomerleau ◽  
Timothy D Barfoot
Keyword(s):  
Mobile Robots ◽  
Particle Filter ◽  
Low Cost ◽  
Simultaneous Localization And Mapping ◽  
Ground Truth ◽  
Anchor Point ◽  
Outlier Rejection ◽  
Cluttered Environments ◽  
Localization And Mapping ◽  
Anchor Points

Tethered mobile robots are useful for exploration in steep, rugged, and dangerous terrain. A tether can provide a robot with robust communications, power, and mechanical support, but also constrains motion. In cluttered environments, the tether will wrap around a number of intermediate ‘anchor points’, complicating navigation. We show that by measuring the length of tether deployed and the bearing to the most recent anchor point, we can formulate a tethered simultaneous localization and mapping (TSLAM) problem that allows us to estimate the pose of the robot and the positions of the anchor points, using only low-cost, nonvisual sensors. This information is used by the robot to safely return along an outgoing trajectory while avoiding tether entanglement. We are motivated by TSLAM as a building block to aid conventional, camera, and laser-based approaches to simultaneous localization and mapping (SLAM), which tend to fail in dark and or dusty environments. Unlike conventional range-bearing SLAM, the TSLAM problem must account for the fact that the tether-length measurements are a function of the robot’s pose and all the intermediate anchor-point positions. While this fact has implications on the sparsity that can be exploited in our method, we show that a solution to the TSLAM problem can still be found and formulate two approaches: (i) an online particle filter based on FastSLAM and (ii) an efficient, offline batch solution. We demonstrate that either method outperforms odometry alone, both in simulation and in experiments using our TReX (Tethered Robotic eXplorer) mobile robot operating in flat-indoor and steep-outdoor environments. For the indoor experiment, we compare each method using the same dataset with ground truth, showing that batch TSLAM outperforms particle-filter TSLAM in localization and mapping accuracy, owing to superior anchor-point detection, data association, and outlier rejection.

scholarly journals A Multiscale Constraints Method Localization of 3D Facial Feature Points

2015 ◽  
Vol 2015 ◽  
pp. 1-6
Author(s):  
Hong-an Li ◽  
Yongxin Zhang ◽  
Zhanli Li ◽  
Huilin Li
Keyword(s):  
Facial Feature ◽  
Feature Point ◽  
Distribution Model ◽  
Feature Points ◽  
Widespread Application ◽  
Point Distribution ◽  
Localization Accuracy ◽  
Localization Method ◽  
Relative Angle ◽  
Point Distribution Model

It is an important task to locate facial feature points due to the widespread application of 3D human face models in medical fields. In this paper, we propose a 3D facial feature point localization method that combines the relative angle histograms with multiscale constraints. Firstly, the relative angle histogram of each vertex in a 3D point distribution model is calculated; then the cluster set of the facial feature points is determined using the cluster algorithm. Finally, the feature points are located precisely according to multiscale integral features. The experimental results show that the feature point localization accuracy of this algorithm is better than that of the localization method using the relative angle histograms.

Sign in / Sign up

Export Citation Format

Share Document