Bispectral Imaging Research Articles

Accumulated bispectral image-based respiratory sound signal classification using deep learning.

The COVID-19 virus is increasingly crucial to human health since new variants appear frequently. Detection of COVID-19 through respiratory sound has been an important area of research. This study analyzes respiratory sounds using novel accumulated bi-spectral features. The principal domain bispectrum is used for computing accumulated bispectrum. The resulting magnitude bispectrum is used in forming the bispectral image. In this work, a convolutional neural network (CNN) and ResNet-50 algorithms are designed to classify respiratory sounds as either COVID-19 or healthy. The performance of the proposed method is compared with the state-of-the-art methods. The proposed CNN-based method achieves the highest accuracy of 87.68% for shallow breath sounds, and ResNet-50 achieves the highest accuracy of 87.62% for deep breath sounds. Similarly, proposed methods gives the improved performance for other respiratory sounds.

Recursion-driven bispectral imaging for dynamic scattering scenes.

Imaging dynamic strongly scattering scenes remains a significant challenge because it is typically believed that moving objects and dynamic media provide huge barriers. Instead, we use the dynamics of objects and media and put forward a recursion-driven bispectral imaging (ReDBI) framework here for the reconstruction of a stationary or moving object hidden behind the dynamic media. ReDBI avoids the errors introduced by speckle modulation and phase-retrieval algorithms in the existing studies. We also quantitatively assess the reconstruction difficulty of character and shape objects with the benchmark of the minimum number of speckle images (MNSI) required to achieve a high-quality reconstruction, which can help to comprehend the media's transfer properties.

Bispectral Images of Radar Wideband Objects Characters Interpretation

A methodological approach to the analysis of broadband radar signatures based on the application of the theory of bispectral estimation is presented. The approach involves analyzing the phase relationships of the target scattering centers, providing the more complete account of the information contained in the frequency characteristic of the target compared to the range portrait traditionally obtained using the Fourier transform. Analysis of phase connections allows identifying scattering centers formed as a result of multiple reflections of electromagnetic waves by structural elements of the object of complex shape or by separate close-located objects within the observed scene. The geometric image of the bispectra of the radar broadband object’s signature used for analysis is a hexagon in the coordinates “longitudinal range — longitudinal range,” which allows detecting mutual connections of scattering centers spaced along the direction of the location. The proposed methodological approach was tested using a synthesized frequency characteristic of an abstract multipoint target, as well as based on electrodynamic modeling data of complex backscattering fields. The comparison of the results of identification of scattering centers obtained using a bispectral image, the range portrait and the priori information about the location object indicates the correctness of the proposed methodological approach.

Research on Embedded Ball Screw Diagnosis System for Mechanical Fault Based on Bispectral Image

Ball screw is one of the main basic transmission components in CNC machine tool feed system because of its high transmission efficiency, positioning accuracy, and rigidity. It plays an irreplaceable role in the process of machine tool torque transmission and positioning. However, ball screw is also one of the parts which are easy to break down in the feed system. If it breaks down, it will affect the processing accuracy of the whole machine tool and even cause shutdown. Numerical control means that digital control is a high-efficiency technology that uses digital information to control mechanical movement and processing processes. Therefore, to increase the high-speed and high-precision operation ability of CNC machine tools, research and development of efficient and reliable predictive maintenance and issue identification technology to guide maintenance of CNC machine tools are critical. Throughout this study, a bispectrum image-based embedded defect fight against the disease for cylindrical gears is provided. Firstly, the bispectrum of fault signal is generated by Wavelet Packet Threshold denoising, wavelet packet reconstruction, and bispectrum analysis, and the characteristics of bispectrum are represented by the first kind of gray moments. These feature statistics are used as input feature vectors of BP neural network pattern recognition algorithm to classify these feature sets and identify the corresponding gear fault types. Experiments show that under the condition of noise, after 14.5 hours of testing, the NGI has increased significantly and can be used to diagnose faults in the gear system, and the method achieves relatively ideal recognition rate and verifies the feasibility of gear box fault diagnosis method based on image recognition. The code compiled by OpenCV library is easy to transplant to embedded system, with high development efficiency and reliable program operation. OpenCV has the characteristics of powerful matrix computing capability and convenient and flexible interface, and it is a general algorithm that can realize real-time image processing.

Fault diagnosis of a planetary gearbox based on a local bi-spectrum and a convolutional neural network

The transmission paths of vibration signals in the planetary gearboxes are complex. The signals have the characteristics of strong background noise, instability and non-Gaussian. Bi-spectrums can suppress Gaussian colored noise and are suitable for vibration signal processing of planetary gearboxes. In the traditional fault diagnosis methods based on bi-spectrums, the amplitudes of fault characteristic frequency, or the other further quantitative calculations values, are generally used as the basis of fault diagnosis processes. It has been found that bi-spectrum images can directly characterize the faults of the planetary gearboxes. Convolutional neural networks (CNNs) have been used in mechanical fault diagnoses in recent years. One-dimensional original signals are converted into two-dimensional images as CNN input, which is an effective method for mechanical fault diagnoses. At the present time, there has not been any relevant research conducted using bi-spectral images as CNN input. In this study, a fault diagnosis method based on local bi-spectrum and CNN was proposed. A bi-spectral analysis of the vibration signals of the planetary gearbox was first carried out in order to reveal the fault information while retaining the non-Gaussian information. Then, according to the bi-spectrum symmetry, local images containing the main information were taken as the input of the CNN, which reduced the redundancy of the fault information. Then, in order to improve the diagnostic accuracy of the CNN, the key parameters of CNN architecture were optimized. Finally, a CNN diagnosis model was built to realize the classification diagnoses of different fault positions and different fault degrees of planetary gearboxes. This study’s comparison of the diagnosis results of the full bi-spectrum + CNN, original vibration signal + CNN, local bi-spectrum + (support vector machines), and local bi-spectrum + (stacked auto-encoder) showed that the proposed method in this study had achieved both accuracy and rapidity in the fault diagnoses of planetary gearboxes.

Daily Burned Area Mapping for Prescribed Rangeland Burning in the Flint Hills Region Using MODIS Data

Highlights Average burn frequency and fire size were larger in the center part of the Flint Hills region. The maximum daily burned area was 0.2 million ha. Even distribution of fires can reduce smoke impact. Fires were concentrated on days with high solar radiation. Changing this pattern can reduce the impact on O 3 . Abstract. Smoke from prescribed burning in the Flint Hills region impacts air quality and contributes to the exceedances of ozone (O3). The objectives of this study were 1) to map the daily burned area in this region from 2003 to 2019 using the combination of Moderate Resolution Imaging Spectroradiometer (MODIS) highest resolution imagery and standard active fire data from satellite, and 2) to identify the spatial and temporal distributions and patterns of daily fire activities. Red and near-infrared images were combined, and supervised minimum distance classification of the bi-spectral images was applied to map the daily burned area. Results showed that fire activities were highly concentrated in a few days in mid-April. The annual burned percentage (ranged from 11% to 52%) and the average fire size (ranged from 160 to 400 ha) were larger in the central part of the Flint Hills region than in the Southern part and at the edge. On average, the preferred weather conditions by landowners only occurred in around 10 days in one spring burning season. The maximum daily burned area in the Flint Hills study region was as high as 0.2 million ha, about 1/6 of the total burned area in the whole spring burning season. Based on analysis of historical daily burned area and weather data, most fires occurred on days with high solar radiation, favoring O3 production. Changing this pattern or more evenly distributed fires can reduce the smoke impact on daily O3. The results of this study provided a solid foundation for the ongoing development of O3 regression models using daily burned area and meteorological factors as predictor variables. Keywords: MODIS, Ozone, Prescribed burning, Remote sensing, Smoke impact.

Quantification of gray mold infection in lettuce using a bispectral imaging system under laboratory conditions.

Gray mold disease caused by the fungus Botrytis cinerea damages many crop hosts worldwide and is responsible for heavy economic losses. Early diagnosis and detection of the disease would allow for more effective crop management practices to prevent outbreaks in field or greenhouse settings. Furthermore, having a simple, non‐invasive way to quantify the extent of gray mold disease is important for plant pathologists interested in measuring infection rates. In this paper, we design and build a bispectral imaging system for discriminating between leaf regions infected with gray mold and those that remain unharmed on a lettuce (Lactuca spp.) host. First, we describe a method to select two optimal (high contrast) spectral bands from continuous hyperspectral imagery (450–800 nm). We then explain the process of building a system based on these two spectral bands, located at 540 and 670 nm. The resultant system uses two cameras, with a narrow band‐pass spectral filter mounted on each, to measure the bispectral reflectance of a lettuce leaf. The two resulting images are combined using a normalized difference calculation that produces a single image with high contrast between the leaves’ infected and healthy regions. A classifier was then created based on the thresholding of single pixel values. We demonstrate that this simple classification produces a true‐positive rate of 95.25% with a false‐positive rate of 9.316% in laboratory conditions.

WITHDRAWN: An efficient approach for generating IRIS codes for optimally recognizing IRIS using multi objective genetic algorithm

Abstract A process of uniquely identifying a human being includes the very prominent method of Iris Recognition. One of the approaches in this process is by using Bi-Spectral Imaging. However, in the course of the process the man challenge is the trade-off between inter and intra class variability in the search of performance improvement in such conditions. In the current methods of Biometric Security using pattern recognition feature, it made use of Iris Recognition with feature optimization. Henceforth, our aim in the following research manuscript is to evaluate the recapturing and equality of Iris images for both the noticeable as well as closer-infrared illumination to attain higher accuracy using feature selection and feature extraction method.

Design and Implementation of Marine Automatic Target Recognition System Based on Visible Remote Sensing Images

Gao, X.B., 2020. Design and implementation of marine automatic target recognition system based on visible remote sensing images. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 277-279. Coconut Creek (Florida), ISSN 0749-0208.In the process of visible light remote sensing imaging, different sea surface wave conditions have different reflection ability to illumination, which makes the brightness, contrast and other information of visible light remote sensing images have great changes. Marine ship target recognition is an important application of image processing in remote sensing field. Based on pixel-level fusion of visible and infrared bispectral images, this paper extracts features from fusion results, and recognizes targets in images according to the matching of target image features and template image features. Comprehensive utilization of image preprocessing, image smoothing and anti-cloud interference algorithms can quickly and accurately realize ship target detection under the complex background of land and sea. The experimental results show that the algorithm is effective both in physical mechanism and in actual image effect.

City-Scale Distance Sensing via Bispectral Light Extinction in Bad Weather

In this paper, we propose a novel city-scale distance sensing algorithm based on atmosphere optics. The suspended particles, especially in bad weather, would attenuate the light at almost all wavelengths. Observing this fact and starting from the light scattering mechanism, we derive a bispectral distance sensing algorithm by leveraging the difference of extinction coefficient between two specifically selected near infrared wavelengths. The extinction coefficient of the atmosphere is related to both wavelength and meteorological conditions, also known as visibility, such as the fog and haze day. To account for different bad weather conditions, we explicitly introduce visibility into our algorithm by incorporating it into the calculation of extinction coefficient, making our algorithm simple yet effective. To capture the data, we build a bispectral imaging system that is able to take a pair of images with a monochrome camera and two narrow band-pass filters. We also present a wavelength selection strategy that allows us to accurately sense distance regardless of material reflectance and texture. Specifically, this strategy determines two distinct near infrared wavelengths by maximising the extinction coefficient difference while minimizing the influence of building’s reflectance variance. The experiments empirically validate our model and its practical performance on the distance sensing for the city-scale buildings.

Solar-blind ultraviolet object detection based on the ultraviolet and visible bispectral airborne imaging system

The solar-blind ultraviolet (UV) and visible (VIS) imaging system provides a valuable tool for search and rescue missions. However, due to atmospheric scattering and absorption effects, the UV images are significantly degraded, even missing the target in some frames. A framework based on a weighted mask, with three schemes suitable for various imaging conditions is proposed. Compared with traditional methods, this framework not only preserves low-intensity target regions but also highlights and tracks any suspicious target. Scheme 1 enhances the signal-to-noise ratio (SNR) by computing the accumulating weights of sequential frames, supporting temporal and average weighting means. The temporal weighting serves as a traditional recursive temporal filtering method, which has an effect similar to that of average weighting. Scheme 2 mitigates small platform drifts by introducing a Kalman filter. Scheme 3 mitigates large platform perturbations by eliminating interference from a moving background, which is achieved by determining the warping relationship from adjacent VIS frames. The experiments are designed to cover as many situations as possible, including low-SNR imaging on a static platform, high-SNR imaging on a flat-flying small drone, and strong/weak complex target imaging on a hovering platform. The experiments assess the proposed methods and validate their predicted performance.

A coupled in-situ measurement of temperature and kinematic fields in Ti-6Al-4V serrated chip formation at micro-scale

The present paper describes and uses a novel bi-spectral imaging apparatus dedicated to the simultaneaous measurement of kinematic and thermal fields in orthogonal cutting experiment. Based on wavelength splitting, this device is used to image small scale phenomenon (about 500×500μm500×500μm area) involved in the generation of serrated chips from Ti-6Al-4V titanium alloy. Small to moderate cutting speeds are investigated at 6000 images per second for visible spectrum and 600 images per second for infrared measuresments. It allows to obtain unblurred images. A specific attention is paid to calibration issue including optical distortion correction, thermal calibration and data mapping. A complex post-processing procedure based on DIC and direct solution of the heat diffusion equation is detailed in order to obtain strain, strain-rate, temperature and dissipation fields from raw data in a finite strains framework. Finally a discussion is addressed and closely analyzes the obtained results in order to improve the understanding of the segment generation problem from a kinemtatic standpoint but also for the first time from an energetic standpoint.

Imaging photoplethysmography for clinical assessment of cutaneous microcirculation at two different depths.

The feasibility of bispectral imaging photoplethysmography (iPPG) system for clinical assessment of cutaneous microcirculation at two different depths is proposed. The iPPG system has been developed and evaluated for in vivo conditions during various tests: (1) topical application of vasodilatory liniment on the skin, (2) skin local heating, (3) arterial occlusion, and (4) regional anesthesia. The device has been validated by the measurements of a laser Doppler imager (LDI) as a reference. The hardware comprises four bispectral light sources (530 and 810 nm) for uniform illumination of skin, video camera, and the control unit for triggering of the system. The PPG signals were calculated and the changes of perfusion index (PI) were obtained during the tests. The results showed convincing correlations for PI obtained by iPPG530 nm and LDI at (1) topical liniment (r = 0.98) and (2) heating (r = 0.98) tests. The topical liniment and local heating tests revealed good selectivity of the system for superficial microcirculation monitoring. It is confirmed that the iPPG system could be used for assessment of cutaneous perfusion at two different depths, morphologically and functionally different vascular networks, and thus utilized in clinics as a cost-effective alternative to the LDI.

Reproduction of Reflective and Fluorescent Components using Eight-band Imaging

We propose a method for relighting fluorescent objects using a multiband image system. Fluorescence is often present in everyday articles and its optical properties make it harder to reproduce than pure reflectance. Decomposing colors into separate fluorescent and reflective components is required for accurate color reproduction. In our method, bi-spectral images are captured using an eight-band camera and an eight-band lighting system for the decomposition. First, spectral reflectance of the object is estimated. Next, the multiband image of the fluorescent components under relighting illumination is generated from the weighted linear combination of the captured fluorescent images. The weight of each band is calculated from the spectral transmittance of each band-pass filter attached to the lighting system, and the spectral power distributions (SPD) of the illumination during image capturing and relighting. Finally, a relighted image is reproduced by composing reflective and fluorescent component images. Experimental evaluations show that the spectral reflectance and SPD of fluorescent components are accurately estimated and relighting images are well reproduced.

A Modified Bispectral Image Reconstruction Method in Ophthalmology

A modified bispectral method is proposed for solving the inverse problem of image reconstruction in ophthalmology. Modeling shows that the method produces stable results for typical symmetric aberrations of the human eye's imaging system in the presence of turbulent distortions leading to a signalternating optical transfer function.

Optical System for Bispectral Imaging in Mid-IR at 1000 Frames per Second

We propose, evaluate, and demonstrate the performance of an IR/optical double-image experimental setup where we capture two simultaneous images of a single object, in two different spectral bands, using a single detector array. With this arrangement, we may observe rapidly changing phenomena, at a rate of more than 1000 frames per second, without the loss of the spatial information about the test subject. We describe the optical system to perform simultaneous imaging in IR for slightly inclined optical axes. We verify the actual performance by applying the experimental method to flame analysis in the mid-IR to determine the combustion efficiency.

Using bi-spectral imaging technology for simulated online-weed control in winter wheat and maize.

In spring 2011, two field trials on site-specific weed control in winter wheat and maize were carried out at Ihinger Hof research station of the University of Hohenheim. For the image acquisition, bi-spectral cameras were mounted on a vehicle. These cameras are able to take images free from disturbances by soil, mulch and stones. Images and the corresponding GPS-data were stored on-the-go. Afterwards, the images were analyzed by a weed recognition software. Weed infestation was mapped in consideration of weed species and weeds grouped according to their herbicide sensitivity. In order to simulate an online herbicide application, a onesided moving average of order five was used for the weed mapping. This kind of rearward calculation uses only the data of weed infestation which were already assessed behind or directly in the current position of the vehicle. The calculated weed distribution maps were checked by visual grid sampling. Herbicide application maps were generated by applying weed thresholds on the weed distribution maps. The herbicide application based on the maps was conducted by a multiple sprayer which allows the application of up to three herbicides independently from each other in a single pass across the field. Later on, the performance of the herbicide application was controlled again by visual grid sampling. Compared to a uniform herbicide application, the sitespecific weed control saved 83 % and 58 % herbicides respectively in winter wheat and 66 % in maize. The average efficacy of the site-specific herbicide application system in winter wheat was 70 % of the conventional herbicide application. Keywords: Bi-spectral cameras, herbicide application, image analysis, site-specific, weed control Simulation einer online Unkrautkontrolle in Winterweizen und Mais unter Verwendung von Bispektralkameras Im Fruhjahr 2011 wurden auf der Versuchsstation Ihinger Hof der Universitat Hohenheim Feldversuche zur teilschlagspezifischen online-Unkrautkontrolle in den Kulturen Winterweizen und Mais durchgefuhrt. Die Bildaufnahme fur die Erfassung der Verunkrautung mit Hilfe von digitaler Bildverarbeitung erfolgte mit einem Kamerafahrzeug, auf welchem Bispektralkameras montiert waren. Die Verwendung dieser Kameras gewahrleistet die Aufnahme von Bildern, die von Boden, Steinen und Mulch weitestgehend ungestort sind. Zusammen mit den Bildern wurden die korrespondierenden Geokoordinaten gespeichert. Nach der anschliesenden Bildauswertung unter Verwendung digitaler Bildauswerteverfahren erfolgte eine Kartierung der ermittelten Verunkrautung nach Unkrautarten bzw. Unkrauter gruppiert gemas der Herbizidempfindlichkeit. Fur die Kartierung wurden einseitig gleitende Mittelwerte der funften Ordnung berechnet. Die Bestimmung des Mittelwertes erfolgte jeweils mit den vier Messwerten die zeitlich gesehen hinter dem aktuellen Messwert lagen und dem aktuellen Messwert. Durch diese ruckwartsgewandte Mittelwertbildung wurde die online Bildverarbeitung simuliert. Zur Uberprufung der Plausibilitat der berechneten Unkrautverteilungskarten wurden die aus einer visuellen Rasterbonitur stammenden Daten herangezogen. Unter Verwendung von Schadschwellen wurden die auf der Basis der Bildanalyse erstellten Unkrautverteilungskarten fur die Berechnung von Applikationskarten benutzt. Die Umsetzung der Applikationskarten erfolgte mit einer Dreikammerspritze, welche eine simultane Applikation von bis zu drei Herbiziden unabhangig voneinander erlaubt. Eine Erfolgskontrolle der durchgefuhrten Herbizidapplikation erfolgte im zeitlichen Abstand wiederum anhand einer visuellen Rasterbonitur. Im Vergleich zur betriebsublichen Variante wurde durch die teilschlagspezifische Herbizidapplikation im Winterweizen eine Herbizideinsparung von 83 % bzw. 58 % und im Mais von 66 % realisiert. Die durchschnittliche Wirksamkeit der teilschlagspezifischen Herbizidmasnahme im Winterweizen betrug 70 % der betriebsublichen Variante. Stichworter: Bildverarbeitung, Bispektralkameras, Herbizidapplikation, teilschlagspezifisch, Unkrautkontrolle

Application of Non-Negative Tensor Factorization in Intelligent Fault Diagnosis of Gearboxes

In this paper, a novel approach is proposed to extract features from the bispectra of mechanical fault signals using non-negative tensor factorization (NTF) for the purpose of establishing an intrinsic relationship between mechanical faults and extracted characteristics. First, the bispectra of mechanical signals are obtained and stacked to form a three-dimensional (3D) tensor. Then, an NTF method is applied to extract features, which are represented by a series of “basis images,” from this tensor. Finally, coefficients indicating these basis images’ weights in constituting original bispectral images are calculated for fault classification. Experiments on fault datasets of gearboxes showed that the results of the proposed method not only reveal some nonlinear features of the system, but also have low data dimensions and intuitive meanings with regard to fault characteristic frequencies, which bring great convenience to an explanation of the relationship between mechanical faults and the corresponding bispectra.

Stratus and Fog Products UsingGOES-8–93.9-μm Data

Abstract Using data from the GOES-8–9 imager, this paper discusses the potential for consistent, around-the-clock image products that can trace the movement and evolution of low, stratiform clouds. In particular, the paper discusses how bispectral image sequences based on the shortwave (3.9 μm) and longwave (10.7 μm) infrared channels can be developed for this purpose. These sequences can be animated to produce useful loops. The techniques address several problems faced by operational forecasters in the tracking of low clouds. Low clouds are often difficult or impossible to detect at night because of the poor thermal contrast with the background on infrared images. During the day, although solar reflection makes low, stratiform clouds bright on GOES visible images, it is difficult to distinguish low clouds from adjacent ground snowcover or dense cirrus overcasts. The shortwave infrared channel often gives a superior delineation of low clouds on images because water droplets produce much higher reflectance...

Practical aspects of image recovery by means of the bispectrum

The use of the bispectrum as a tool to handle the phase-retrieval problem associated with speckle interferometry is examined. The basic concepts and equations involved in bispectral imaging are discussed. Based in signal-to-noise ratio considerations, a simple recipe to predict the success of bispectral imaging is given. Because of their higher noise tolerance, two least-squares minimization schemes are used to reconstruct the object Fourier phase encrypted in the bispectral phase. The error-reduction algorithm for phase retrieval is applied in conjunction with the minimization procedures to overcome stagnation at local minima. Examples with simulated and real astronomical data are presented, including a comparison of the outcome of bispectral processing applied to both adaptively compensated and uncompensated data. The resulting diffraction-limited reconstructions are very similar.