Regular Digital Camera Research Articles

Analysis of Coral Reef Conditions in the Waters of Panjang Island, Central Bangka Regency

Coral reefs are organisms that live at the bottom of the water and take the form of sturdy limestone formations capable of withstanding the force of ocean waves. Ecologically, coral reefs serve as habitats where various animal and plant organisms seek food and shelter. This research aims to analyze the coral reef ecosystem conditions in the waters of Panjang Island and provide recommendations for sustainable management of marine biodiversity in the waters of Panjang Island, Central Bangka Regency. The Underwater Photo Transect (UPT) method involves underwater photography using a digital or regular digital camera equipped with a waterproof housing to withstand seawater exposure. The research results indicate that the percentage of live coral cover in the waters of Panjang Island ranges from 70.07% to 14.07%, categorizing it as fair to poor according to the Minister of Environment Decree No. 4 of 2001 on the Standard for Coral Reef Damage. Fourteen coral growth forms were identified in the waters of Panjang Island, belonging to 17 coral genera. Recommendations for managing marine resources on Panjang Island include sustainable tourism development. Environmentally based tourism development can serve as a solution for sustainably utilizing coral reefs and promoting improving coastal and fisheries management based on Marine Conservation Areas.

Microcrack characterization of loaded Engineered Cementitious Composites via optical scans and photogrammetric analyses

Concrete cracks accelerate the ingress of harmful species and must be gauged accurately for durability evaluation and prediction. As a novel class of ultra-ductile concrete, Engineered Cementitious Composites (ECC) develops multiple sub-hairline cracks that are difficult to visualize using conventional techniques. In this study, a semi in-situ laboratory approach is proposed based on optical microscopy and photogrammetric analysis to enhance the accuracy of crack width measurement in ECC. Microscopic images scanned from the material surface were reconstructed and analyzed to extract the statistics of crack width, location, number, and spacing. Results suggested that general portable microscopes can effectively identify cracks smaller than 2 µm in loaded condition and provide magnified high-resolution crack images that are hardly achieved by regular digital cameras. Crack openings can be isolated via 2D FFT filtering and binarized to attain the datasets of crack spacing and crack width distribution. In contrast to microscopy, conventional digital image correlation (DIC) as an indirect method was found to overestimate sub-pixel crack widths particularly when the crack width and spacing are substantially smaller than the image resolution. In these scenarios, it is recommended to combine optical microscopy with DIC to ensure simultaneously accurate and holistic crack width characterization. The proposed technique can be used for general materials with multiple fine cracks.

CNN based approach for identifying banana species from fruits

Classification and recognition of fruits are still the challenging one as there are different classes of fruit types having wide inter-class resemblance. This paper proposes a banana identification model using a five-layer convolution neural network (CNN) which composed of convolution layer, pooling layer and fully connected layer. Fruits like Apple, Strawberry, and Orange, Mango and banana have been analyzed and several features have been extracted using deep learning-based CNN algorithm. Finally, the fruit identification process is done by random forest and K-Nearest Neighborhood (K-NN) classifying algorithms. A regular digital camera is used for the image acquisition process. All image manipulation processes are performed in MATLAB-17 environment.Experiments are conducted in our database consisting of 5887 fruit images. The performance of the proposed deep learning based-random forest and KNN classifiers are compared with the existing feature extraction method of HOG based random forest and KNN in terms of accuracy, precision, recall and f-score and we have achieved a accuracy rate of 96.98% for deep feature-random forest classification combination algorithm which is better than the deep feature-KNN, HOG based KNN and random forest classifiers.

Snapshot hyperspectral imaging using wide dilation networks

Hyperspectral (HS) cameras record the spectrum at multiple wavelengths for each pixel in an image, and are used, e.g., for quality control and agricultural remote sensing. We introduce a fast, cost-efficient and mobile method of taking HS images using a regular digital camera equipped with a passive diffraction grating filter, using machine learning for constructing the HS image. The grating distorts the image by effectively mapping the spectral information into spatial dislocations, which we convert into a HS image by a convolutional neural network utilizing novel wide dilation convolutions that accurately model optical properties of diffraction. We demonstrate high-quality HS reconstruction using a model trained on only 271 pairs of diffraction grating and ground truth HS images.

Light-field image acquisition from a conventional camera: design of a four minilens ring device

In the past few years, a new type of camera has been emerging on the market: a digital camera capable of capturing both the intensity of the light emanating from a scene and the direction of the light rays. This camera technology called a light-field camera uses an array of lenses placed in front of a single image sensor, or simply, an array of cameras attached together. An optical device is proposed: a four minilens ring that is inserted between the lens and the image sensor of a digital camera. This device prototype is able to convert a regular digital camera into a light-field camera as it makes it possible to record four subaperture images of the scene. It is a compact and cost-effective solution to perform both postcapture refocusing and depth estimation. The minilens ring makes also the plenoptic camera versatile; it is possible to adjust the parameters of the ring so as to reduce or increase the size of the projected image. Together with the proof of concept of this device, we propose a method to estimate the positions of each optical component depending on the observed scene (object size and distance) and the optics parameters. Real-world results are presented to validate our device prototype.

Deep Neural Networks Analysis of Borescope Images

This paper presents results on applying deep neural networks to analysis of images from borescope inspections of large turbofan engines, carried out in the field. Such inspections are done as a part of routine monitoring and maintenance as well as an initial, investigative response to alerts from automatic monitoring systems, pilots or engineers. Across GE’s commercial engines fleet, a substantial number of images have been gathered this way. The deep learning techniques that have come out of computer vision and machine learning research in the last decade offer new possibilities for analyzing and mining such data collections. This paper presents initial results on separating borescope images from images created with regular digital cameras, as well as classifying images containing various engine parts, with average accuracy of 95% and 77%, respectively, on unseen validation data.

Estimation of evapotranspiration of temperate grassland based on high-resolution thermal and visible range imagery from unmanned aerial systems

ABSTRACTSpatially distributed high-resolution data of land surface temperature (LST) and evapotranspiration (ET) are important information for crop water management and other applications in the agricultural sector. While satellite data can provide LST high-resolution data of 100 m, the current development of unmanned aerial systems (UAS) and affordable low-weight thermal cameras allows LST and subsequent ET to be derived at resolutions down to centimetre scale.In this study, UAS-based images in the thermal infrared (TIR) and visible spectral range were collected over a managed temperate grassland in July 2016 at the Terrestrial Environmental Observatories Networks TERENO preAlpine observatory site at Fendt, Germany. The UAS set-up included a lightweight thermal camera (Optris Pi Lightweight) and a regular digital camera (Sony α 6000) that allowed for the acquisition of thermal and optical images with a ground resolution of 5 cm and 1 cm, respectively. Three TIR-based ET models of different complexity were applied and the resulting ET estimates were compared to the Eddy covariance (EC) observations of turbulent energy fluxes and also to the evaporative fraction. While the Deriving Atmosphere Turbulent Transport Useful To Dummies Using Temperature (DATTUTDUT) model and the Triangle Method belong to the group of simpler contextual models, the Two-Source Energy Balance (TSEB) model incorporates a more physically based formulation of the surface energy balance. In addition to the comparison of UAS-based estimates of latent heat fluxes to EC observations, the effect of the spatial resolution of the model imagery input on the modelled results was analysed by running the models with imagery from the native resolution of the acquired images to resolutions that were aggregated up to 30 m.The results show that both contextual models are sensitive to the input image resolution and that the agreement with the EC observations improves with increasing image resolution. The TSEB model assumes that LST pixels represent a mixed signal of the soil and canopy components, thus an image resolution coarse enough to ensure this assumption should be chosen. However, with the exception of the native image resolution of 5 cm, we found no effect of image resolution on the spatially weighted mean TSEB estimates.For the studied grassland, the comparison of model estimates with EC observations indicates that all three models are able to reproduce observed energy fluxes with comparable accuracy with mean absolute errors of ET between 20 and 40 W m−2. The TSEB model showed larger deviations from the reference observations under cloudy conditions with rapid fluctuations of LST within the 30 min averaging period for EC. The two contextual models yielded similar results for most of the flights. The good performance of the DATTUTDUT model, which had the lowest input requirements of the three models, is especially promising in view of the application of UAS for routine near-real-time ET monitoring.

SNAPSHOT SPECTRAL AND COLOR IMAGING USING A REGULAR DIGITAL CAMERA WITH A MONOCHROMATIC IMAGE SENSOR

Abstract. Spectral imaging (SI) refers to the acquisition of the three-dimensional (3D) spectral cube of spatial and spectral data of a source object at a limited number of wavelengths in a given wavelength range. Snapshot spectral imaging (SSI) refers to the instantaneous acquisition (in a single shot) of the spectral cube, a process suitable for fast changing objects. Known SSI devices exhibit large total track length (TTL), weight and production costs and relatively low optical throughput. We present a simple SSI camera based on a regular digital camera with (i) an added diffusing and dispersing phase-only static optical element at the entrance pupil (diffuser) and (ii) tailored compressed sensing (CS) methods for digital processing of the diffused and dispersed (DD) image recorded on the image sensor. The diffuser is designed to mix the spectral cube data spectrally and spatially and thus to enable convergence in its reconstruction by CS-based algorithms. In addition to performing SSI, this SSI camera is capable to perform color imaging using a monochromatic or gray-scale image sensor without color filter arrays.

Detection of soybean aphids in a greenhouse using an image processing technique

Soybean aphid (Aphis glycines) is one of the most important insect pests of soybeans in North America. Insecticide application is performed if the aphids count exceeds the economic threshold of 250 per plant. Precise estimates of aphid densities are needed for field conditions to maximize insecticide application efficiency. The current method of identifying and counting aphids on a plant is a labor-intensive and time consuming process. The objective of this study was to use image processing technique to detect and count different sized soybean aphids on a soybean leaf. The trials were conducted with soybean plants grown in a greenhouse. Three sets of data were collected on different dates using replicate plants from 4 soybean varieties infested with a range of aphid densities. Images of infested soybean trifoliate leaves were captured with different cameras under 2 different illumination conditions with different cameras used across the different data sets. The images captured were processed in MATLAB™ R2014a software using the Image Processing Toolbox to identify and count aphids. In order to evaluate the accuracy of the algorithm, the aphids counted with the sensing system were compared to a count generated manually by a trained expert. The algorithm counting with SONY™ camera images correlated (r2=0.96) very well with manual counts. The misclassification percentage was low for most cameras with different resolutions under high illumination conditions. The results also showed that images captured with an inexpensive regular digital camera gave satisfactory results under high illumination conditions.

Compressed sensing snapshot spectral imaging by a regular digital camera with an added optical diffuser.

We propose a spectral imaging method that allows a regular digital camera to be converted into a snapshot spectral imager by equipping the camera with a dispersive diffuser and with a compressed sensing-based algorithm for digital processing. Results of optical experiments are reported.

Periodic spline-based frames for image restoration

We present a design scheme that generates tight and semi-tightframes in discrete-time periodic signals space originated fromfour-channel perfect reconstruction periodic filter banks. Filter banksare derived from interpolating and quasi-interpolating polynomial and discrete splines. Each filter bank comprises one linear phaselow-pass filter (in most cases interpolating) and one high-passfilter, whose magnitude's response mirrors that of a low-pass filter.These filter banks comprise two band-pass filters. We introduce local discrete vanishing moments (LDVM). When the frame is tight, analysis framelets coincidewith their synthesis counterparts. However, for semi-tight frames,we swap LDVM between synthesis and analysis framelets. The designscheme is generic and it enables us to design framelets with anynumber of LDVM. The computational complexity of the the framelet transforms,which consists of calculating the forward and the inverse FFTs, doesnot depend on the number of LDVM and does depend on the size of the the impulse response fi lters. The designed frames are used for image restorationtasks, which were degraded by blurring, random noise and missingpixels. The images were restored by the application of the SplitBregman Iterations method. The frames performances are evaluated. Apotential application of this methodology is the design of asnapshot hyperspectral imager that is based on a regular digitalcamera. All these imaging applications are described.

Treatment of acne scars using the microneedling and drug delivery technique

Acne vulgaris is one of the most common skin diseases and most often results in scars that are typically associated with aesthetic and psychological problems. To date, there is no standardized treatment for this kind of scarring. Objectives: To evaluate the improvement of distensible type acne scars on the face after treatment with the microneedling technique, followed by the topical application of a gel containing growth factors. Methods: Ten patients with acne scars who were treated from 2012 to 2014 and met the inclusion criteria were selected. All underwent 3 microneedling sessions with intervals of 1 to 2 months, with a 1-year follow up. Pre- and post- procedure photographs were carried out with a regular digital camera, and with a digital camera with a 3D system. Skin biopsies were performed prior to treatment, and 30 days after the last session. Results: Eight patients completed the study. Among these, seven showed a random reduction in the roughness of the scars in the analyzed area, seven showed a decrease in melanin with a homogenization of its distribution across the skin, and seven patients showed an increase in hemoglobin in the area being studied. The appearance of the scars varied among the eight patients. Deep ice-pick type scars did not improve with the procedure. Conclusions: The studied treatment promotes overall improvement in skin texture and a discreet effect on acne scars

Colorimetric disposable paper coated with ZnO@ZnS core-shell nanoparticles for detection of copper ions in aqueous solutions.

In this study, we have proposed a new nanoparticle-containing test paper sensor that could be used as an inexpensive, easy-to-use, portable, and highly selective sensor to detect Cu(2+) ions in aqueous solutions. This disposable paper sensor is based on ZnO@ZnS core-shell nanoparticles. The core-shell nanoparticles were synthesized using a chemical method and then they were used for coating the paper. The synthesis of the ZnO@ZnS core-shell nanoparticles was performed at a temperature as low as 60 °C, and so far this is the lowest temperature for the synthesis of such core-shell nanoparticles. The sensitivity of the paper sensor was investigated for different Cu(2+) ion concentrations in aqueous solutions and the results show a direct linear relation between the Cu(2+) ions concentration and the color intensity of the paper sensor with a visual detection limit as low as 15 μM (∼0.96 ppm). Testing the present paper sensor on real river turbulent water shows a maximum 5% relative error for determining the Cu(2+) ions concentration, which confirms that the presented paper sensor can successfully be used efficiently for detection in complex solutions with high selectivity. Photographs of the paper sensor taken using a regular digital camera were transferred to a computer and analyzed by ImageJ Photoshop software. This finding demonstrates the potential of the present disposable paper sensor for the development of a portable, accurate, and selective heavy metal detection technology.

Using phenological cameras to track the green up in a cerrado savanna and its on-the-ground validation

Plant phenology has gained new importance in the context of global change research, stimulating the development of novel technologies for phenological observations. Regular digital cameras have been effectively used as three-channel imaging sensors, providing measures of leaf color change or phenological shifts in plants. We monitored a species rich Brazilian cerrado savanna to assess the reliability of digital images to detect leaf-changing patterns. Analysis was conducted by extracting color information from selected parts of the image named regions of interest (ROIs). We aimed to answer the following questions: (i) Do digital cameras capture leaf changes in cerrado savanna vegetation? (ii) Can we detect differences in phenological changes among species crowns and the cerrado community? (iii) Is the greening pattern detected for each species by digital camera validated by our on-the-ground leafing phenology (direct observation of tree leaf changes)? We analyzed daily sequences of five images per hour, taken from 6:00 to 18:00h, recorded during the cerrado main leaf flushing season. We defined 24 ROIs in the original digital image, including total or partial regions and crowns of six plant species. Our results indicated that: (i) for the studied period, single plant species ROIs were more sensitive to changes in relative green values than the community ROIs, (ii) three leaf strategies could be depicted from the species' ROI patterns of green color change, and (iii) the greening patterns and leaf functional groups were validated by our on-the-ground phenology. We concluded that digital cameras are reliable tools to monitor high diverse tropical seasonal vegetation and it is sensitive to inter-species differences of leafing patterns.

Automatic Face Classification of Cushing's Syndrome in Women - A Novel Screening Approach

Cushing's syndrome causes considerable harm to the body if left untreated, yet often remains undiagnosed for prolonged periods of time. In this study we aimed to test whether face classification software might help in discriminating patients with Cushing's syndrome from healthy controls. Diagnostic study. Using a regular digital camera, we took frontal and profile pictures of 20 female patients with Cushing's syndrome and 40 sex- and age-matched controls. Semi-automatic analysis of the pictures was performed by comparing texture and geometry within a grid of nodes placed on the pictures. The leave-one-out cross-validation method was employed to classify subjects by the software. The software correctly classified 85.0% of patients and 95.0% of controls, resulting in a total classification accuracy of 91.7%. In this preliminary analysis we found a good classification accuracy of Cushing's syndrome by face classification software. Testing accuracy is comparable to that of currently employed screening tests.

Camera that takes pictures of aircraft and ground vehicle tires can save lives

Damaged tires cause many fatal car accidents that claim lives worldwide. The use of a regular digital camera that can generate JPEG images, so as to become aware of damaged tires, is proposed. The digital camera repeatedly takes pictures of the car’s tires. When there is a drastic change in a particular block of JPEG, the value of many of its frequency coefficients will be high and it will be compressed into many more bits; therefore, if the image is overly large, an embedded computer system will turn on a noticeable light-emitting diode in the car. The driver will be aware of the damaged tire before a severe accident would possibly happen.

Fast measurement of automotive headlamps based on high dynamic range imaging

The headlamp of the automobile is a very important device for the safety of driving in the dark. Therefore, the distribution of the light designed to provide forward and lateral illumination needs to meet the requirements of various regulations. Traditional measurement of the distribution has been based on a point-by-point approach using a goniophotometer. In this paper, an imaging photometer is developed by combining a regular digital camera and a high dynamic range imaging technique to achieve faster and more complete measurement of the entire distribution. The experimental results indicate that errors of the measurements are within 10% of the true values, which is better than the 20% requirements of the industry.

Compressive Light Field Sensing

We propose a novel design for light field image acquisition based on compressive sensing principles. By placing a randomly coded mask at the aperture of a camera, incoherent measurements of the light passing through different parts of the lens are encoded in the captured images. Each captured image is a random linear combination of different angular views of a scene. The encoded images are then used to recover the original light field image via a novel Bayesian reconstruction algorithm. Using the principles of compressive sensing, we show that light field images with a large number of angular views can be recovered from only a few acquisitions. Moreover, the proposed acquisition and recovery method provides light field images with high spatial resolution and signal-to-noise-ratio, and therefore is not affected by limitations common to existing light field camera designs. We present a prototype camera design based on the proposed framework by modifying a regular digital camera. Finally, we demonstrate the effectiveness of the proposed system using experimental results with both synthetic and real images.

Application of Texture Analysis and Kohonen Map for Region Segmentation of Pavement Images for Crack Detection

The first phase of a research study on detecting cracks in pavements is described. For reliable crack detection, various regions in a road image have to be segmented accurately. A procedure based on the texture and color properties of different regions of images is used in conjunction with the Kohonen map, also known as the self-organizing map. Accuracy of 89.7% was obtained with classification based on the Kohonen map of images taken with a regular digital camera and simple lighting setup. Furthermore, a complementary algorithm is described to remove spurious classifications caused by inaccuracies in the trained Kohonen map. With the help of this algorithm, an overall segmentation accuracy of 97.7% is reported. This research is expected to affect other problems in transportation engineering, such as road boundary detection and road marking inspection. The detection of cracks from the segmented regions will be addressed in the future.

Stereovision for 3D Measurements of Fabric Pilling

This paper introduces a 3D imaging system designed for objective evaluation of fabric pilling. The system was aimed at using a pair of regular digital cameras to capture two side-by-side images of a pilling fabric without special lighting, and the robust calibration and stereo-matching algorithms to reconstruct high-fidelity 3D surfaces of fabric. The depth data provides the most relevant information for pilling segmentation and measurements. The outcome of the surface reconstruction is independent of fabric structures, colors and fiber contents. 3D measurements are useful for understanding pilling mechanisms in different abrasive treatments.