scholarly journals Image Feature Point Selection Method Using Nearest Neighbor Distance Ratio Matching

2012 ◽  
Vol 49 (12) ◽  
pp. 124-130
Author(s):  
Jun-Woo Lee ◽  
Jea-Hyup Jeong ◽  
Jong-Wook Kang ◽  
Sang-Il Na ◽  
Dong-Seok Jeong
Keyword(s):  
Nearest Neighbor ◽  
Selection Method ◽  
Feature Point ◽  
Image Feature ◽  
Neighbor Distance ◽  
Point Selection ◽  
Distance Ratio ◽  
Nearest Neighbor Distance ◽  
Ratio Matching

scholarly journals Anomaly Detection Based on Local Nearest Neighbor Distance Descriptor in Crowded Scenes

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Xing Hu ◽  
Shiqiang Hu ◽  
Xiaoyu Zhang ◽  
Huanlong Zhang ◽  
Lingkun Luo
Keyword(s):  
Anomaly Detection ◽  
Nearest Neighbor ◽  
Computation Time ◽  
Compact Representation ◽  
Feature Descriptor ◽  
Neighbor Distance ◽  
Low Level ◽  
Feature Descriptors ◽  
Nearest Neighbor Distance ◽  
Crowded Scenes

We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous interaction among multiple events, while most existing feature descriptors only contain the information of single event. Second, LNND descriptor is a compact representation and its dimensionality is typically much lower than the low-level feature descriptor. Therefore, not only the computation time and storage requirement can be accordingly saved by using LNND descriptor for the anomaly detection method with offline training fashion, but also the negative aspects caused by using high-dimensional feature descriptor can be avoided. We validate the effectiveness of LNND descriptor by conducting extensive experiments on different benchmark datasets. Experimental results show the promising performance of LNND-based method against the state-of-the-art methods. It is worthwhile to notice that the LNND-based approach requires less intermediate processing steps without any subsequent processing such as smoothing but achieves comparable event better performance.

The spatial pattern of a Juniperus communis var. depressa population on a continental dune in subarctic Québec, Canada

1999 ◽  
Vol 29 (4) ◽  
pp. 446-450 ◽  
Author(s):  
Gilles Houle ◽  
Mario Duchesne
Keyword(s):  
Sex Ratio ◽  
Nearest Neighbor ◽  
Dispersion Pattern ◽  
Neighbor Distance ◽  
Juniperus Communis ◽  
Biased Sex Ratio ◽  
Males And Females ◽  
Nearest Neighbor Distance ◽  
Population Dispersion ◽  
Crown Size

We performed a nearest-neighbor analysis to determine the population dispersion pattern and the association between males and females in a Juniperus communis L. var. depressa Pursh population occupying a continental dune in subarctic Quebec, Canada. The overall dispersion pattern was contagious, and males (or females) were proportionately as likely to have a male as they were to have a female nearest neighbor. Crown size was positively related to nearest-neighbor distance for the male-male comparison only, suggesting a somewhat stronger intrasex competition between males. Nearest-neighbor distance increased with crown size (significantly related to age) suggesting a change in the intensity of aggregation with age possibly related to self-thinning. Higher mortality as a result of stronger male-male competition could explain the female-biased sex ratio and the absence of spatial segregation between sexes. The overall contagious dispersion pattern in the population may be related to the fact that most seed cones fall directly underneath the mother plant. Birds can eat the cones of J. communis and thus disperse seeds. However, these seeds are deposited in clumps, a process that may also explain contagion within the population.

scholarly journals Photoluminescence Enhancement and Change in the Second Nearest Neighbor Distance of Sm‐Doped TiO 2 Thin Films

2019 ◽  
Vol 256 (6) ◽  
pp. 1800522 ◽  
Author(s):  
Mariko Murayama ◽  
Kensaku Yoda ◽  
Keita Shiraishi ◽  
Iain F. Crowe ◽  
Shuji Komuro ◽  
...  
Keyword(s):  
Thin Films ◽  
Nearest Neighbor ◽  
Neighbor Distance ◽  
Photoluminescence Enhancement ◽  
Nearest Neighbor Distance

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.

Sign in / Sign up

Export Citation Format

Share Document