Improving SURF Image Matching Using Supervised Learning

Sergieh, Hatem Mousselly; Egyed-Zsigmond, Elöd; Döller, Mario; Coquil, David; Pinon, Jean-Marie; Kosch, Harald

doi:10.1109/sitis.2012.42

Cited by 14 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, , x y σ is obtained. Firstly, non-maximum suppression is performed in the stereo neighborhood of the extremum point 3 3 3 × × [6][7]. Only the extreme values which are larger or smaller than the 26 neighborhood values of the adjacent upper and lower scales and this scale can be used as candidate feature points.…”

Section: A Feature Point Extraction Of Surf Algorithmmentioning

confidence: 99%

The Research of SURF Image Matching Method Based on Region and Feature Information

Chen

Wang²,

Jiang

et al. 2017

Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017)

View full text Add to dashboard Cite

Abstract-According to the SURF feature matching dense matching interpolation algorithm to realize the problems in the complex dynamic background image. The dynamic camera captured the same environment as the object. SURF image is proposed based on the combination of region and the feature information matching method. Firstly, image gray-scale normalization. There may be a reduction the brightness of light due to the translational response point of view. And then add several constraints in the process of extracting SURF feature points. Not only can speed up the matching process, but also can reduce the false match rate. Finally, in order to detect the feature points as the seed point for regional growth, the seed region division of the region by using graph matching. The test show that the algorithm can obtain dense disparity images of good. After the camera shooting of different sizes of image feature matching. Experiments show that, Compared with the SIFT algorithm and the SURF algorithm, the algorithm reduces the number of feature points and matching points, and improves the matching accuracy and the matching accuracy.

show abstract

Section: A Feature Point Extraction Of Surf Algorithmmentioning

confidence: 99%

The Research of SURF Image Matching Method Based on Region and Feature Information

Chen

Wang²,

Jiang

et al. 2017

Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017)

View full text Add to dashboard Cite

show abstract

“…Additionally, these features are rapidly computed, extracted, and compared. In several cases, SURF features were used to solve classification problems for facial expression [51], objects and their localization [52], automatic image annotation [53], and image-matching problems using supervised learning [54].…”

Section: A Speeded-up Robust Features (Surf)mentioning

confidence: 99%

Multi-Sensor Image Fusion for Target Recognition in the Environment of Network Decision Support Systems

Pothitos¹

2015

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instruction, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington This thesis proposed a concept of distributed management of littoral operations at the tactical level, in which timeliness of information and reduced decision cycles are of critical importance. The use of mesh tactical networks augmented by sensor management, operational databases, and an appropriate level of automation of target recognition can turn the obstacles of land masses in littoral environments into a tactical advantage. Ultimately, this thesis concept aimed to enhance situational awareness by enabling the timely exploitation and dissemination of imagery data from small satellites and unmanned systems at the tactical level.Analyses of simulation and field experimentation results that focused on mobile ad-hoc networks (MANETs)-which connected dissimilar imaging sensors and enabled fusion of captured imagessupported this concept. Mesh tactical radios provided an adequate range and quality of service (QoS) to enable networking of kinetic and non-kinetic assets equipped with imaging or data relaying capabilities and to support dissemination of imagery data. Additionally, multi-spectral image fusion of thermal and visual images for target recognition yielded the best classification performance after the use of speeded-up robust features (SURF) and artificial neural networks (ANNs). SUBJECT TERMS MULTI-SENSOR IMAGE FUSION FOR TARGET RECOGNITION IN THE ENVIRONMENT OF NETWORK DECISION SUPPORT SYSTEMSMichail Pothitos Lieutenant Commander, Hellenic Navy B.S., Hellenic Naval Academy, 1999Submitted in partial fulfillment of the requirements for the degrees of MASTER OF SCIENCE IN COMBAT SYSTEMS TECHNOLOGYand MASTER OF SCIENCE IN SYSTEMS TECHNOLOGY (COMMAND, CONTROL & COMMUNICATIONS)from the NAVAL POSTGRADUATE SCHOOL December 2015Approved

show abstract

“…By using the integral images for the image convolution, SURF Journal of Electrical and Computer Engineering only requires a small number of histograms to quantize the gradient orientations [17]. Sergieh et al in [18] studied the way to reduce the number of required features by SURF, while preserving the high correct matching performance. Zhang and Hu in [3] invented the Fast-Hessian detectors for SURF from accelerated segment test (FAST) corner detector.…”

Section: Related Workmentioning

confidence: 99%

Maximum Entropy Threshold Segmentation for Target Matching Using Speeded-Up Robust Features

Zhou

Xia

Tian

et al. 2014

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

This paper proposes a 2-dimensional (2D) maximum entropy threshold segmentation (2DMETS) based speeded-up robust features (SURF) approach for image target matching. First of all, based on the gray level of each pixel and the average gray level of its neighboring pixels, we construct a 2D gray histogram. Second, by the target and background segmentation, we localize the feature points at the interest points which have the local extremum of box filter responses. Third, from the 2D Haar wavelet responses, we generate the 64-dimensional (64D) feature point descriptor vectors. Finally, we perform the target matching according to the comparisons of the 64D feature point descriptor vectors. Experimental results show that our proposed approach can effectively enhance the target matching performance, as well as preserving the real-time capacity.

show abstract

Improving SURF Image Matching Using Supervised Learning

Cited by 14 publications

References 15 publications

The Research of SURF Image Matching Method Based on Region and Feature Information

The Research of SURF Image Matching Method Based on Region and Feature Information

Multi-Sensor Image Fusion for Target Recognition in the Environment of Network Decision Support Systems

Maximum Entropy Threshold Segmentation for Target Matching Using Speeded-Up Robust Features

Contact Info

Product

Resources

About