Camera Module Research Articles

Open-source all-in-one LabToGo Office Chromatography

Print and media technologies were used uncommonly in the field of chromatography and explored in application to create a miniaturized all-in-one LabToGo system. This novel research field termed Office Chromatography (OC) uses additive manufacturing in terms of 3D printing of operational parts as well as open-source hard- and software. The OCLab2 presented here has been considerably extended in its functionalities. For inkjet printing of solutions, a newly designed printhead was manufactured controlled by a self-constructed ink-jet board, allowing to check the nozzles’ resistance heating circuit. Plate heating was newly integrated, especially favorable for the demonstrated application of higher volumes of aqueous samples. The UV/Vis/FLD plate images were captured by a Raspberry Pi V2 camera module under illumination by novel light emitting diodes (LEDs) for highly selective RGBW color (Vis), UVC 278-nm (UV) and UVA 366-nm (FLD) detection, installed in a newly created miniature cabinet to protect from extraneous light. The spectral separation of differently colored food dyes was achieved by the fully addressable driver controlled RGBW LEDs. The software was newly written in R to speed-up the processes, supported by the new Raspberry Pi 4B computer with 4 GB RAM. The analysis of Stevia leaves for steviol glycosides yielded results comparable to the status quo. Different water samples were analyzed for bioactive compounds. Thereby, compounds of general cytotoxicity were effect-directed detected by bioluminescent A. fischeri bacteria. It allowed the bioanalytical screening for potential risks in tap water, surface waters, rain water, landfill leachates and biogas slurries.

Continuous digital zooming using generative adversarial networks for dual camera system

This paper presents a generative adversarial network (GAN) with patch match algorithm to realize a high-quality digital zooming using two camera modules with different focal lengths. In dual camera system, shorter focal length module produces the wide-view image with the low resolution. On the other hand, the longer focal length module produces the tele-view image via optical zooming. The long-focal image contains more details than short-focal image and can be used to guide short-focal image to reconstruct high frequency part. Firstly, a feature extraction block (FEB) is advanced to extract feature of long-focal image and short focal-image to reconstruct a wide-view image with different resolutions. Next, a patch match algorithm is integrated into convolution neural networks (CNN) to fuse information of long-focal with short-focal image and generate a new fused image. Finally, the fused image and short-focal image are merged with a feature fusion block (FFB) to predict high-resolution images. In addition, generative adversarial networks are used for filtering information integrated by previous network and output the zoomed image. Extensive experiments on benchmark datasets show that our algorithm achieves favorable performance against state-of-the-art methods.

Automated laryngeal mass detection algorithm for home-based self-screening test based on convolutional neural network

BackgroundEarly detection of laryngeal masses without periodic visits to hospitals is essential for improving the possibility of full recovery and the long-term survival ratio after prompt treatment, as well as reducing the risk of clinical infection.ResultsWe first propose a convolutional neural network model for automated laryngeal mass detection based on diagnostic images captured at hospitals. Thereafter, we propose a pilot system, composed of an embedded controller, a camera module, and an LCD display, that can be utilized for a home-based self-screening test. In terms of evaluating the model’s performance, the experimental results indicated a final validation loss of 0.9152 and a F1-score of 0.8371 before post-processing. Additionally, the F1-score of the original computer algorithm with respect to 100 randomly selected color-printed test images was 0.8534 after post-processing while that of the embedded pilot system was 0.7672.ConclusionsThe proposed technique is expected to increase the ratio of early detection of laryngeal masses without the risk of clinical infection spread, which could help improve convenience and ensure safety of individuals, patients, and medical staff.

GNSS Localization in Constraint Environment by Image Fusing Techniques

Satellite localization often suffers in terms of accuracy due to various reasons. One possible source of errors is represented by the lack of means to eliminate Non-Line-of-Sight satellite-related data. We propose here a method for fusing existing data with new information, extracted by using roof-mounted cameras and adequate image processing algorithms. The roof-mounted camera is used to robustly segment the sky regions. The localization approach can benefit from this new information as it offers a way of excluding the Non-Line-of-Sight satellites. The output of the camera module is a probability map. One can easily decide which satellites should not be used for localization, by manipulating this probability map. Our approach is validated by extensive tests, which demonstrate the improvement of the localization itself (Horizontal Positioning Error reduction) and a moderate degradation of Horizontal Protection Level due to the Dilution of Precision phenomenon, which appears as a consequence of the reduction of the satellites’ number used for localization.

An Illegal Dumping Detection System Based on Image Processing in OpenALPR

Tipping or depositing large waste onto land using unauthorized and unlicensed methods are considered as illegal dumping. The increasing rate of illegal dumping becomes a crucial nation issue because this activity causes negative impacts to social, economy and environment. Thus, study on detecting the dumping activities is conducted to control the illegal dumping activities in Malaysia. Raspberry Pi with Python language is used as the microprocessor and a Raspberry Pi camera module with a microwave radar sensor are interfaced to it to capture the image of any vehicles entering the illegal dumping site. The image is captured to recognize the license plate of the vehicle. The method in this study is by using Open Automatic License Plate Recognition (ALPR), Open Computer Vision (CV) libraries and Optical Character Recognition (OCR) to detect the character of the plate registration number. The outcome of the study consists of recognition of Malaysia vehicles’ plate number and the automatic real time email notification on the illegal dumping case. The detection system can be used for case monitoring since the plate number recognition is done in real time. The system can be upgraded to ensure its sustainability in the harsh and isolated environment.

A low-cost assistive wheelchair for handicapped & elderly people

In this paper, a mixed control wheelchair (MCW) is presented to overcome problem related to movement and user command for elderly and paralyzed people. The MCW comprises of five individual control blocks, which are fed at the main control unit to provide appropriate control actions. The main feature of this assistive device is that it can navigate by following the eyesight of the user. The proposed MCW can also be controlled using either joystick or voice command or finger movement or through mobile app or a combination of all. This system uses multiple sensor networks to measure the terrain condition, users command and translate it into control action. The proposed control system runs on a Raspberry Pi, which can able to take a proper turn as well as capable to control forward or backward motion. Raspberry Pi, camera module and sensors networks, etc. were all connected into the android mobile system, shortening the physical distance between the disabled person end and the supervisor end and serial communication was used. Multiple-Layer system architecture with outstanding control functions was constructed that uses android mobile interfacing to realize the automatic control and capture videos of the room remotely. It is shown that the users can carry out all essential tasks with the proposed MCW, almost as fast as with the traditional controller. The smart wheelchair can assist elderly people and also improve their quality of life.

Internet of Things (IOT) Enabled Bot For Home Security

This is a savvy observation robot that performs face acknowledgment, controlled by means of an Android application for analyzing unapproved passage in its region. The robot is fit for identifying people progressively situations. The movement pattern of the robot is ordered in various errands: Object Detection, Face Detection, Face Recognition, age of ready signs to the client. The robot recognizes the human face dependent on Haar Cascade Algorithm utilizing a camera module interfaced with Arduino uno. The framework is presented to various facial pictures of individuals from various points and foundation conditions. This structures the data set to prepare the framework which helps in facial acknowledgment. In this way, when the robot identifies a human face, it starts the calculation for acknowledgment of face which utilizes Local Binary Pattern (LBP) approach. As indicated by pictures in the dataset, the robot decides if the human recognized is Known or not. In the event of a match with the dataset, the client gets a message through the GSM module on his/her cell phone. If there should be an occurrence of a crisscross, a danger or an alarm message is gotten by the client. The movement of the robot is constrained by the android application through Bluetooth.

AUTOMOTIVE COLLISION AVOIDANCE SYSTEM (ACAS) APPLICATION

Automotive collision avoidance system is a system that avoid collision when danger occur. It is also very helpful in order to alert the drivers and passengers. The system also reacts to danger automatically, faster, and more efficient. The system is implemented on a remote control car. The remote control car can automatically brake when the difference between front ultrasonic sensor and obstacle is less than 35cm. While the system applies automatic braking system a red LED will light on. Furthermore, the system is also surrounded with another 3 ultrasonics which is on both sides and at the back of the prototype. In this project, this system is using 2 controllers which is Raspberry Pi 4B and Arduino Uno. A camera module is connected to Rasberry Pi which detects the corresponding object. Next, the ultrasonic sensor is used to detect distance and send the reading to Arduino Uno to calculate distance. LCD is used to display the calculated distance. This system also uses dc motor to control the movement of the remote control car through the Arduino Uno controller LED’s and a buzzer is used as alerting devices for the prototype.

Preview the Products on Display at Display Week 2021

Preview the Products on Display at Display Week 2021

Care-giver alerting for bedridden patients using hand gesture recognition system

Hand gestures are most intrinsic way of non-verbal communication. It has been difficult task for hospitals to remove the miscommunication between patients and the healthcare providers, when patients ask for help in emergency or in need. In healthcare centers like hospitals, some systems are having complicated device installation which are expensive and quite hard cumbersome. Human Computer Interaction plays a predominant role in Hand Gesture recognition (HCI). Human Computer Interaction made easy to communicate between human and machine which grabs good attention now a days. An alerting system makes a better alarm model which notifies care-givers when patients require assistance by giving defined hand gestures. The study is related to hand gesture based alerting system which uses camera module to capture the hand images. The system uses background subtraction, image recognition and speech conversion to notify the healthcare providers. It can be useful in hospitals, rehabilitation centers, or assisted living areas, where health care providers can take care of their patients more attentively. With this alerting system it increases the operational efficiency, responsiveness, patient’s and other stakeholders’ satisfaction. For recognized hand gesture text and voice is obtained as output which alerts the care-giver to help the bed-ridden patients.

Design and characterization of a thin linear ultrasonic motor for miniature focus systems

We present a miniature linear piezoelectric ultrasonic motor with a thin and hollow design, which can serve as an essential component of autofocusing features in next-generation camera modules. It consists of a thin square stator with a hole and an elastic cylindrical slider with a slit. The motor design, in which the slider inserted into the stator hole expands outward, enables a hollow structure for centering a lens and an optimal preload for enhancing the motor thrust force. In this study, we model the relationship between the dimensions and the preload statically to quantify the preload value and clarify the design methodology of the motor. After optimizing the preload empirically, we evaluate the fundamental characteristics experimentally. The stator with a side length of 4.5 mm and a thickness of less than 1 mm provides a thrust force of 12.9 mN that leads to a quick response, which is a requirement of autofocusing. Finally, the motor drive system with visual feedback control is used to demonstrate the positioning of an actual lens group in front of an image sensor to obtain clearer images.

Secondary Particle Interactions in a Compton Camera Designed for in vivo Range Verification of Proton Therapy.

The purpose of this study was to determine the types, proportions, and energies of secondary particle interactions in a Compton camera (CC) during the delivery of clinical proton beams. The delivery of clinical proton pencil beams ranging from 70 to 200 MeV incident on a water phantom was simulated using Geant4 software (version 10.4). The simulation included a CC similar to the configuration of a Polaris J3 CC designed to image prompt gammas (PGs) emitted during proton beam irradiation for the purpose of in vivo range verification. The interaction positions and energies of secondary particles in each CC detector module were scored. For a 150-MeV proton beam, a total of 156,688(575) secondary particles per 108 protons, primarily composed of gamma rays (46.31%), neutrons (41.37%), and electrons (8.88%), were found to reach the camera modules, and 79.37% of these particles interacted with the modules. Strategies for using CCs for proton range verification should include methods of reducing the large neutron backgrounds and low-energy non-PG radiation. The proportions of interaction types by module from this study may provide information useful for background suppression.

Design of an Intelligent Inspection Robot for Underwater Pipelines

This paper will introduce the design of an intelligent inspection robot for underwater pipelines. The whole device is divided into detection module, control module, drive module and housing. Among them, the detection module is the camera and the head, the control module is mainly the Raspberry Pi motherboard, the drive module includes the battery, motor, motor driver. The device through the camera module feedback to the Raspberry Pi to make decisions, and this decision through the IO port output, and then through the motor drive module to drive the motor, the motor to make speed and direction of adjustment. This device is proposed to use stepper motor for robot movement method.

A smart wearable device based on internet of things for the safety of children in online transportation

The world needs to pay attention to children who often become victims of violence and cannot escape social problems. Various safety devices that are commonly known as smart wearable devices have been created, but they still have many shortcomings. Thus, in this research a safety device that can be held by children is designed and is equipped with a button that can be pressed, then it will automatically send the location and photo of the scene to the parent's cellphone via the telegram application. It uses the Raspberry Pi Zero W controller, the GNSS HMC5983 SAW LNA GPS Module to determine the location, and the 5MP Raspberry Pi Zero Camera Module to capture the incident. Based on the results, the average time needed to share locations is 0.91 seconds, and the average time needed to capture is 11.57 seconds, if the device and receiving cellphone use the same network. Additionally, the average time needed to share locations is 0.96 seconds, and the average time needed to capture is 12.09 seconds, if the device and receiving cellphone use a different network. Both conditions have 97.5% location accuracy rate and 100% photo accuracy rate.

Automated Attendance System and Voice Assistance using Face Recognition

In this work we propose a Live Attendance Marking System for institutional purpose. This system will enable the department to mark the attendance of students automatically by recognizing their faces. The system is based on the face detection and recognition algorithms and automatically recognizes a student whenever he/she comes across the camera module. Further after the recognition, it automatically updates his/her attendance in the Cloud web server database. The basic architecture and all the algorithms used in the model are described in the paper elaborately. Moreover in order to evaluate and enhance the performance of the system many of the filter functions are used which provide the capability to capture and recognize the images even in dull and low light places. This project also suggests the technique to ensure that a student can mark the attendance only once in a day. The live attendance system is much more efficient to traditional attendance systems both in saving time and in maintaining the database.

RASPBERRY PI SEBAGAI PEMANTAU RUANG LABORATORIUM MENGGUNAKAN METODE PEREKAMAN TERJADWAL BERBASIS DATABASE


 
 
 Practicum activities in higher education especially in State Polytechnic of Malang are generally carried out in a laboratory and based on a predetermined schedule. In the practicum activities are usually used equipment and practical materials borrowed by students from cabinets or warehouses for storage of tools and materials. In addition, in the laboratory where the practicum is carried out there are equipment and personal belongings belonging to students or teachers. From the experience that has happened, some campus-owned lab equipment and materials have been damaged and lost, or the personal property of students or teachers who have been left behind and even lost. Monitoring and recording using ordinary cameras has a disadvantage, that is, we cannot adjust the recording schedule that changes every day based on the space usage schedule. And record data is still one part or not grouped based on space usage schedule. Therefore, it is necessary to make a system that can monitor and record the process of laboratory practicum activities based on space usage schedule. In this study a system will be made using the embeded Raspberry Pi system and a camera module with MySQL as the database, this system is designed and created so that it can be used to record the laboratory practicum activities based on the space usage schedule in the database
 
 

Optimization Shortest One-Way Path for Energy Saving Auto Robot Collecting Floating Garbage using Fast Approximate Nearest Neighbor Search

Floating garbage is a global problem that needs to be cleared and disposed of from the sea and rivers or canals. Mostly the floating plastic garbage directly affects the ecology and the aquatic animals. This paper proposes to develop a low-cost auto robot from waste materials in the household, school, or agriculture, then combines with the Internet of Things technology and focusing on the power energy saving with the highest accuracy in operation of floating garbage collection. ESP32 development kit board is the primary controller with a camera module and ultrasonic sensor for detecting the floating garbage while moving on the water’s surface in the boundary of the specified area, including the small canal, rectangle area, and no rectangle area. The mixed mode is a new method to define the shortest one-way path using a fast approximate nearest neighbor search for the auto robot to detect and collect the floating garbage on the water surface. It was combined between the stationary and the cover model. The mixed mode can eliminate the blind spot area that occurs when using the stationary mode and cover mode. As a result, the auto robot system’s accuracy in mixed mode is 98.3%. It was found that the development of the shortest one-way path for the auto robot collecting floating garbage by mixed mode provides the highest efficiency in detecting floating garbage and also helps to save overall costs, and the resource consumption is nearly half of cover mode consumption.

Robotic Search and Rescue using Human Detection System

In this Technological advancement period, advanced construction improvements lead the formation of skyscrapers and homes which expanded the dangers of losing life because of natural and manmade catastrophes. In this system, we are proposing a radio-controlled bot that can identify live human beings from which are in the inaccessible region. Python libraries are used in Raspberry Pi microcontroller having Camera module to catch pictures of objects around it. This paper discusses about the mentioned system. The project takes live image samples and sends it to a network where this images can be accessed through a device. This images can be used for human detection. PIR sensor is used for the detection of human being trapped under debris. Whenever a human is detected the bot will send GPS co-ordinates to the device.

Voice Controlled Personal Assistive Bot with Object Detection

Currently innovation has made our lives simpler for individuals. Be that as it may, from this innovation, certain gatherings of individuals need more assistance and backing for old or handicap individuals. This innovation can make a method of having a typical life. Thus, we zeroed in on the idea of an individual colleague robot. The fundamental objectisto supply helptodebilitated people.ThisPerson alassistive Bot help to decrease the manual endeavors being put by people in their everyday errands. The intention is to execute a specialized work that is voice controlling one which can act as a PA that can performvarious errands or administrations for a person.This is uncommonly intended for this group of people asits primary reason for existing is to supply help to relate senior or debilitated individual. The human voice order is given to the mechanical right hand distantly,by utilizing a voice order.The automaton will perform different movements: Forward, Backward, Right, Left and start/stop activities. The robot can likewise peruse and perceive the letter sets and text and the words which are said by the person will check from the google dictionary and printasatext.The capability of the robotisto detect the objects and relocate the m from one place to another and includes the face recognition. So, our main ideology is to create a personal assistance bot, which is capable of handling small objects. We are planning to make the bot consisting of four wheels and an arm placed on top. Using Raspberry Pi, we are communicating the sensors and motors throughour voice commands. Smart assistants like Google for android,Sir ifor Apple,Corton a for Microsoft,the seassistive gives us a platform to communicate to a bot. Asweare programming on Python, Amodule name Pyaudio will helpto communicate with a bot and having the extra feature like ‘Speechto Text’.And we would like to add an extra feature like object and person detection. A Camera module will be installed for capturing video and recognize the Humans and objects carried out with Machine Learning Algorithm

Rancang Bangun Sistem Deteksi Kecepatan Kendaraan di Wilayah Zona Selamat Sekolah (ZoSS) Berbasis Mini PC

This study aims to create a system to detect vehicle speed in the School Safe Zone area using Mini PC based with Computer Vision technology and Image Processing techniques. This research, was hoped for the drivers will more discipline in driving, so can create safe and comfortable traffic in the School Safe Zone area. This system was made using a camera module to take video of the track, Raspberry Pi was used as the main device for detection and speed calculation. Every vehicle which crossed the zone would be detected and tracked to follow every vehicle movement, then was conducted a process of saving the center point of the vehicle object based on the initial detection line. Finally, calculated the vehicle speed based on the distance and time the vehicle moved on the frame which was set based on the detection line. The results of the vehicle speed would be displayed on the LCD and the output was in the form of a sound from the speaker as a warning for drivers whose vehicle speed exceeds 25 km / hour. Based on results of this research, the system was capable for work well in detecting and getting the speed results of passing vehicles. However, for direct implementation the devices in this system are inadequate for video processing, so that the response time and accuracy level was obtained by the system did not match for actual conditions.