• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.3
• /
• pp.115-125
• /
• 2011

The smartphones which have been recently are embedded with high resolution quality camera, assisted GPS, accelerometer, gyroscope and various sensors including magnetometer sensor that could be directly used for measurement. This study aims to suggest the possible application of smartphone camera providing high resolution images in terms of photogrammetry by calibrating it and assessing its accuracy. First of all, prior to the accuracy assessment of smartphone camera, camera calibration was conducted to correct lens distortion of each camera and the accuracy of image coordinates and object coordinates calculated by bundle adjustment during this procedure was analyzed. Also regarding three-dimensional positioning, result analysis depending on considering lens distortion coefficients was conducted, and finally relative accuracy of smartphone camera on metric camera was assessed. The result showed that in terms of distortion correction of smartphone camera, also higher order symmetric radial lens distortion coefficients should be considered, and three dimensional position determined by smartphone images was a little difference from that by metric camera. Therefore it is expected that smartphone images have huge possibility to be used for photogrammetry.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.487-489
• /
• 2016

In this paper, quad copter provides a method for preventing the possibility of accident in the air during a formation flight. The existing studies had a few studies upon the falls because quad copter formation flight was generally implemented indoors. Therefore, in this paper, we provide a self-diagnosis system to prevent a secondary accident for mismatching the Proportional-Integral-Derivative(PID) and detecting an abnormal communication modules each others in formation flying system. Scheme to be proposed, a system is that when one of the node meets a problem, the header node is sending the information of the current state to the server in the first and making a diagnosis itself in order to avoid the problems caused by dropping from the air. Therefore, if the difference between PID value of header node and slave node is greater than specified values or if it detects a defective sensors and communication modules, the proposed system is set to provide for moving toward a safe place. As a result, we expect that this proposed system is possible to minimize additional incidents by self adjusting the height through a self-diagnosis discovering flawed the acceleration sensor, gyro sensor and various attached sensors.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.68-77
• /
• 2021

In this paper, a GPS/MEMS IMU integrated navigation receiver module capable of operating in a high dynamic environment is designed and fabricated, and the results is confirmed. The designed module is composed of RF receiver unit, inertial measurement unit, signal processing unit, correlator, and navigation S/W. The RF receiver performs the functions of low noise amplification, frequency conversion, filtering, and automatic gain control. The inertial measurement unit collects measurement data from a MEMS class IMU applied with a 3-axis gyroscope, accelerometer, and geomagnetic sensor. In addition, it provides an interface to transmit to the navigation S/W. The signal processing unit and the correlator is implemented with FPGA logic to perform filtering and corrrelation value calculation. Navigation S/W is implemented using the internal CPU of the FPGA. The size of the manufactured module is 95.0×85.0×.12.5mm, the weight is 110g, and the navigation accuracy performance within the specification is confirmed in an environment of 1200m/s and acceleration of 10g.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.9 no.2
• /
• pp.137-144
• /
• 2015

In this paper, we present an inertial sensor-based gait analysis system to measure and analyze lower-limb movements. We developed an integral AHRS(Attitude Heading Reference System) using a combination of rate gyroscope, accelerometer and magnetometer sensor signals. Several AHRS modules mounted on segments of the patient's body provide the quaternions representing the patient segments's orientation in space. And a method is also proposed for calculating three-dimensional inter-segment joint angle which is an important bio-mechanical measure for a variety of applications related to rehabilitation. To evaluate the performance of our AHRS module, the Vicon motion capture system, which offers millimeter resolution of 3D spatial displacements and orientations, is used as a reference. The evaluation resulted in a RMSE(Root Mean Square Error) of 1.08 and 1.72 degree in yaw and pitch angle. In order to evaluate the performance of our the gait analysis system, we compared the joint angle for the hip, knee and ankle with those provided by Vicon system. The result shows that our system will provide an in-depth insight into the effectiveness, appropriate level of care, and feedback of the rehabilitation process by performing real-time limb or gait analysis during the post-stroke recovery.

• Korean Journal of Remote Sensing
• /
• v.31 no.3
• /
• pp.215-226
• /
• 2015

Normally, aero photography using UAV uses about 430 MHz bandwidth radio frequency (RF) modem and navigates and remotely controls through the connection between UAV and ground control system. When using the exhausting method, it has communication range of 1-2 km with frequent cross line and since wireless communication sends information using radio wave as a carrier, it has 10 mW of signal strength limitation which gave restraints on life my distance communication. The purpose of research is to use communication technologies such as long-term evolution (LTE) of smart camera, Bluetooth, Wi-Fi and other communication modules and cameras that can transfer data to design and develop automatic shooting system that acquires images to UAV at the necessary locations. We conclude that the android based UAV filming and communication module system can not only film images with just one smart camera but also connects UAV system and ground control system together and also able to obtain real-time 3D location information and 3D position information using UAV system, GPS, a gyroscope, an accelerometer, and magnetic measuring sensor which will allow us to use real-time position of the UAV and correction work through aerial triangulation.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.