Normalized Cross-correlation Function Research Articles

Normalized weighted cross correlation for multi-channel image registration

The normalized cross-correlation (NCC) is widely used for image registration due to its simple geometrical interpretation and being feature-agnostic. Here, after reviewing NCC definitions for images with an arbitrary number of dimensions and channels, we propose a generalization in which each pixel value of each channel can be individually weighted using real non-negative numbers. This generalized normalized weighted cross-correlation (NWCC) and its zero-mean equivalent (ZNWCC) can be used, for example, to prioritize pixels based on signal-to-noise ratio. Like a previously defined NWCC with binary weights, the proposed generalizations enable the registration of uniformly, but not necessarily isotropically, sampled images with irregular boundaries and/or sparse sampling. All NCC definitions discussed here are provided with discrete Fourier transform (DFT) formulations for fast computation. Practical aspects of NCC computational implementation are briefly discussed, and a convenient function to calculate the overlap of uniformly, but not necessarily isotropically, sampled images with irregular boundaries and/or sparse sampling is introduced, together with its DFT formulation. Finally, examples illustrate the benefit of the proposed normalized cross-correlation functions.

Reconstructive interpolation for pulse wave estimation to improve local PWV measurement of carotid artery.

Ultrasonic transit time (TT)-based local pulse wave velocity (PWV) measurement is defined as the distance between two beam positions on a segment of common carotid artery (CCA) divided by the TT in the pulse wave propagation. However, the arterial wall motions (AWMs) estimated from ultrasonic radio frequency (RF) signals with a limited number of frames using the motion tracking are typically discrete. In this work, we develop a method involving motion tracking combined with reconstructive interpolation (MTRI) to reduce the quantification errors in the estimated PWs, and thereby improve the accuracy of the TT-based local PWV measurement for CCA. For each beam position, normalized cross-correlation functions (NCCFs) between the reference (the first frame) and comparison (the remaining frames) RF signals are calculated. Thereafter, the reconstructive interpolation is performed in the neighborhood of the NCCFs' peak to identify the interpolation-deduced peak locations, which are more exact than the original ones. According to which, the improved AWMs are obtained to calculate their TT along a segment of the CCA. Finally, the local PWV is measured by applying a linear regression fit to the time-distance result. In ultrasound simulations based on the pulse wave propagation models of young, middle-aged, and elderly groups, the MTRI method with different numbers of interpolated samples was used to estimate AWMs and local PWVs. Normalized root mean squared errors (NRMSEs) between the estimated and preset values of the AWMs and local PWVs were calculated and compared with ones without interpolation. The means of the NRMSEs for the AWMs and local PWVs based on the MTRI method with one interpolated sample decrease from 1.14% to 0.60% and 7.48% to 4.61%, respectively. Moreover, Bland-Altman analysis and coefficient of variation were used to validate the performance of the MTRI method based on the measured local PWVs of 30 healthy subjects. In conclusion, the reconstructive interpolation for the pulse wave estimation improves the accuracy and repeatability of the carotid local PWV measurement.

Light-field spectral decomposition with a spatial–angular consistency prior for disparity estimation

Modeling the spatial–angular relationship is the theoretical basis for accurate disparity estimation from the light-field data. In this paper, the spatial–angular coupling relationship of light-field is established under the assumption of constant radiance along rays, and the spatial–angular consistency model of light-field is established under the assumption of Lambertian radiance. Based on the spatial–angular consistency prior of light-field, the light-field spectral decomposition based on disparity layers can be modeled as the ill-posed inverse problem. Based on the spectral decomposition, the disparity estimation is transformed into the process of searching for the spatial domain support set in the scene disparity hierarchy. The normalized cross-correlation function is utilized to estimate the disparity based on spectral decomposition under the spatial–angular consistency of the light-field. The performance on both simulated and real captured data show that the proposed algorithm is effective at high-precision and dense disparity estimation.

The Study of the Bistatic Cross-Correlation Function of Two Signals Separated in Frequency Reflected by the Water Surface

The purpose of this study is to analyze the applicability conditions for the significant wave height (SWH) measurement approach based on measuring the cross-correlation function of two signals with similar frequencies reflected by the sea surface in the bistatic problem statement (the transmitting antenna and the receiving antenna are separated in space). When implementing this approach, the modulus of the normalized cross-correlation function for several pairs of signals with different frequency bases will be measured in the experiment. The advantage of this approach over the traditional method for radar altimetry, based on the analysis of the shape of the reflected pulse, is the high accuracy in measuring the SWH for weak waves. In the bistatic formulation of the problem, an important advantage of the approach under study is the possibility of obtaining analytical formulas for solving the direct problem. This paper presents the derivation of a formula for the modulus of the normalized cross-correlation function of reflected signals, which expresses an explicit relationship with the parameters of sea waves and the measurement geometry in the bistatic formulation of the problem. This paper considers the influence on the modulus of the normalized cross-correlation function of the antenna patterns of the transmitting and receiving antennas, the distances to the sea surface, the wave slope variances, the SWH and the frequency base of the transmitted signals. The optimal variants of the measurement scheme are discussed. The results and conclusions obtained can be easily expanded to underwater acoustic sounding.

Low back pain influences trunk-lower limb joint coordination and balance control during standing in persons with lower limb loss

BackgroundBalance is sustained through multi-joint coordination in response to postural perturbations. Low back pain alters postural responses; however, it is unknown how coordination between the trunk and lower extremities affects center of mass control during standing balance among persons with limb loss, particularly those with back pain. MethodsForty participants with unilateral lower limb loss (23 with back pain) stood with eyes open and closed on a firm surface, while wearing IMUs on the sternum, pelvis, and bilaterally on the thigh, shank, and foot. A state-space model with Kalman filter calculated sagittal trunk, hip, knee, and ankle joint angles. Fuzzy entropy quantified center of mass variability of sagittal angular velocity at the sacrum. Normalized cross-correlation functions identified coordination patterns (trunk-hip, trunk-knee, trunk-ankle). Multiple linear regression predicted fuzzy entropy from cross-correlation values for each pattern, with body mass and amputation level as covariates. FindingsWith eyes open, trunk-lower limb joint coordination on either limb did not predict fuzzy entropy. With eyes closed, positive trunk-hip coordination on the intact limb predicted fuzzy entropy in the pain group (p = 0.02), but not the no pain group. On the prosthetic side, inverse trunk-hip coordination patterns predicted fuzzy entropy in pain group (p = 0.03) only. InterpretationPersons with limb loss and back pain demonstrated opposing coordination strategies between the lower limbs and trunk when vision was removed, perhaps identifying a mechanism for pain recurrence. Vision is the dominant source of balance stabilization in this population, which may increase fall risk when visual feedback is compromised.

Технологии вычисления коэффициента корреляции между полезным сигналом и помехой по оценке их релейной взаимной корреляционной функции

Показано, что часто при формировании зашумленных сигналов нарушается условие отсутствия корреляции между полезным сигналом и помехой. Поэтому при корреляционном анализе этих сигналов возникают определенные погрешности, становящиеся причиной неадекватности полученных результатов. Кроме того, существующие технологии корреляционного анализа не позволяют использовать помехи как носители ценной информации. Поэтому для полного использования колоссального информационного потенциала зашумленных сигналов необходимо создать новые технологии, которые как при выполнении известных классических условий, так и при их невыполнении исключили бы потерю ценной информации. Разработаны алгоритмы определения оценки коэффициента корреляции между полезным сигналом и помехой, которые невозможно измерить непосредственно или выделить из зашумленного сигнала. С этой целью использована нормированная взаимная корреляционная функция между полезным сигналом и помехой. Разработан алгоритм вычисления оценок нормированной взаимной корреляционной функции между полезным сигналом и помехой по оценкам релейной корреляционной функции на зашумление сигнала. Показано, что значение этой оценки, вычисленное при нулевом временном сдвиге, представляет собой оценку коэффициента корре-ляции между полезным сигналом и помехой. Проведена технология вычислительных экспериментов, сравнительный анализ, подтверждена достоверность предложенных алгоритмов и технологий. Показано, что при нормальном техническом состоянии объекта оценки релейной корреляционной взаимной функции и коэффициента корреляции между полезным сигналом и помехой будут близки нулю. При зарождении различных дефектов, предшествующих неполадкам на объекте, эти оценки в зависимости от степени повреждения будут изменяться. Поэтому в системах мониторинга и контроля именно оценки взаимной корре-ляционной функции и коэффициента корреляции между полезным сигналом и помехой целесообразно использовать как информативные признаки для сигнализации и контроля начала изменений технического состояния объектов и динамики развития их неисправностей. Благодаря использованию этих новых эффективных информативных признаков можно повысить степень достоверности и надежности функционирования современных информационных систем.

Efficient Mobility Prediction in MANET using Linear Predictive Approach

Mobility has recently sparked a lot of interest, as users' demand for more reliable connections and higher service quality has risen. In mobile networks, effective estimation of consumer mobility allows for efficient resource and handover management, preventing undesirable loss of perceived efficiency. As a result, predicting mobility in wireless networks is important, and several studies have been conducted on the subject. The importance of mobility prediction is discussed in this paper, as well as its inherent attributes in terms of predictability of the node movement, outputs of the prediction, and evaluation metrics. Furthermore, the learning perspective of mobility prediction solutions has been explored.This work outlines a similarity estimation based approach to mobility prediction. To obtain a time series of past measurements, each node tracks the Signal to Noise Ratio (SNR) of its wireless connections with the other nodes. When a prediction is requested, the node uses the collected training data to calculate the normalized cross-correlation function of the recent past in order to identify situations similar to the current one in the background of its relations. The matched records are then utilized as the prediction's basis.

Detection of Concentration Inhomogeneity of Carbon Nanotubes in Polyethylene by Spectral-Correlation Method

It is shown that the concentration of single-walled carbon nanotubes in polyethylene can be estimated using a spectral-correlation method, which consists of statistical processing of random intensity distributions (speckles) formed by scattering on optical inhomogeneity of the material. The optimal conditions for performing measurements are established, possible causes of errors are determined, and the statistical errors of measurements are estimated. Based on experimental data, expressions are obtained for approximating the dependence of the nanotube concentration on the half-width of the normalized cross-correlation function of the intensity distributions of backscattered radiation at different wavelengths. The possibility of using extrapolation of calibration dependencies for two different physical models (linear and exponential) is considered and the expediency of using a linear model at nanotube concentration above 2% is shown. The concentration of nanotubes in one of the elements of the high-voltage coupling design is evaluated and the possibility of detecting inhomogeneity of the filler concentration in the material is demonstrated.

Sub-pixel displacement measurement based on the combination of a gray wolf optimizer and gradient algorithm.

The digital speckle correlation method (DSCM) aims to measure the displacement of the interesting points by matching the subset around the same point between the undeformed image and the deformed image. It is an effective and powerful optical metrology method for deformation measurement. Considering that the gray wolf optimizer (GWO) is one of the most popular metaheuristic algorithms to calculate the unknown search spaces in the field of optical engineering, a sub-pixel displacement measurement technique based on the GWO and gradient algorithm is proposed. First, the zero-mean normalized cross correlation function is applied to analyze the correlation between the reference image and deformed image subsets. Second, by exploiting the global searching ability of the GWO algorithm, the initial integer pixel value is obtained and further viewed as the initialization displacement. Finally, the final sub-pixel displacement is generated by using a Barron gradient algorithm. Compared with the state-of-the-art methods on synthetic speckle images, the proposed method can effectively measure the displacement and deformation of rigid bodies. Furthermore, the experiments on the real images demonstrate the effectiveness of our presented framework.

Bilateral Gait Asymmetry in Patients with Hallux Valgus using Normalized Cross-Correlation Function

The characterization of changed gait patterns caused by hallux valgus (HV) has been proposed in several studies; however, most of these studies have primarily focused on univariate kinematic variables rather than on the coupled and coordinated movement of multiple body segments during walking. Human gait is a spatiotemporally complex and coordinated movement; hence, simple univariate measures cannot assess the coupled relationship between multiple joint motions. The purpose of this study was to examine how HV would change the gait dynamics of the lower extremity and whether the type of shoes worn by the subjects would affect gait behavior. In particular, the cross-correlation function (CCF) was used to determine the coupled characteristics between individual joint variables during gait. The CCF quantified the bilateral asymmetry of the lower extremities and the degree of coupling of multiple body segments. From the perspective of bilateral symmetry, the joint coupling relationship of the lower limbs had a significant deviation in the ankle and knee joint coupling (AK) instead of in the hip and knee joint coupling (HK). For low heels, the types of shoes worn by patients with HV are commonly found to have the lowest maximum CCF values for HK and AK $$(p < .05)$$ . The ankle joints in patients with HV had the main effect, particularly with higher heels. The results of this study show that the gait performance can be characterized using the CCF and may help clinicians in examining the bilateral gait asymmetry of patients with HV and other people with gait disturbances.

Wet gas metering using a vortex cross-correlation meter based on fluctuating pressure measurement

A solution for wet gas metering was developed with a vortex meter by using pressure sensors and correlation technology. For the fluctuating pressure measurement, the micro pressure sensors, especially the probe-transducer systems, were designed to acquire reliable vortex signals. For the experiments, an annular mist flow loop with a film metering system was established, and the tests were conducted on various pressure, gas velocity and liquid flowrate conditions. Then, the dimensionless convection velocity, named convection coefficient, and the peak value of the normalized cross-correlation function, named correlation coefficient were calculated. A piecewise function was developed for the convection coefficient with modified Weber number where the segmentation was determined by the correlation coefficient. Finally, the wet gas measurement model was developed and realized by iterative algorithm. Under the present conditions, the ±5% error bands contain 91% of the relative errors for gas flowrate prediction, the mean absolute percentage error is 2.54%, and the uncertainty of gas flowrate prediction is 2.85%. The primary advantage of the proposed method is that the convection coefficient is almost independent of liquid fraction, no extra systems are necessary for watercut measurement, hence providing a cost-effective solution for wet gas metering.

Improving Ultrasound Lateral Strain Estimation Accuracy using Log Compression of Regularized Correlation Function.

Normalized cross-correlation (NCC) function used in ultrasound strain imaging can get corrupted due to signal decorrelation inducing large displacement errors. Bayesian regularization has been applied in an iterative manner to regularize the NCC function and to reduce estimation variance and peak-hopping errors. However, incorrect choice of the number of iterations can lead to over-regularization errors. In this paper, we propose the use of log compression of regularized NCC function to improve subsample estimation. Performance of parabolic interpolation before and after log compression of the regularized NCC function were compared in numerical simulations of uniform and inclusion phantoms. Significant improvement was achieved with the proposed scheme for lateral estimation results. For example, lateral signal-to-noise ratio (SNR) was 10 dB higher after log compression at 3% strain in a uniform phantom. Lateral contrast-to-noise ratio (CNR) was 1.81 dB higher with proposed method at 3% strain in inclusion phantom. No significant difference was observed in axial estimation due to presence of phase information and high sampling frequency. Our results suggest that this simple approach makes Bayesian regularization robust to over-regularization artifacts.

Echo of ring current storms in the ionosphere

The ionospheric weather Vσ index maps are generated from GIM-TEC produced at the Jet Propulsion Laboratory (JPL) with the denser grids of 1 × 1° in latitude and longitude, respectively. Using sliding-window statistical analysis, moving TEC median μ for 15 preceding days with estimated variance bounds is obtained for each grid pixel of GIM-TEC. The ionosphere variability index, Vσ, is ΔTEC deviation from the median normalized by the standard deviation σ. Vσ index segmentation is introduced specifying TEC storm if an instant TEC is outside the bound of μ±2σ. Comparisons of Vσ variability of 1 × 1° GIM-TEC maps with normal GIM-TECs of 2.5 × 5° in latitude and longitude demonstrates the greater TEC storm activity with denser grids maps. The superposed epoch analysis is performed for 77 intense storms (Dst ≤ −100 nT) and 246 moderate storms (−100 < Dst ≤ −50 nT) during 2000–2017, with zero time, t0, at Dst storm peak. The probabilities of TEC storm occurrence both positive (Vσp index) and negative (Vσn) are evaluated for 24 h prior to t0 and 48 h after t0 for global scale and three specified latitude zones: North High (NH) magnetic latitudes λ > 50°, South High (SH) λ < −50°, and Equatorial Ionization Anomaly (EIA) Band between ±35° magnetic latitudes. The equinoctial positive Vσp index shows the maxima on March and September, Dst intensity peaks on April and October, and the negative Vσn peaks on May and November. The amplitude of Vσp for the intense storms exceeds that for the moderate storm by 2 times and exceeds the amplitude of Vσn by 1.5 times. Storm Enhanced Density (SED) is evident with the largest amplitude of Vσp at EIA Band exceeding Vσp for NH and SH zones by 3 times. The negative Vσn occurrence observed for selected zones during the intense storms is decreased by 5 times for the moderate storms. The normalized cross-correlation function is used to define lag (time delay) between peak of Vσp and Vσn and t0 of Dst peak. The majority of positive Vσp indices (57.5%) are observed prior to Dst storm (lag varies from −1 to −6 h with Dst from −50 to −400 nT) so the TEC enhancement can serve as a precursor of Dst storm. The time delay for the negative Vσn is inversely related with Dst storm intensity (lag varies from 11 to 8 h with Dst from −50 to −400 nT).

Fired bullet signature correlation using the Congruent Matching Profile Segments (CMPS) method

We introduce the Congruent Matching Profile Segments (CMPS) method for objective comparison of striated tool marks and apply it to bullet signature correlations. The method is derived from the congruent matching cell (CMC) method developed for the comparison of impressed tool marks. The proposed method is designed to increase comparison accuracy by addressing the comparison challenges caused by striae profiles with different lateral scales, varying vertical (height) scales, and sections that are poorly marked or have little to no similarity. Instead of correlating the entire profiles extracted from striated tool marks, the method divides one of the compared profiles into segments. Each segment is then correlated with the other profile. The CMPS method uses the normalized cross-correlation function with multiple correlation peak inspection to determine the number of profile segments that have both significant topography similarity and a congruent registration position. Initial tests were performed on the land engraved areas (LEAs) of 35 bullets fired from 10 consecutively manufactured pistol barrels. The results show clear separation between the CMPS scores of the 549 known non-matching (KNM) LEA profiles and the 46 known matching (KM) LEA profiles. These results are an improvement over those obtained using the correlation coefficient score of whole profiles. The large number of CMPS segment correlations may facilitate a statistical approach to error rate estimations.

EIT monitors valid and robust regional ventilation distribution in pathologic ventilation states in porcine study using differential DualEnergy-CT (\u0394DECT)

It is crucial to precisely monitor ventilation and correctly diagnose ventilation-related pathological states for averting lung collapse and lung failure in Intensive Care Unit (ICU) patients. Although Electrical Impedance Tomography (EIT) may deliver this information continuously and non-invasively at bedside, to date there are no studies that systematically compare EIT and Dual Energy CT (DECT) during inspiration and expiration (ΔDECT) regarding varying physiological and ICU-typical pathological conditions such as atelectasis. This study aims to prove the accuracy of EIT through quantitative identification and monitoring of pathological ventilation conditions on a four-quadrant basis using ΔDECT. In a cohort of 13 pigs, this study investigated systematic changes in tidal volume (TV) and positive end-expiratory pressure (PEEP) under physiological ventilation conditions. Pathological ventilation conditions were established experimentally by single-lung ventilation and pulmonary saline lavage. Spirometric data were compared to voxel-based entire lung ΔDECT, and EIT intensities were compared to ΔDECT of a 12-cm slab of the lung around the EIT belt, the so called ΔDECTBelt. To validate ΔDECT data with spirometry, a Pearson’s correlation coefficient of 0.92 was found for 234 ventilation conditions. Comparing EIT intensity with ΔDECT(Belt), the correlation r = 0.84 was found. Normalized cross-correlation function (NCCF) between scaled global impedance (EIT) waveforms and global volume ventilator curves was r = 0.99 ± 0.003. The EIT technique correctly identified the ventilated lung in all cases of single-lung ventilation. In the four-quadrant based evaluation, which assesses the difference between end-expiratory lung volume (ΔEELV) and the corresponding parameter in EIT, i.e. the end-expiratory lung impedance (ΔEELI), the Pearson’s correlation coefficient of 0.94 was found. The respective Pearson’s correlation coefficients implies good to excellent concurrence between global and regional EIT ventilation data validated by ventilator spirometry and DECT imaging. By providing real-time images of the lung, EIT is a promising, EIT is a promising, clinically robust tool for bedside assessment of regional ventilation distribution and changes of end-expiratory lung volume.

Matching Algorithm of Statistical Optimization Feature Based on Grid Method

The matching algorithm based on image feature points is widely used in image retrieval, target detection, identification and other image processing fields. Aiming at the problem that the feature matching algorithm has low recall rate, a statistical optimization feature based on grid of the normalized cross correlation function is proposed. The matching main direction difference and scale ratio are introduced to feature matching process, for comprehensively utilizing SIFT feature points' information, such as the main direction, scale and position constrains, to accelerate the solution of matching position constraint under the grid framework, which optimizes the feature matching results and improves the recall rate and comprehensive match performance. Firstly, the nearest neighbor matching feature points of each feature point in the original image are found in the target image, and the initial matching results are obtained. Secondly, the matching main direction difference is used to eliminate most mismatches of the initial matching. Thirdly, the matching images are meshed based on the matching scale ratio information, and the position information of the matching feature points distributed among the grids is gathered statistics. Finally, the normalized cross correlation function of each small grid in the original image is calculated to determine whether the matching in the small grid is correct, and the optimized feature matching results are obtained. The experimental results show that the matching accuracy of the new algorithm is similar to that of classical feature matching algorithms, meanwhile the matching recall rate is increased by more than 10%, and a better comprehensive matching performance is obtained.

1/f spectrum estimation based on α-stable distribution in colored Gaussian noise environments

The main goal of this paper is to suppress the effect of unavoidable colored Gaussian noise on declining accuracy of transistor 1/f spectrum estimation. Transistor noises are measured by a nondestructive cross-spectrum measurement method, which is first to amplify the voltage signals through ultra-low noise amplifiers, then input the weak signals into data acquisition card. The data acquisition card collects the voltage signals and outputs the amplified noise for further analysis. According to our studies, the output 1/f noise can be characterized more accurately as non-Gaussian α-stable distribution rather than Gaussian distribution. Therefore, by utilizing the properties of α-stable distribution, we propose a cross-spectrum method effective in noisy environments based on samples normalized cross-correlation function. Simulation results and diodes output noise spectrum estimation results confirm the effectiveness of our method.

Valid data based normalized cross-correlation (VDNCC) for topography identification

Abstract The Normalized Cross-Correlation (NCC) function is a widely used pattern-matching method. However, when the input data have a void area created by non-rectangular data or outliers, the accuracy of the standard NCC function may decrease. Especially when the regional mean values under the NCC window have a significant difference in the global mean value, the possible mis-matching may affect the identification results. In this paper, a valid data based NCC (VDNCC) algorithm is proposed for eliminating the effect of the void area. The new algorithm prevents void areas from being included in the calculation by introducing the valid data templates. VDNCC obtains higher NCC values and probabilities of correct matching in the experiments. In the ballistics identification tests, the results show that VDNCC can enhance the capacity of identification based on the NCC function as the core.

Particle Filter–Based Target Tracking Algorithm for Magnetic Resonance–Guided Respiratory Compensation: Robustness and Accuracy Assessment

To assess overall robustness and accuracy of a modified particle filter-based tracking algorithm for magnetic resonance (MR)-guided radiation therapy treatments. An improved particle filter-based tracking algorithm was implemented, which used a normalized cross-correlation function as the likelihood calculation. With a total of 5 healthy volunteers and 8 patients, the robustness of the algorithm was tested on 24 dynamic magnetic resonance imaging (MRI) time series with varying resolution, contrast, and signal-to-noise ratio. The complete data set included data acquired with different scan parameters on a number of MRI scanners with varying field strengths, including the 1.5TMR linear accelerator. Tracking errors were computed by comparing the results obtained by the particle filter algorithm with experts' delineations. The ameliorated tracking algorithm was able to accurately track abdominal as well as thoracic tumors, whereas the previous Bhattacharyya distance-based implementation failed in more than 50% of the cases. The tracking error, combined over all MRI acquisitions, is 1.1±0.4 mm, which demonstrated high robustness against variations in contrast, noise, and image resolution. Finally, the effect of the input/control parameters of the model was very similar across all cases, suggesting a class-based optimization is possible. The modified particle filter tracking algorithm is highly accurate and robust against varying image quality. This makes the algorithm a promising candidate for automated tracking on the MR linear accelerator.

Cosmic rays intensity and atmosphere humidity at near earth surface

Experimental studies of estimation the mutual influence of humidity and flux of cosmic rays in first approximation were carried out. Normalized cross-correlation function of time series of neutron monitors count rate and level of relative atmosphere humidity near cosmic rays registration point is studied. Corrected and uncorrected on pressure minute and hour data of 6NM64 neutron monitor count rate were used for the study. Neutron monitor is located in Al-Farabi Kazakh National University, at an altitude of 850 m above sea level. Also, data from NM64 neutron monitor of Tien Shan mountain research station of Institute of Ionosphere, located at an altitude of 3340 m above sea level were used. Uncorrected on pressure cosmic rays intensity better reflects the changes in relative atmosphere humidity. Average and sometimes strong relationship is often observed by time changes of atmosphere humidity near the point of cosmic rays detection and their intensity: the value of normalized cross-correlation function of respective signals, even in case of their long duration and a large number of data (eg, for minute changes at intervals of up to several months) covers 0.5 - 0.75 range, sometimes falling to ∼⃒ 0.4.