• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.469-478
• /
• 2016

This paper designs an application for detecting various objects using a smart phone with camera sensor, then implements the application that detects the number of faces in front of a user by using the Face API provided by android and generates a speech to the user. For implementing the application, the GoF strategy pattern is applied to design the application. It provides some advantages; first, the algorithm development schedule can separate the whole application development schedule; next, it makes easier to add the algorithm. For example, another detecting algorithm for the other objects (character, motion detection) that may be developed in the future, or it may be replaced by a more high-performance algorithm. With the propose method, a general smart phone can make some advantages that can provide information of various objects (such as moving people and objects, and detected character from signboards) to the person who is visually impaired.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권7호
• /
• pp.1815-1830
• /
• 2012

Existing R-tree that is based on a variety of outdoor-based techniques to manage moving objects have been investigated. Due to the different characteristics of the indoor and outdoor, it is difficult to management of moving object using existed methods in indoor setting. We propose a new index structure called ACII(adaptive Cell-based index for Indoor moving objects) for Indoor moving objects. ACII is Cell-based access structure adopting an overlapping technique. The ACII refines cells adaptively to handle indoor regional data, which may change its locations over time. The ACII consumed at most 30% of the space required by R-tree based methods, and achieved higher query performance compared with r-tree based methods.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.309-312
• /
• 2005

The need for LBS (Loc,ation Based Services) is increasing due to the wnespread of mobile computing devices and positioning technologies~ In LBS, there are many applications that need to manage moving objects (e.g. taxies, persons). The moving object join operation is to make pairs with spatio-temporal attribute for two sets in the moving object database system. It is import and complicated operation. And processing time increases by geometric progression with numbers of moving objects. Therefore efficient methods of spatio-temporal join is essential to moving object database system. In this paper, we apply spatial join methods to moving objects join. We propose two kind of join methods with TB- Tree that preserves trajectories of moving objects. One is depth first traversal spatio-temporaljoin and another is breadth-first traversal spatio-temporal join. We show results of performance test with sample data sets which are created by moving object ,generator tool.

• Journal of Information Processing Systems
• /
• 제7권3호
• /
• pp.519-530
• /
• 2011

A Snake is an active contour for representing object contours. Traditional snake algorithms are often used to represent the contour of a single object. However, if there is more than one object in the image, the snake model must be adaptive to determine the corresponding contour of each object. Also, the previous initialized snake contours risk getting the wrong results when tracking multiple objects in successive frames due to the weak topology changes. To overcome this problem, in this paper, we present a new snake method for efficiently tracking contours of multiple objects. Our proposed algorithm can provide a straightforward approach for snake contour rapid splitting and connection, which usually cannot be gracefully handled by traditional snakes. Experimental results of various test sequence images with multiple objects have shown good performance, which proves that the proposed method is both effective and accurate.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.53.2-53
• /
• 2001

The Non-Contact Optical Sensor using the Hologram Laser for CD Pickup was developed to measure a shape of transparent objects and shown a good performance. Therefore the problems caused by the contact sensor are solved by using the Non-Contact Sensor. The Non-Contact Sensor has to move toward the objects and obtain the Focus Error Signal to measure a position of transparent objects. However, if the distance between the sensor and the object is shorter than the working distance of the objective lens, the sensor will be collided against the objects. In this paper we proposed a new algorithm to estimate the start position of the Focus Error Signal to solve the problems of collision between the sensor and the objects. In addition, we verified that the algorithm is free from the collision in the real time measurement.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.65-71
• /
• 2024

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.

• International Journal of Computer Science & Network Security
• /
• 제23권10호
• /
• pp.44-48
• /
• 2023

Augmented Reality (AR) is an emerging technology and a vibrant field, it has become common in application development, especially in smartphone applications (mobile phones). The AR technology has grown increasingly during the past decade in many fields. Therefore, it is necessary to determine the optimal approach to building the final product by evaluating the performance of each of them separately at a specific task. In this work we evaluated overall CPU and RAM performance for several types of Markerless Augmented Reality applications by using a multiple-objects in mobile development. The results obtained are show that the objects with fewer number of vertices performs steady and not oscillating. Object was superior to the rest of the others is sphere, which is performs better values when processed, its values closer to the minimum CPU and RAM usage.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.600-602
• /
• 2005

Recently image display devices have become large and high quality. To control the qualities of the component, measurements of the shape and thickness of a plate glass has been required. In order to measure the shape of the specular objects, Non-Contact Optical Sensor using Hologram laser unit was proposed. The sensor has a optical system that is composed of a Hologram laser and objective lens used for CD Player, and the sensor showed high performance for measuring the shape and thickness of transparent plates. In the sensor, the temperature of the sensor body is controlled by TEC(Thermoelectric Cooler). In this paper, we proposed the measuring method to make better performance of sensor using focus error signal of a hologram laser unit. It can measure the shape and the thickness of transparent objects with the s-type focus error signal which is generated by the sensor while it goes to the object.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.171.1-171
• /
• 2001

This paper describes the design and implementation of a new type of a force reflective joystick. It has single degree of freedom that is actuated by motor and brake pair. The use of motor and brake allows various objects to be simulated without the stability problem and related safety issues involved with high torque motors only. The joystick performance is measured by its ability to simulate various test objects. Simple test objects are modeled as a benchmark test of the system´s performance and to evaluate different control approaches for hybrid motor/brake actuator. The force output joystick is capable of simulating forces in a variety of virtual environments. This device demonstrates the effectiveness of a hybrid motor/brake haptic actuator.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.53.3-53
• /
• 2001

This paper deals with the development of a shape inspection system of the Light Guide Panel(LGP), and the study for the performance of the system. The conventional contact sensing methods have been used to inspect the shape. However the contact-sensing methods have some problems. The contact between a tip of the sensor and the surface of objects make a sensor tip abraded and generate a defect on the surface of objects. In this paper, we employed the Non-Contact Optical Sensor[1] to measure the shape inspection system of LGPs, The Sensor composed of Hologram laser[3] unit used for CD Optical Pickup[2] is low cost and has a good performance to measure a transparent objects. From the results of experiments for LGP shape inspection ...