Estimasi Jarak Menggunakan Sensor Kinect

2017

This paper describes method for fall detection, because fall is a serious problem and often resulting to injury, which can endanger the safety of the person. Therefore, falling detection is crucially needed. The device that being used is Kinect, which also could be used to detect people. The detection is using the help of Microsoft Kinect SDK. Kinect can detect a person in front of it and processing it to create a skeleton of the person. The method which being used is to get a set of data on the position of the person. Next, the rate of change in position would be calculated with the available formulae. The data obtained would be selected, in order to distinguish the activities undertaken. When fall is detected, the application can provide the alert.

AVITEC

The limited ground marshall, yellow line and others at an airport will affect when parking aircraft. Aviation technology has provided solutions, among others, by attaching to aircraft equipment known as the Visual Docking Guidance System (VDGS), is a tool provided by the airport to help a pilot park his plane without the help of a marshaller to direct the movement of planes to the correct parking. However, not all airports are equipped with sophisticated equipment. So this research aims to create a system that can make it easier for pilots to park aircraft while in Apron. To overcome this problem, a VDGS tool was designed which was designed using a TF Mini Lidar sensor and programmed for aircraft parking systems at pioneering airports. This tool is able to provide information on the distance of the plane as far as 12 meters given a condition that the aircraft will display identification of guidance or collision prevention that will STOP if the aircraft is at a distance of 1-3 meter...

ComTech: Computer, Mathematics and Engineering Applications, 2010

Measuring distance from an object can be conducted in a variety of ways, including by making use of distance measuring sensors such as ultrasonic sensors, or using the approach based vision system. This last mode has advantages in terms of flexibility, namely a monitored object has relatively no restrictions characteristic of the materials used at the same time it also has its own difficulties associated with object orientation and state of the room where the object is located. To overcome this problem, so this study examines the possibility of using stereo vision to measure the distance to an object. The system was developed starting from image extraction, information extraction characteristics of the objects contained in the image and visual distance measurement process with 2 separate cameras placed in a distance of 70 cm. The measurement object can be in the range of 50 cm-130 cm with a percentage error of 5:53%. Lighting conditions (homogeneity and intensity) has a great influence on the accuracy of the measurement results.

ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika

ABSTRAKKesalahan GPS (Global Positioning System) dalam menentukan titik koordinat dipengaruhi faktor terhalang oleh bangunan, kondisi cuaca, dan hal lain yang dapat mengurangi akurasi dari GPS. Penelitian ini, digunakan tapis Kalman untuk meminimalisir kesalahan pada alat GPS tipe BN-220 ketika menentukan jarak. Tapis Kalman dirancang dengan dua tahapan yaitu proses prediksi dan koreksi. Pada tahap prediksi, data mentah dari koordinat akan diihitung varian kesalahannya dengan mengatur matriks Q. Kemudian, pada tahap koreksi dilakukan perbaikan dengan menentukan penguatan Kalman berdasarkan matriks R dan hasilnya digunakan untuk mengestimasi data keluaran. Berdasarkan pengujian pada delapan titik uji, diperoleh bahwa penggunaan tapis Kalman menghasilkan rata-rata selisih kesalahan sekitar 5,27% terhadap Google Maps jika dibandingkan dengan tanpa tapis Kalman sebesar 7,56%.Kata kunci: GPS BN-220, tapis Kalman, Haversine, Google Maps ABSTRACTGPS (Global Positioning System) error in det...

Currently, determining the exact position and orientation in a technical system has an important role, especially in terms of control on a navigation system. Of the instruments used in navigation systems is the Inertial Measurement Unit (IMU). The IMU consists of a combination of the acceleration sensor (accelerometer) and the angular sensor (gyroscope) to track the whereabouts and movement of an object. In this final step is to design and manufacture of gyroscope and accelerometer sensors to determine angles and distances based on ATmega32 microcontroller to detect the rotation angle and position of objects. The data is obtained from the integral point of the gyroscope output signal in the form of angular velocity and accelerometer output in the form of the acceleration signal. Data from both these sensors are then displayed via computer with the program through a wireless RF c # YS-1020UA. Based on the results of research conducted on all three axis gyroscope axis to clockwise rotation angle value obtained with the smallest error in the roll axis of 0.55 % and for anticlockwise rotation angle value obtained with the smallest error in the yaw axis of 0.39 %. The result of the best distance with the smallest error is on the y axis with an error of 1.37 %.

IJEIS (Indonesian Journal of Electronics and Instrumentation Systems), 2021

Fall cases of elderly people aged 65 or above put their health at risk because it could lead to hip bone fracture, concussion, even death. Immediate help is needed if fall happened which is why an automatic and unobtrusive fall detection system is needed. There are three approaches in fall detection system; wearable, ambience, and vision-based. Wearable approach has the drawback of its obtrusive nature while ambience approach is prone to high false positive value. Vision-based approach is chosen because its unobtrusive nature and low false positive value. This study uses Kinect camera because of its ability on extracting skeletal data. The methods that are used in the fall detection system are AdaBoost method and joint velocity thresholding method. Thresholding method is used as a comparison to AdaBoost method. Both methods use skeletal data from the subject recorded by the Kinect camera. AdaBoost method compares the skeletal data with model that was made before while thresholding m...

Jurnal Infra, 2014

2021

ABSTRAK Saat ini, kecerdasan buatan memungkinkan untuk dikembangkan dalam dunia robotika, khususnya untuk pengaturan gerakan robot berdasarkan pengolahan citra. Penelitian ini mengembangkan sebuah mobile robot yang dilengkapi dengan kamera katadioptrik dengan sudut pandang 360 0 . Citra yang didapatkan, dikonversi dari RGB menjadi HSV. Selanjutnya disesuaikan dengan proses morfologi. Nilai jarak yang terbaca oleh kamera (piksel) dengan jarak sebenarnya (cm) dihitung menggunakan Euclidean Distance. Nilai ini sebagai ekstraksi ciri data jarak yang dilatihkan pada sistem. Sistem yang dibuat pada penelitian ini memiliki iterasi sebanyak 1.000.000, dengan tingkat kelinieran R 2 =0.9982 dan keakuratan prediksi sebesar 99,03%. Kata kunci: Robot, HSV, Euclidean Distance, Kamera katadioptrik, Artifical Neural Network ABSTRACT Recently, artificial intelligence is possible to be developed in robotic, specifically for robot movements control based on image processing. This research develops a ...

Jurnal Penelitian Enjiniring, 2018

Penelitian ini bertujuan untuk merancang sebuah sistem estimasi jarak relatif antara kendaraan sebagai penelitian awal untuk konsep pengemudi tanpa awak agar berkendara dengan aman dan terhindar dari tabrakan. Sistem deteksi ini terdiri atas tahap deteksi dengan metode Histogram of Oriented Gradients (HOG) dan tahap estimasi jarak antara kendaraan dengan metode Width Based. Kendaraan yang digunakan pada penelitian ini adalah jenis city car dan van. Hasil deteksi kendaraan untuk jenis city car diperoleh persentase rata-rata TPR (True Positive Rate) sebesar 92% sedangkan mobil jenis van mendapatkan persentase rata-rata TPR sebesar 64% untuk 5 video yang di uji. Untuk hasil estimasi jarak relatif antara kendaraan diperoleh untuk jenis mobil city car menunjukkan hasil yang lebih baik dengan nilai MSE 0,29 dan untuk mobil jenis van dengan nilai MSE 0,55.

AVITEC, 2020

This study aims to develop a Kalman filter algorithm in order to reduce the accelerometer sensor noise as effectively as possible. The accelerometer sensor is one part of the Inertial Measurement Unit (IMU) used to find the displacement distance of an object. The method used is modeling the system to model the accelerometer system to form mathematical equations. Then the state space method is used to change the system modeling to the form of matrix operations so that the process of the data calculating to the Kalman Filter algorithm is not too difficult. It also uses the threshold algorithm to detect the sensor's condition at rest. The present study had good results, which of the four experiments obtained with an average accuracy of 93%. The threshold algorithm successfully reduces measurement errors when the sensor is at rest or static so that the measurement results more accurate. The developed algorithm can also detect the sensor to move forward or backward.