Person re-identification by fuzzy space color histogram

Xiang, Zong Jie; Chen, Qiren; Liu, Yuncai

doi:10.1007/s11042-012-1286-7

Cited by 14 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, by definition, a pixel can change more than one stack of histograms depending on its color. The main idea of the research [12] is to use the five properties of x, B, C, R and y in the histogram. So that a 5-dimensional histogram is created based on the five properties and then, for each pixel, according to the position and color, the degree of amplification is assigned to one of these stacks.…”

Section: Previous Workmentioning

confidence: 99%

Improving Person Re-Identification Rate in Security Cameras by Orthogonal Moments and a Distance-based Criterion

Dadkhah

Nasri

2020

mjee

View full text Add to dashboard Cite

Surveillance and security cameras help security forces in public places such as airports, railway stations, universities and office buildings to perform high-level surveillance tasks such as detecting suspicious activity or anticipating undesirable events. Re-Identification (Re-ID) is defined as the process of communicating between images of the person in different cameras in a surveillance environment. Changing the field of view of any camera presents challenges such as changing body posture, changing brightness, noise and blockage. This article focuses on extracting the most distinctive features to overcome these challenges. The features of Hu moment, Zernike moment in 9 th order and Legendre moment in 9 th order for each image are extracted and merged into a single feature vector to form a single feature vector for each image. Principal Component Analysis (PCA) was used to reduce the vector dimensionality and finally the Mahalanobis distance criterion was used for identification. The proposed method in the VIPeR database has achieved a re-ID rate of 96.5. Although the presented method is simple, the outcome has been superior compared to many of the state-of-the-art methods.

show abstract

Section: Previous Workmentioning

confidence: 99%

Improving Person Re-Identification Rate in Security Cameras by Orthogonal Moments and a Distance-based Criterion

Dadkhah

Nasri

2020

mjee

View full text Add to dashboard Cite

show abstract

“…Commonly, similarity measure methods consist of the Minkowsky distance, Chebyshev distance, quadratic form distance, Euclidean distance and correlation coefficient, and so on. 31 In this paper, the Pearson correlation coefficient 32 and Euclidean distance, 14,15,19 commonly used in image retrieval systems, were tested for similarity measure. In n-dimensional space, assuming that X ¼ (x 1 , x 2 , .…”

Section: Similarity Measurementioning

confidence: 99%

Image retrieval of wool fabric. Part I: Based on low-level texture features

Zhang

Xiang

Wang

et al. 2019

Textile Research Journal

View full text Add to dashboard Cite

With huge and ever-growing products in the factory, image retrieval can help the worker retrieve the same, or similar, existing products rapidly and accurately to guide production. In this paper, an effective method based on Fourier transform and local binary pattern is proposed to improve the retrieval efficiency of wool fabric. After capturing the fabric image, histogram equalization was implemented on the value of the Hue, Saturation, Value (HSV) mode to enhance the contrast. Subsequently, Fourier transform together with local binary pattern operator were performed to obtain the frequency spectrum and the local binary pattern, respectively. Each frequency spectrum was divided into 22 rings with the same width, and the standard deviation of the frequencies in each ring was calculated as a Fourier feature. Distinct output values of each local binary pattern were counted and normalized as local binary pattern features. Finally, Euclidean distance was adopted to measure the similarity based on the Fourier feature and local binary pattern feature. Twenty thousand wool fabric images were captured to demonstrate the efficacy of the proposed method. Experimental results indicate that the framework is effective and superior for image retrieval of wool fabric, providing referential assistance for the worker in the factory and improving retrieval efficiency.

show abstract

“…In terms of performance, the reason behind RDC high accuracy is that the RDC or also known as PRDC learning metric adopts the second-order Fig. 16 Re-identification rate for STHOG gait descriptor, HSV colour histogram and combination of them [32] Table 6 First rank re-identification rate of learning metrics and Bhattacharyya coefficients for different datasets [61,89] Learning metrics/classifier First rank re-identification rates [60] high level of robustness against illumination and pose variations 3. fuzzy analysis Xiang et al [37], D' Angelo and Dugelay [63] ability to handle severe illumination changes…”

Section: Real-time Re-identificationmentioning

confidence: 99%

“…where std is the standard deviation of the pixels in colour channel I k . Histogram normalisation is another method used in some works [37,58]. Cong et al [101] performed the same algorithm on the data that were grabbed from two locations, but applied different normalisation methods on it.…”

Section: Robustness Against Illumination Variationsmentioning

confidence: 99%

Review of person re‐identification techniques

Saghafi

Hussain

Zaman

et al. 2014

IET Computer Vision

View full text Add to dashboard Cite

Person re-identification across different surveillance cameras with disjoint fields of view has become one of the most interesting and challenging subjects in the area of intelligent video surveillance. Although several methods have been developed and proposed, certain limitations and unresolved issues remain. In all of the existing re-identification approaches, feature vectors are extracted from segmented still images or video frames. Different similarity or dissimilarity measures have been applied to these vectors. Some methods have used simple constant metrics, whereas others have utilised models to obtain optimised metrics. Some have created models based on local colour or texture information, and others have built models based on the gait of people. In general, the main objective of all these approaches is to achieve a higher-accuracy rate and lowercomputational costs. This study summarises several developments in recent literature and discusses the various available methods used in person re-identification. Specifically, their advantages and disadvantages are mentioned and compared.

show abstract

Person re-identification by fuzzy space color histogram

Cited by 14 publications

References 20 publications

Improving Person Re-Identification Rate in Security Cameras by Orthogonal Moments and a Distance-based Criterion

Improving Person Re-Identification Rate in Security Cameras by Orthogonal Moments and a Distance-based Criterion

Image retrieval of wool fabric. Part I: Based on low-level texture features

Review of person re‐identification techniques

Contact Info

Product

Resources

About