Portable Camera Research Articles

Object Identification for Visually Impaired

Objectives: This paper is based on a device that helps blind people to identify a set of objects used in everyday routine thereby enabling them to work independently. Method/Analysis: A new portable camera based method to recognize indoor objects for helping blind people is introduced. A more improvised algorithm called as the Coarse Description Technique has been employed. The coarse description technique can be implemented in two ways: Euclidian distance measurement method and another method that relies on semantic similarity measure modeled by means of Gaussian process estimation. Findings: The techniques used currently perform the recognition task by limiting it to a single predefined class of objects. The proposed concept in this paper utilizes a completely different alternative scheme termed as coarse description. Its main objective is to expand the recognition task to multiple objects and keep the processing period under control at the same time. While the Euclidian distance measurement method evaluates every image based on a matrix created using details regarding the pixels of each image, the Gaussian process estimation method compares images using a number of image attributes. Novelty/Improvement: PIC controller used in the existing system is replaced by a Raspberry Pi board which provides a computation speed twice as fast as the former. Keywords: Coarse Description Technique, Euclidean Distance Measurement, Gaussian Process Estimation, Image Matching, Raspberry Pi

A Multi-Resolution Photogrammetric Framework for Digital Geometric Recording of Large Archeological Sites: Ajloun Castle-Jordan

The generation of reality-based 3D models of archeological sites is the future of representing existing ancient structures. Such approach requires substantial economic and logistical costs which limit this application. In this context, this paper presents the use of photogrammetric workflow, based on Structure from Motion techniques (SfM) to derive 3D metric information from Structure-and-Motion images. The interdisciplinary 3D modeling framework consists of fusion of multi resolution images from both overlapped low-altitude aerial and multi-view terrestrial imagery. The acquisition of aerial photographs survey was based on archived oblique aerial stereo pair photos acquired from the Aerial Photographic Archive for Archaeology in the Middle East (APAAME) project, while terrestrial of close range photos covering the castle walls has been acquired using portable camera. Camera calibration and orientation were carried out by VisualSFM, CMPMVS (Multi-View Reconstruction) and SURE (Photogrammetric Surface Reconstruction from Imagery) software. The resulted cloud points were processed using cloud Compare, MeshLab, Agisoft, and Skethup Softwares. A complete 3D digital geometric recording of the site was accomplished based on dense 3D point clouds with realistic metric accuracy and photorealistic performance to meet all the surveying and archaeological needs. The final Ajloun castle’s digital model geometry was added as a 3D building layer on Google Earth.

High‐performance high dynamic range image generation by inverted local patterns

This study presents an image processing algorithm capable of generating high dynamic range (HDR) images from a single frame. On the basis of liquid crystal display (LCD) backlight theory, the proposed algorithm uses an inverted local pattern approach to adjust the histogram of lighting distribution. To improve processing efficiency, sampled images are classified into three types according to exposure characteristics, which are used to obtain suitable processing factor. The inverting factor is mixed with the original sample to darken the bright areas and brighten the dark areas in the images. Brightness enhancement and auto-gain control are then added to expand the range of the grey levels. Authors’ results demonstrate the efficacy of the proposed HDR algorithm in improving shadow details. In addition, single-pass processing is used to reduce computational complexity, making the algorithm applicable for low-power portable cameras and video recorders.

Calibration of mobile-gantry computed tomography for surgical navigation.

Image-guided interventions that use preoperative 3D computed tomography (CT) models are limited by the preoperative segmentation time 3D image and collection of intraoperative registration data. Intraoperative CT imaging can be ergonomically efficient in a direct navigation system if the imaging device is accurately calibrated. A mobile-gantry CT scanner offers improved patient safety but presents technical challenges beyond those of a conventional scanner. The goal was to calibrate an optoelectronic navigation system to mobile-gantry CT with millimeter-level accuracy. A custom calibration device was designed and manufactured. The calibrator contained optoelectronic markers for navigation reference and radio-opaque markers for CT reference. Calibrations were performed with a ceiling-mounted optoelectronic camera and with a portable camera, and then verified for accuracy. The component fiducial registration errors were extremely small, being 0.36 mm, with standard deviation of 0.16 mm, for the ceiling-mounted camera, and 0.05 mm, with standard deviation of 0.01 mm, for the portable camera. The net target registration error, measured as RMS deviation, was 1.58 mm for the ceiling-mounted camera and 0.73 mm for the portable camera. High-accuracy calibration of the mobile-gantry CT scanner was possible from a single preoperative CT image. A ceiling-mounted optoelectronic camera, which is ergonomically preferable, marginally met the accuracy criteria. The portable camera, which is in widespread use for conventional navigated surgery, had deep sub-millimeter error. This study demonstrates that high accuracy is achievable and offers a system developer options to trade off accuracy and user convenience in direct surgical navigation.

Broadband and Tunable-Focus Flat Lens with Dielectric Metasurface

Metasurface-based flat lens have great potentials for applications in compact and portable cameras. However, the properties of optical metasurfaces are strongly limited by the intrinsic ohmic loss of metal and the fixed working distance. Here, we propose a highly efficient all-dielectric metasurface lens working in near-infrared frequency range. By exploiting silicon nanoblock as meta- atoms, the silicon metasurface produces phase changes covering 0 to 2π and near-unity reflection, inducing the focusing of light over a broad wavelength range. Interestingly, the focal length of such an ultrathin flat lens can be dynamically controlled by incorporating tunable materials such as liquid crystals. By utilizing the phase transition or electrical alignment of liquid crystals, the focal length has been tuned up to 10 %. We believe our research will be important to accelerate the applications of optical metasurfaces.

Use of A Portable Camera for Proximal Soil Sensing with Hyperspectral Image Data

In soil proximal sensing with visible and near-infrared spectroscopy, the currently available hyperspectral snapshot camera technique allows a rapid image data acquisition in a portable mode. This study describes how readings of a hyperspectral camera in the 450–950 nm region could be utilised for estimating soil parameters, which were soil organic carbon (OC), hot-water extractable-C, total nitrogen and clay content; readings were performed in the lab for raw samples without any crushing. As multivariate methods, we used PLSR with full spectra (FS) and also combined with two conceptually different methods of spectral variable selection (CARS, “competitive adaptive reweighted sampling” and IRIV, “iteratively retaining informative variables”). For the accuracy of obtained estimates, it was beneficial to use segmented images instead of image mean spectra, for which we applied a regular decomposing in sub-images all of the same size and k-means clustering. Based on FS-PLSR with image mean spectra, obtained estimates were not useful with RPD values less than 1.50 and R2 values being 0.51 in the best case. With segmented images, improvements were marked for all soil properties; RPD reached values ≥ 1.68 and R2 ≥ 0.66. For all image data and variables, IRIV-PLSR slightly outperformed CARS-PLSR.

Fundus Photography in the 21st Century--A Review of Recent Technological Advances and Their Implications for Worldwide Healthcare.

The introduction of fundus photography has impacted retinal imaging and retinal screening programs significantly. Fundus cameras play a vital role in addressing the cause of preventive blindness. More attention is being turned to developing countries, where infrastructure and access to healthcare are limited. One of the major limitations for tele-ophthalmology is restricted access to the office-based fundus camera. Recent advances in access to telecommunications coupled with introduction of portable cameras and smartphone-based fundus imaging systems have resulted in an exponential surge in available technologies for portable fundus photography. Retinal cameras in the near future would have to cater to these needs by featuring a low-cost, portable design with automated controls and digitalized images with Web-based transfer. In this review, we aim to highlight the advances of fundus photography for retinal screening as well as discuss the advantages, disadvantages, and implications of the various technologies that are currently available.

Study of the Dynamic Image Stabilizer

Most anti-shake technologies can compensate the hand shake when taking a static picture. When people use the camera in the dim environment, the shutter opening time will be extended to increase exposure. However, the hand shake will cause the photos blurry if the shutter opening time was too long. The hand shake problem is even more serious when people doing the dynamic image recording. In the past years, the mobile phones with the digital camera and portable video camera were developed vigorously. Taking pictures and recording dynamic image have become the basic functions of mobile phones since the development of the 3G mobile phone. While the specifications of cameras become high resolution and high magnification optical zoom, the traditional electronic anti-shake technology will not be applied in the digital camera because of the large amount of computing power. It is also difficult to apply the optical anti-shake technology in thin 3C products because the volume of optical anti-shake module is too large. Thus, developing a new anti-shake technology which can be applied in the thin 3C products to enhance the photo and video quality is very important. In this paper, the image processing technologies will be applied to calculate the motion signal. Then, the voluntary and involuntary motion signals will be separated by the signal separation algorithm, and finally the dynamic image will be reconstruction by compensating the involuntary shake of each frame to enhance the quality of the dynamic image.

Portable Camera Based Assistive Pattern Recognition for Visually Challenged Persons

Choosing clothes, food recognition and traffic signal analysis are major challenges for visually impaired persons. The existing automatic clothing pattern recognition is also a challenging research problem due to rotation, scaling, illumination, and especially large intra class pattern variations. This project, a camera based assistive framework is proposed to help blind persons for identification of food pattern, clothe pattern and colors in their daily lives. The existing traffic signal using sensors method is difficult to analysis and many components used. A camera based traffic signal analysis method easy to handle, to provide clear traffic signal analysis and reduce the time delay. The system contains the following major components 1) a camera for capturing clothe, food and traffic signal images, a microphone for speech command input; 2) data capture and analysis to perform command control, recognize clothe patterns, food patterns and traffic signal identification by using a wearable computer and 3) a speaker to provide the name of audio outputs of clothe patterns and colors, food patterns and traffic signal analysis, as well as system status. To handle the large intra class variations, a novel descriptor, Radon Signature is proposed to capture the global directionality of clothe patterns, food patterns and traffic signal analysis. To evaluate the effectiveness of the proposed approach CCNY clothes Pattern dataset is used. Our approach achieves 92.55% recognition to improve the life quality, do not depend others. DOI: 10.17762/ijritcc2321-8169.150329

Online self-supervised learning for dynamic object segmentation

This paper proposes a novel technique for the automatic segmentation of dynamic objects, solely using information from a single uncalibrated moving camera and without the need for manual labeling (or any human intervention, for that matter). Matching pairs of sparse features are extracted from subsequent frames, and the resulting optical flow information is divided into two classes (static or dynamic) using the RANSAC algorithm. This initial classification is then used to incrementally train a Gaussian process (GP) classifier that is then able to segment dynamic objects in new images. The GP hyperparameters are optimized online during navigation, with new data being gradually incorporated into the non-parametric model as it becomes available while redundant data is discarded, to maintain a near-constant computational cost. The result is a vector containing the probability that each pixel in the image belongs to a dynamic object, along with the corresponding uncertainty estimate of this classification. Experiments conducted using different robotic platforms, ranging from modified cars (driving at speeds of up to 50 km/h) to portable cameras (with a full six-degree-of-freedom range of motion), show promising results even in highly unstructured environments with cars, buses and pedestrians as dynamic objects. We also show how it is possible to cluster individual dynamic pixels into different object instances, and then further cluster those into semantically meaningful categories without any prior knowledge of the environment. Finally, we provide visual odometry results that testify to the proposed algorithm’s ability to correctly segment (and then remove) dynamic objects from a scene, and how this translates into a more accurate motion estimate between frames.

The Pune diabetic retinopathy awareness and screening model

Background: Diabetic retinopathy has become a serious public health problem. Aim: To evolve a reliable and scalable model of diabetic retinopathy screening and awareness usable at the national level. Setting and Design: Community-based cross-sectional observational study. Materials and Methods: The model was used in Pune and surrounding districts in 25 locations, between March to November 2014. It involved the local communities to arrange, enrol attendees, and disseminate information about the mission before and after the program. This was done through a women's self-help group Tanishka with over 70,000 volunteer members distributed throughout Maharashtra. Screening was done by telemedicine using an indigenous low-cost portable retinal camera, with a remote reporting capability. All programs were reported by the vernacular press to ensure a force multiplier effect by conveying the message to its entire readership. Results and Conclusion: A total of 25 programs were held and attended by 2,965 persons. One thousand four hundred and eighteen diabetics patients were screened out of which 193 were found to have retinopathy requiring further investigation and treatment. Repeated press coverage over an extended period ensured high reader uptake. Creating awareness and screening were used simultaneously and to complement each other. Local participation, affordable indigenous technology, and awareness through the press were the three pillars of this model. The model was found to be viable, reliable, reproducible, and scalable. It can be expanded to function at a national level.

Efficacy of cost-effective, portable nonmydriatic fundus camera, manufactured in India, to detect retinal pathology in comparison with regular mydriatic fundus camera

Background: Diabetic retinopathy is a major public health problem and causes a huge economic burden. Therefore, a cost-effective screening tool for its detection is warranted. This study analyzes the efficacy of a low-cost, portable, Indian-made, nonmydriatic fundus camera as a tool for mass screening. Objective: To assess the potential to detect retinal pathology by cost-effective, portable, nonmydriatic fundus camera compared with regular dilated fundus imaging system and to assess its utility as a screening tool. Materials and Methods: A cross-sectional study was carried out at Kasturba Medical College, Manipal, Karnataka, India. The study period was from February 2011 to April 2011. Retinal images (n = 451) were captured using nonmydriatic fundus/test camera and regular mydriatic fundus camera. Diagnosis of normal fundus (n = 167), diabetic retinopathy (n = 180), and abnormal cup:disc ratio (n = 104) was made by a senior ophthalmologist, and then, the retinal images were classified by two ophthalmologist who were blinded to each other’s findings. SPSS, version 15, and kappa coefficient were used for statistical analysis. Results: Nonmydriatic camera was noted to have a sensitivity of 88.3% (159/180 images) and 100% in detecting diabetic retinopathy and abnormal cup-to-disc ratio, respectively. Diagnostic accuracy of 91.1% was noted in the detection of diabetic retinopathy with nonmydriatic camera in comparison with the regular camera, with kappa coefficient being 0.82 and p < 0.001. Conclusion: Nonmydriatic fundus camera being cost-effective, quick, convenient, and portable, with high sensitivity and diagnostic accuracy is a useful tool for mass screening of diabetic retinopathy and glaucoma.

Portable Camera Based Assistive Pattern Recognition for Visually Challenged Persons

Portable Camera Based Assistive Pattern Recognition for Visually Challenged Persons

Cameras in the courts: why the prohibition occurred in the UK

At the turn of the twentieth century, the owners of newspapers quickly understood the significance of truly portable cameras when they began to be manufactured. Photographers began to take photographs in courts, mainly for the purposes of publishing images of salacious trials and society gossip from the divorce courts. This article Stephen Mason (Barrister + IALS Associate Research Fellow) sets out why the taking of photographs was prohibited in courts in England &amp; Wales in 1925 and outlines the recent decision by the Minister of Justice to permit the use of cameras in court.

Shake, rattle and roll: bringing a little rock to the IVF laboratory to improve embryo development

Shake, rattle and roll: bringing a little rock to the IVF laboratory to improve embryo development

Hologram synthesis of three-dimensional real objects using portable integral imaging camera

We propose a portable hologram capture system based on integral imaging. An integral imaging camera with an integrated micro lens array captures spatio-angular light ray distribution of the three-dimensional scene under incoherent illumination. The captured light ray distribution is then processed to synthesize corresponding hologram. Experimental results show that the synthesized hologram is optically reconstructed successfully, demonstrating accommodation and motion parallax of the reconstructed three-dimensional scene.

Text extraction from natural scene image: A survey

With the increasing popularity of portable camera devices and embedded visual processing, text extraction from natural scene images has become a key problem that is deemed to change our everyday lives via novel applications such as augmented reality. Text extraction from natural scene images algorithms is generally composed of the following three stages: (i) detection and localization, (ii) text enhancement and segmentation and (iii) optical character recognition (OCR). The problem is challenging in nature due to variations in the font size and color, text alignment, illumination change and reflections. This paper aims to classify and assess the latest algorithms. More specifically, we draw attention to studies on the first two steps in the extraction process, since OCR is a well-studied area where powerful algorithms already exist. This paper offers to the researchers a link to public image database for the algorithm assessment of text extraction from natural scene images.

Importance of Video Technologies in Seizure Identification – Evidence through a Case Report

Epilepsy is characterized by unprovoked repetitive occurrence of seizures, which are the clinical manifestation of an abnormal cerebral discharge. Seizure semiology is widely variable, in some cases being difficult to identify and diagnose. Especially in non-convulsive seizures, a high grade of suspicion is necessary and description of episodes by patients and witness may be bizarre and misleading. Video recording of seizures could be widely available through portable cameras and may help physicians recognize seizures. We present a case of a patient with an eight years history of non-convulsive seizures that was only diagnosed with epilepsy after self recording a seizure on his phone camera. Through this case we would like to alert the medical community for the usefulness of these widespread portable video technologies in the diagnosis of seizure disorders.

고령자 낙상에 의한 응급 상황의 4족 로봇 기반 알리미 시스템 설계 및 구현

본 논문에서는 노인의 낙상에 의한 위급상항을 모니터링 하기 위한 4족 로봇 및 모니터링 시스템을 소개한다. 4족 로봇은 FPGA Board(Field Programmable Gate Array)를 이용한 특정 색을 판별하는 영상처리에 기반하여 자율 이동한다. 노인의 낙상을 감지하기 위해 가슴에 센서노드를 착용하고, 낙상에 의한 응급 상황 시에 4족 로봇이 낙상신호를 관리자에게 전송한다. 관리자는 전송된 영상을 기반으로 4족 로봇을 제어 및 상황판단을 하고, 위급상황이면 119에 신고를 한다. 센서노드만을 사용한 낙상 감지 시스템에서 98.33% 낙상의 Sensitivity와 일상행동 94.375% Specificity가 측정 되었다. 100% 낙상 감지를 못했던 점을 낙상 감지 시스템과 이동형 카메라(로봇)의 결합 알고리즘을 제안 및 실험을 통해 100% 검증 하였다. In this paper, we introduce a quadruped robot-based alarm system for monitoring the emergency situation due to falling in the elderly. Quadruped robot includes the FPGA Board(Field Programmable Gate Array) applying a red-color tracking algorithm. To detect a falling of the elderly, a sensor node is worn on chest and accelerations and angular velocities measured by the sensor node are transferred to quadruped robot, and then the emergency signal is transmitted to manager if a fall is detected. Manager controls the robot and then he judges the situation by monitoring the real-time images transmitted from the robot. If emergency situation is decided by the manager, he calls 119. When the fall detection system using only sensor nodes is used, sensitivity of 100% and specificity of 98.98% were measured. Using the combination of the fall detection system and portable camera (robot), the emergency situation was detected to 100 %.

The Fluorescence Image of Portable System Enhanced by Asynchronous Trigger UV-LED Excitation

Fluorescence is widely used to detect the biochemical effect and some substance containing certain dye. In general, the formation of fluorescent reaction is that an organism or dye, excited by UV light, emits a specific frequency of light; the light is usually a visible or near infrared light. Practically, the fluorescence of object can be excited by continued UV light, but the contrast and sharpness of fluorescence image decrease readily with stray light from the surrounding. In this study, we connect a trigger LED light module to a portable camera system and to perform the fluorescence inspection. When the fluorescent object is excited by asynchronous trigger UV-LED light, the extra intensity of fluorescence can be obtained. In the experiment of security organic dye (BL-ORT), the relative intensity of fluorescence acquired by 30 fps CCD can be increased by more than 11 %. In addition, when the fluorescent dye (chlorine e6) is injected into the tail vein of nude mouse, if its tail excited by the 375nm asynchronous trigger and continuous UV-LED are processed, the average relative intensity is 56.5 % and 49 %, respectively. Therefore, an added relative fluorescence of 15.3 % can be obtained from asynchronous triggering method. Furthermore, the ratio of extra intensity increases with the increase of frame rate of camera.