Standard Camera Images Research Articles

An automated lightweight approach for detecting dead fish in a recirculating aquaculture system

Accurate methods for detecting dead fish are of great significance for fisheries because of their potential to improve production and reduce water pollution. Small-scale fisheries typically apply manual observation, but this approach is labor-intensive and time-consuming, which limits its application on large-scale farms. Advances in computer vision tools have provided the foundation for revolutionary methods of automated identification of individual-animal behavior. However, computer vision systems often suffer from unstable accuracy, low efficiency, and limited detection capability. Thus, the aim of this study was to design a deep learning system, designated “Deadfish-YOLO”, to detect dead fish based solely on standard underwater camera images with no additional hardware. First, eight selected rearing tanks were monitored by a self-developed computer version system. From these tank images, a dataset containing 18,114 frames was built by manual labeling. Next, a lightweight backbone network was generated with YOLOv4 to ensure fast computations, and an attention mechanism was introduced into the model to suppress unimportant features. Finally, the ReLU-memristor-like activation function was adopted to improve neural-network performance. The accuracy and processing speed of Deadfish-YOLO were superior to those of other state-of-the-art single- and two-stage detection models; Deadfish-YOLO ran at 85 frames per second with a mean average precision of 0.946 and an average ratio of 0.924 between intersection and union. These results demonstrate that Deadfish-YOLO may be used to automatically monitor dead fish in real circulating aquaculture systems. In addition, the results of this study should facilitate the wider application of artificial-intelligence-based animal monitoring in aquaculture.

Mind the Exit Pupil Gap: Revisiting the Intrinsics of a Standard Plenoptic Camera.

Among the common applications of plenoptic cameras are depth reconstruction and post-shot refocusing. These require a calibration relating the camera-side light field to that of the scene. Numerous methods with this goal have been developed based on thin lens models for the plenoptic camera's main lens and microlenses. Our work addresses the often-overlooked role of the main lens exit pupil in these models, specifically in the decoding process of standard plenoptic camera (SPC) images. We formally deduce the connection between the refocusing distance and the resampling parameter for the decoded light field and provide an analysis of the errors that arise when the exit pupil is not considered. In addition, previous work is revisited with respect to the exit pupil's role, and all theoretical results are validated through a ray tracing-based simulation. With the public release of the evaluated SPC designs alongside our simulation and experimental data, we aim to contribute to a more accurate and nuanced understanding of plenoptic camera optics.

A Novel Approach for the Shape Characterisation of Non-Melanoma Skin Lesions Using Elliptic Fourier Analyses and Clinical Images.

The early detection of Non-Melanoma Skin Cancer (NMSC) is crucial to achieve the best treatment outcomes. Shape is considered one of the main parameters taken for the detection of some types of skin cancer such as melanoma. For NMSC, the importance of shape as a visual detection parameter is not well-studied. A dataset of 993 standard camera images containing different types of NMSC and benign skin lesions was analysed. For each image, the lesion boundaries were extracted. After an alignment and scaling, Elliptic Fourier Analysis (EFA) coefficients were calculated for the boundary of each lesion. The asymmetry of lesions was also calculated. Then, multivariate statistics were employed for dimensionality reduction and finally computational learning classification was employed to evaluate the separability of the classes. The separation between malignant and benign samples was successful in most cases. The best-performing approach was the combination of EFA coefficients and asymmetry. The combination of EFA and asymmetry resulted in a balanced accuracy of 0.786 and an Area Under Curve of 0.735. The combination of EFA and asymmetry for lesion classification resulted in notable success rates when distinguishing between benign and malignant lesions. In light of these results, skin lesions’ shape should be integrated as a fundamental part of future detection techniques in clinical screening.

Aerial image resolution measurement based on the slanted knife edge method.

Image resolution is one of the most important performance specifications of aerial display techniques. However, there is no standard method for evaluating the aerial image resolution. In this paper, we propose a method for measuring the modulation transfer function (MTF) of an aerial imaging system based on the slanted knife edge method. We hypothesize that aerial images have a different blur function from standard camera images. In order to explore this, we simulate blurred slanted knife edge images by convolving two types of blur functions. Furthermore, the MTF curves of the aerial image formed using different retro-reflectors are compared using the proposed method.

White-light solar corona structure observed by naked eye and processed images

ABSTRACT Light and dark adaptation and luminance contrast enhancement are well-known characteristics of human vision that allow us to observe a wide range of light intensity not fully captured in standard camera images. The naked-eye observations of total eclipses, some recorded with spectacular detail in artists’ paintings, reveal structure that is consistent with images obtained by telescopes equipped with recording media. The actual shape of the corona during a total eclipse depends not only on the phase of the solar cycle but, as can be simply demonstrated, also on the day-to-day variability and spatial distribution of coronal intensity that is determined by solar surface magnetic fields, including the locations of coronal holes that are the sources of high-speed solar wind causing geomagnetic storms. The latter were very similar for the eclipses in 1932, 1994, and 2017, which is the main reason why the naked-eye observations, as well as the processed images (1994 and 2017), of the white-light corona displayed very similar shapes. White-light corona image processing is a useful technique to enhance the contrast to observe fine-scale structure that is consistent with the physics of the solar atmosphere shaped by the magnetic field drawn out into the interplanetary space by solar wind.

A Novel Thermochromic Liquid Crystal Fabric Design for the Early Detection of High-Risk Foot Complications

We developed a prototype of a novel thermochromic liquid crystal (TLC)–coated fabric with an extended temperature range and enhanced sensitivity. By incorporating color and pattern recognition into the fabric, rapid determination of the underlying pedal temperature is facilitated. The purpose of this study was to evaluate the accuracy of the TLC fabric as a potential diagnostic aid for identifying complications in the high-risk foot. The hands of 100 individuals were used to compare the mean maximum temperatures indicated by the fabric versus standard thermal camera images. Findings were statistically analyzed using a paired <italic>t</italic> test, with significance defined as <italic>P</italic> < .05. Except for the tip of the thumb and regions in the palm, there were no statistically significant differences between mean maximum temperatures measured with the thermal camera and those detected with the TLC fabric. Minor differences were relatively consistent in all nine regions of the hand and were not considered to be clinically significant. Using direct visual analysis, we demonstrated that a novel TLC fabric could accurately map temperatures in the palmar surface of the hand. The findings support the continued development of a temperature-sensitive sock that can be used in the home to monitor for temperature changes that may indicate the onset of complications in the high-risk foot.

High-level intuitive features (HLIFs) for intuitive skin lesion description.

A set of high-level intuitive features (HLIFs) is proposed to quantitatively describe melanoma in standard camera images. Melanoma is the deadliest form of skin cancer. With rising incidence rates and subjectivity in current clinical detection methods, there is a need for melanoma decision support systems. Feature extraction is a critical step in melanoma decision support systems. Existing feature sets for analyzing standard camera images are comprised of low-level features, which exist in high-dimensional feature spaces and limit the system's ability to convey intuitive diagnostic rationale. The proposed HLIFs were designed to model the ABCD criteria commonly used by dermatologists such that each HLIF represents a human-observable characteristic. As such, intuitive diagnostic rationale can be conveyed to the user. Experimental results show that concatenating the proposed HLIFs with a full low-level feature set increased classification accuracy, and that HLIFs were able to separate the data better than low-level features with statistical significance. An example of a graphical interface for providing intuitive rationale is given.

Physiological characterization of skin lesion using non-linear random forest regression model.

The current diagnostic technique for melanoma solely relies on the surface level of skin and under-skin information is neglected. Since physiological features of skin such as melanin are closely related to development of melanoma, the non-linear physiological feature extraction model based on random forest regression is proposed. The proposed model characterizes the concentration of eumelanin and pheomelanin from standard camera images or dermoscopic images, which are conventionally used for diagnosis of melanoma. For the validation, the phantom study and the separability test using clinical images were conducted and compared against the state-of-the art non-linear and linear feature extraction models. The results showed that the proposed model outperformed other comparing models in phantom and clinical experiments. Promising results show that the quantitative characterization of skin features, which is provided by the proposed method, can allow dermatologists and clinicians to make a more accurate and improved diagnosis of melanoma.

A coarse-to-fine approach for segmenting melanocytic skin lesions in standard camera images

Melanoma is a type of malignant melanocytic skin lesion, and it is among the most life threatening existing cancers if not treated at an early stage. Computer-aided prescreening systems for melanocytic skin lesions is a recent trend to detect malignant melanocytic skin lesions in their early stages, and lesion segmentation is an important initial processing step. A good definition of the lesion area and its border is very important for discriminating between benign and malignant cases. In this paper, we propose to segment melanocytic skin lesions using a sequence of steps. We start by pre-segmenting the skin lesion, creating a new image representation (channel) where the lesion features are more evident. This new channel is thresholded, and the lesion border pre-detection is refined using an active-contours algorithm followed by morphological operations. Our experimental results based on a publicly available dataset suggest that our method potentially can be more accurate than comparable state-of-the-art methods proposed in literature.

A two-stage approach for discriminating melanocytic skin lesions using standard cameras

In this paper, we propose a novel approach to discriminate malignant melanomas and benign atypical nevi, since both types of melanocytic skin lesions have very similar characteristics. Recent studies involving the non-invasive diagnosis of melanoma indicate that the concentrations of the two main classes of melanin present in the human skin, eumelanin and pheomelanin, can potentially be used in the computation of relevant features to differentiate these lesions. So, we describe how these features can be estimated using only standard camera images. Moreover, we demonstrate that using these features in conjunction with features based on the well known ABCD rule, it is possible to achieve 100% of sensitivity and more than 99% accuracy in melanocytic skin lesion discrimination, which is a highly desirable characteristic in a prescreening system.

Large-scale, dense city reconstruction from user-contributed photos

The goal of our work is to incrementally reconstruct terrestrial city models from standard digital camera images contributed by multiple users. Hence, the Wiki principle well known from textual knowledge databases is transferred to 3D computer vision. Many state-of-the-art computer vision methods must be applied and modified according to the changing requirements. We describe the utilized 3D vision methods in detail and show results obtained from the current image databases Vienna and Graz acquired by in-house participants. The reconstructions are all maintained in a global database and comprise thousands of photographs.

Compact large FoV gamma camera for breast molecular imaging

The very low sensitivity of scintimammography for tumours under 1 cm in diameter, with current nuclear medicine cameras, is the major limitation in recommending this test modality for screening purposes. To improve this diagnostic technique,a new concept of scintillation gamma camera, which fits the best requirements for functional breast imaging has been developed under “Integrated Mammographic Imaging” (IMI) project. This camera consists of a large detection head (6″×7″),very compact sized and with light weight to be easily positioned in the same X-ray geometry. The detection head consists of matrix of 42 photodetector Hamamatsu 1 in 2 square H8520-C12 PSPMTs, which are closely packed and coupled to a NaI(Tl) scintillating array, with individual crystal pixel 2×2×6 mm 3 size. Large FoV camera shows a very good pixel identification in the detection dead zones between tubes allowing an accurate LUT correction of the final image reconstruction. Electronic read-out was especially designed to optimize the intrinsic spatial resolution and camera compactness. With respect to Anger camera, the overall spatial resolution is improved up to 40% while the overall energy resolution values is ∼16% at 140 keV. Large FoV dedicated camera was characterized and tested by phantom studies; and clinical trials are currently performed. For all patients, compression views have been acquiring for both breasts in craniocaudal projections, and are compared with standard gamma camera images.

High-Precision Range Estimation from an Omnidirectional Stereo System.

This paper presents the estimation of depth based on the cylindrical re-projection of images captured by a stereo setup of ODV (OmniDirectional Vision). In general, images obtained by such a device have relatively low spatial resolution and have some aberration in comparison to standard camera images and thus, considerable range estimation errors are caused. We propose a stereo setup of ODV, which features two mirrors with the original curvature to minimize blurring influence. We also propose an edge-based intensity interpolation method to improve the spatial resolution of the developed image. The bidirectional subpixel matching procedure and the discontinuity compensation algorithm are also presented to improve the quality of the range estimation. The experimental result reveals that the proposed ODSV (OmniDirectional Stereo Vision system) can successfully contribute to reduce disparity error and has subpixel range estimation accuracy even in the cluttered outdoor environment.

Special Characteristics and Potential of Single Photon Emission Computed Tomography in the Brain

Single photon emission tomographic techniques for evaluation of the brain have as their major advantage the ability to employ readily available radionuclides, such as technetium-99m. With present radiopharmaceuticals, single photon emmision tomography of the brain primarily provides morphological information that may be complimentary to standard gamma camera images. Particular areas of assistance have included detection of basal lesions, delineation of multiplicity of lesions, definition of medial extent of abnormalities, clear separation of skull and intracranial abnormalities, and perhaps improved lesion characterization. Overall, however, the reported improvement in sensitivity has been relatively small. To optimally utilize the tomographic and quantiative capabilities of single emission tomography, new classes of radiopharmaceuticals must be developed that can penetrate the blood-brain barrier and provide information on CNS function and pathophysiology. If such radiopharmaceuticals can be labeled with single emission radionuclides, this technique has the potential to provide critically important information. The ultimate outcome of single emission tomographic techniques for the study of the brain may depend on radiopharmaceutical advances.

Cardiac emission tomography in patients using 201Thallium. A new technique for perfusion scintigraphy

The distribution of 201thallium (Tl) in the myocardium has been studied by the new technique of emission tomography, and compared with standard gamma camera images in 5 patients. Tomographic imaging was carried out using a dual-detector scanner operated under the single-photon technique. Initial results have been promising, with visualisation of resting perfusion defects in patients with recent infarction and those with ventricular aneurysms. Emission tomography has also been performed at exercise, and has shown tracer deficits in the distribution of significant coronary stenoses. This new approach to myocardial perfusion scintigraphy may lead to improved sensitivity for detecting apical and inferior wall abnormalities by providing depth information not available from a conventional two-dimensional image.