High speed robust image registration and localization using optimized algorithm and its performances evaluation

An, Meng; Jiang, Zhiguo; Zhao, Danpei

doi:10.3969/j.issn.1004-4132.2010.03.026

Cited by 13 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to perform secondary matching of Hamming distance from the initial matching feature points, the PROSAC is used. In the PROSAC processing, RANSAC first extracts the samples from all the data [22]. Then, PROSAC divides the samples by descending the quality of the samples and extracts the samples from the data subsets with higher quality to find the optimal estimate solution, thus eliminating the false match.…”

Section: E Prosac Algorithm For Secondary Fine Matchingmentioning

confidence: 99%

A Novel Information Fusion Method for Vision Perception and Location of Intelligent Industrial Robots

Jin

Lin²,

Yang

et al. 2019

ELEKTRON ELEKTROTECH

View full text Add to dashboard Cite

An improved SURF (Speeded-Up Robust Feature） algorithm is proposed to deal with the time-consuming and low precision of positioning of industrial robot. Hessian matrix determinant is used to extract feature points from the target image and a multi-scale spatial pyramid is constructed. The location and scale value of feature points are determined by neighbourhood non-maximum suppression method. The direction of feature points is defined as directional feature descriptors by the binary robust independent elementary feature (BRIEF). The progressive sample consensus (PROSAC) is used to carry out second precise matching and remove mismatching points based on the Hamming distance. Then, an affine transformation model is established to describe the relationship between the template and target images. Centroid coordinates of the target can be obtained based on the affine transformation. Comparative tests were carried out to demonstrate that the proposed method can effectively improve the recognition rate and positioning accuracy of the industrial robots. The average time consuming is less than 0.2 s, the matching accuracy is 96 %, and the positioning error of the robot is less than 1.5 mm. Therefore, the proposed method has practical application importance.

show abstract

Section: E Prosac Algorithm For Secondary Fine Matchingmentioning

confidence: 99%

A Novel Information Fusion Method for Vision Perception and Location of Intelligent Industrial Robots

Jin

Lin²,

Yang

et al. 2019

ELEKTRON ELEKTROTECH

View full text Add to dashboard Cite

show abstract

“…In order to determine the target outer contour, it is necessary to make edge detection and extraction for the segmentation image [8][9]. Image segmentation, shape feature extraction and texture feature extraction are the important link and basis of edge feature extraction in the complex background image.…”

Section: Target Edge Detection and Extraction Algorithmmentioning

confidence: 99%

“…The shape of target can be obtained after the segmentation of target image. In order to determine the target outer contour, it is necessary to make edge detection and extraction for the segmentation image [8][9] Step edges behave that pixel gray values on both sides of discontinuities of the image brightness have significant difference. This difference is the transition from the light background to the dark background or from the dark background to the light background in aspect of vision.…”

Section: Target Edge Detection and Extraction Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Image Processing and Recognition Algorithm for Target Tracking

Lü

Wang

2016

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

Abstract-to improve target tracking performance in dynamic target track system, this paper propose the processing method of positive and negative difference image to extract target information; research target image preprocessing algorithm, the separation and segmentation processing algorithm of target and background, target edge detection and extraction based on the collected images; use Laplace operator, Canny operator. Gauss-Laplace operator to gain target information and improved recognition target image effect, analyze the positive and negative difference image measure to solve the background subtraction interference between two sequence images. Through the actual image processing, The results shows the proposed processing method can clear gain target marginal information and target image particle center, control tracking platform can stably track the target, and give the comparison results.

show abstract

“…The useful information is preserved and the useless information is removed with image preprocessing. At the same time, the degree of recognition is increased, the image data is simplified and the quality of the original image is improved with image enhancement processing (Li, 2015;Li, 2016;Meng and Zhiguo, 2010). Image preprocessing concludes the following operations, such as the digital processing of the analog image, which make the image to be processed by PC software, the geometric transformation, which make image processing easier, normalization, smoothing, restoration, enhancement and so on.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian Detection under Low Illumination Environment

2016

Rev. Téc. Ing. Univ. Zulia

View full text Add to dashboard Cite

The moving target detecting is playing a very important role in machine vision, image understanding and other fields. In this paper, the pedestrian detection under the low illumination environment is studied. In order to make the fuzzy pedestrian in the image clearer, the method of combining Gaussian filtering and histogram equalization is used to process the image, which is the base of detecting and extracted Human characteristics. The pedestrian is detected by the method of HOG feature extraction and SVM. To examine the proposed method of the performance detection, experiments have been conducted on the pedestrian image acquired under the low illumination. The results show that the method has clear effect on target image and has achieved the better pedestrian detection under the low illumination environment.

show abstract

High speed robust image registration and localization using optimized algorithm and its performances evaluation

Cited by 13 publications

References 0 publications

A Novel Information Fusion Method for Vision Perception and Location of Intelligent Industrial Robots

A Novel Information Fusion Method for Vision Perception and Location of Intelligent Industrial Robots

Image Processing and Recognition Algorithm for Target Tracking

Pedestrian Detection under Low Illumination Environment

Contact Info

Product

Resources

About