A method of registration based on skeleton for 2-D shapes

Li, Ce; Luo, Xinying; Du, Shaoyi; Xiao, Lei

doi:10.1109/cisp.2012.6469977

Cited by 3 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since they are heavily influenced by starting point (initial pose) regression techniques are often fooled into local minima and, to compensate, researchers proposed various hierarchical techniques that parametrized depth, changes in resolution, and the number of iterations [7], [11], [12], [16]. Common population based parameters include computational budget, thresholds, and population size.…”

Section: B Challengesmentioning

confidence: 99%

“…Factors affecting input include variations in data production or acquisition [13], distortions [18], blurring [18], occlusion [19], and variations in quantity such as extraneous data or noise [12], [20], missing data [14], outliers [20], or variations in the density or distribution of data [9]. These input related issues will hereinafter be referred to as noise and are addressed through greater levels of data abstraction as will be discussed later.…”

Section: B Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Differential Evolution Applied to Point Matching 2D GIS Data

Khan

Neri

Ahmadi

2015

2015 IEEE Symposium Series on Computational Intelligence

View full text Add to dashboard Cite

The impetus behind data analytics and integration is the need for greater insight and data visibility, but since a growing share of our data is multimedia, there is a parallel need for methods that can align multimedia data. This paper explores georeferencing, which is used to combine spatial datasets and used here to align map images to 2D GIS models. This paper surveys various approaches for building the key components of a georeferencing solution, notes their strengths and weaknesses, and comments on their trajectory to help orient future work. The implementation presented here uses Hough transforms for feature detection, nearest neighbor correspondences with simplistic similarity measures, and a population based optimizer. The comparison among metaheuristics has shown that Differential Evolution (DE) frameworks appear especially suited for this problem. In particular, the controlled randomization of DE parameters appears to display the best performance in terms of execution time and competitive performance in terms of function evaluations even with respect to more complex memetic implementations.

show abstract

Section: B Challengesmentioning

confidence: 99%

Section: B Challengesmentioning

confidence: 99%

Adaptive Differential Evolution Applied to Point Matching 2D GIS Data

Khan

Neri

Ahmadi

2015

2015 IEEE Symposium Series on Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…To speed up the point set matching process, we use the center line to in itialize the init ial value of ICP, and the points on the contour are adopted to iterate again. The center line is the main axis between the upper part contour and the lower part contour by the similar way of the SKICP [14]. The center line is shown in Fig.…”

Section: B Contour Registrationmentioning

confidence: 99%

A New Method of View-Invariant Human Activity Recognition

Su¹,

Wang²

2015

Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science

View full text Add to dashboard Cite

We present a new method to recognize human activity under uncertain view. The activity width image which is extracted from the sequence of silhouette is used to represent the activity features. It converts the spatial and temporal pattern to a grey-level image. View difference causes the deformation of activity width images and degradation of recognition accuracy. To solve this problem, we transform the feature images to the new images in the uniform view based on the activity templates using Iterative closet point (ICP). For reducing the complexity, we choose the center line and the contour of the activity width images to register and the affine transformation is adopted to transform. The similarity matrix is used to measure the difference between the transformed feature image and the templates. We evaluate our method on the CAS IA database and the results show that our method is simple and efficient.

show abstract

Tightly-Coupled GNSS-LiDAR-Inertial State Estimator for Mapping and Autonomous Driving

Gil¹,

Lee²,

Song³

et al. 2023

J. Korea Robot. Soc.

View full text Add to dashboard Cite

The main purpose of this technical report is to describe in detail the implementation of the pure pursuit path tracking algorithm. Given the general success of the algorithm over the past few years, it seems likely that it will be used again in land-based navigation problems. This report also includes a geometric derivation of the method, and presents some insights into the performance of the algorithm as a function of its parameters.

show abstract

A method of registration based on skeleton for 2-D shapes

Cited by 3 publications

References 12 publications

Adaptive Differential Evolution Applied to Point Matching 2D GIS Data

Adaptive Differential Evolution Applied to Point Matching 2D GIS Data

A New Method of View-Invariant Human Activity Recognition

Tightly-Coupled GNSS-LiDAR-Inertial State Estimator for Mapping and Autonomous Driving

Contact Info

Product

Resources

About