• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.262-269
• /
• 2020

Recently, many attempts have been made to reduce the time required for payment in various shopping environments. In addition, for the Fourth Industrial Revolution era, artificial intelligence is advancing, and Internet of Things (IoT) devices are becoming more compact and cheaper. So, by integrating these two technologies, access to building an unmanned environment to save people time has become easier. In this paper, we propose a smart shopping cart system based on low-cost IoT equipment and deep-learning object-detection technology. The proposed smart cart system consists of a camera for real-time product detection, an ultrasonic sensor that acts as a trigger, a weight sensor to determine whether a product is put into or taken out of the shopping cart, an application for smartphones that provides a user interface for a virtual shopping cart, and a deep learning server where learned product data are stored. Communication between each module is through Transmission Control Protocol/Internet Protocol, a Hypertext Transmission Protocol network, a You Only Look Once darknet library, and an object detection system used by the server to recognize products. The user can check a list of items put into the smart cart via the smartphone app, and can automatically pay for them. The smart cart system proposed in this paper can be applied to unmanned stores with high cost-effectiveness.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.3
• /
• pp.165-178
• /
• 2007

The recent progress in multimedia signal processing and transmission technologies has contributed to the extensive use of multimedia devices to watch sports games with small LCD panel. However, the most of video sequences are captured for normal viewing on standard TV or HDTV, for cost reasons, merely resized and delivered without additional editing. This may give the small-display-viewers uncomfortable experiences in understanding what is happening in a scene. For instance, in a soccer video sequence taken by a long-shot camera techniques, the tiny objects (e.g., soccer ball and players) may not be clearly viewed on the small LCD panel. Moreover, it is also difficult to recognize the contents of the scorebox which contains the elapsed time and scores. This renuires intelligent display technique to provide small-display-viewers with better experience. To this end, one of the key technologies is to determine region of interest (ROI) and display the magnified ROI on the screen, where ROI is a part of the scene that viewers pay more attention to than other regions. Examples include a region surrounding a ball in long-shot and a scorebox located in the comer of each frame. In this paper, we propose a scheme for raising viewing experiences of multimedia mobile device users. Instead of taking generic approaches utilizing visually salient features for extraction of ROI in a scene, we take domain-specific approach to exploit unique attributes of the soccer video. The proposed scheme consists of two modules: ROI determination and scorebox extraction. The experimental results show that the proposed scheme offers useful tools for intelligent video display on multimedia mobile devices.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.1-10
• /
• 2010

This present paper's goal is to show a virtual human agent's movement-data loci based on realistically limited perception data is human-like. To determine human-likeness of the movement-data loci, we consider interactions between two parameters: Realistically Limited Perception (RLP) data and Incremental Movement-Path data Generation (IMPG). That is to consider how the former (i.e., RLP), one of the simulated parameters of human thought or its elements dictates the latter (i.e., IMPG), one of the simulated parameters of human movement behavior. Mapping DB is a prerequisite for navigation in an agent system because it functions as an interface between perception and movement behavior. Although Hill et al. studied mapping DB methodology based on RLP, their research dealt only with a rendering camera's view point data. The agent system in this present paper was integrated with the Hill's mapping DB module and then the two parameters' interaction was considered on a military reconnaissance mission with unexpected enemy emergence. Movement loci that were generated by the agent and subjects were compared with each other. The agent system in this present research verifies that it can be a functional test bed for producing human-like movement-data loci although the human-likeness of agent is the result of a pilot test, determined by two parameters (RLP and IMPG) and only 30 subjects.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.1-12
• /
• 2011

Large-sized multi-touch screen is usually made using infrared rays. That is because it has technical constraints or cost problems to make the screen with the other ways using such as existing resistive overlays, capacitive overlay, or acoustic wave. Using infrared rays to make multi-touch screen is easy, but is likely to have technical limits to be implemented. To make up for these technical problems, two other methods were suggested through Surface project, which is a next generation user-interface concept of Microsoft. One is Frustrated Total Internal Reflection (FTIR) which uses infrared cameras, the other is Diffuse Illumination (DI). FTIR and DI are easy to be implemented in large screens and are not influenced by the number of touch points. Although FTIR method has an advantage in detecting touch-points, it also has lots of disadvantages such as screen size limit, quality of the materials, the module for infrared LED arrays, and high consuming power. On the other hand, DI method has difficulty in detecting touch-points because of it's structural problems but makes it possible to solve the problem of FTIR. In this thesis, we study the algorithms for effectively correcting the distort phenomenon of optical lens, and image processing algorithms in order to solve the touch detecting problem of the original DI method. Moreover, we suggest calibration algorithms for improving the accuracy of multi-touch, and a new tracking technique for accurate movement and gesture of the touch device. To verify our approaches, we implemented a table-based multi touch screen.

• Korean Journal of Optics and Photonics
• /
• v.12 no.3
• /
• pp.240-249
• /
• 2001

A high speed ultra-compact lens with a diffractive optical element (DOE) is designed, which can be applied to mobile communication devices such as IMT2000, PDA, notebook computer, etc. The designed hybrid lens has sufficiently high performance of less than f/2.2, compact size of 3.3 mm (1st surf. to image), and wide field angle of more than 30 deg. compared with the specifications of a single lens. By proper choice of the aspheric and DOE surface which has very large negative dispersion, we can correct chromatic and high order aberrations through the optimization technique. From Seidel third order aberration theory and Sweatt modeling, the initial data and surface configurations, that is, the combination condition of the DOE and the aspherical surface are obtained. However, due to the consideration of diffraction efficiency of a DOE, we can choose only four cases as the optimization input, and present the best solution after evaluating and comparing those four cases. On the other hand, we also report dramatic improvement in optical performance by inserting another refractive lens (so-called, field flattener), that keeps the refractive power of an original DOE lens and makes the petzval sum zero in the original DOE lens system. ystem.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.4
• /
• pp.43-54
• /
• 2007

This paper presents design and verification of a face detection hardware for real time application. Face detection algorithm detects rough face position based on already acquired feature parameter data. The hardware is composed of five main modules: Integral Image Calculator, Feature Coordinate Calculator, Feature Difference Calculator, Cascade Calculator, and Window Detection. It also includes on-chip Integral Image memory and Feature Parameter memory. The face detection hardware was verified by using S3C2440A CPU of Samsung Electronics, Virtex4LX100 FPGA of Xilinx, and a CCD Camera module. Our design uses 3,251 LUTs of Xilinx FPGA and takes about 1.96${\sim}$0.13 sec for face detection depending on sliding-window step size, when synthesized for Virtex4LX100 FPGA. When synthesized on Magnachip 0.25um ASIC library, it uses about 410,000 gates (Combinational area about 345,000 gates, Noncombinational area about 65,000 gates) and takes less than 0.5 sec for face realtime detection. This size and performance shows that it is adequate to use for embedded system applications. It has been fabricated as a real chip as a part of XF1201 chip and proven to work.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.49-64
• /
• 2008

Recently, many researches about making more comfortable input device based on gaze detection technology have been done in human computer interface. However, the system cost becomes high due to the complicated hardware and there is difficulty to use the gaze detection system due to the complicated user calibration procedure. In this paper, we propose a new gaze detection method based on the 2D analysis and a simple user calibration. Our method used a small USB (Universal Serial Bus) camera attached on a HMD (Head-Mounted Display), hot-mirror and IR (Infra-Red) light illuminator. Because the HMD is moved according to user's facial movement, we can implement the gaze detection system of which performance is not affected by facial movement. In addition, we apply our gaze detection system to 3D first person shooting game. From that, the gaze direction of game character is controlled by our gaze detection method and it can target the enemy character and shoot, which can increase the immersion and interest of game. Experimental results showed that the game and gaze detection system could be operated at real-time speed in one desktop computer and we could obtain the gaze detection accuracy of 0.88 degrees. In addition, we could know our gaze detection technology could replace the conventional mouse in the 3D first person shooting game.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.471-477
• /
• 2014

In this paper, we propose a low-cost license plate recognition system based on smart cam system using Android. The proposed system consists of a portable device and server. Potable device Hardware consists of ARM Cortex-A9 (S5PV210) processor control unit, a power supply device, wired and wireless communication, input/output unit. We develope Linux kernel and dedicated device driver for WiFi module and camera. The license plate recognition algorithm is consisted of setting candidate plates areas with canny edge detector, extracting license plate number with Labeling, recognizing with template matching, etc. The number that is recognized by the device is transmitted to the remote server via the user mobile phone, and the server re-transfer the vehicle information in the database to the portable device. To verify the utility of the proposed system, user photographs the license plate of any vehicle in the natural environment. Confirming the recognition result, the recognition rate was 95%. The proposed system was suitable for low cost portable license plate recognition device, it enabled the stability of the system when used long time by using the Android operating system.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.30-39
• /
• 2013

In recent years, with the development of devices to collect multimedia data such as small CMOS camera sensor and micro phone, studies on wireless multimedia sensor network technologies and their applications that extend the existing wireless sensor network technologies have been actively done. In such applications, various basic schemes such as the processing, storage, and transmission of multimedia data are required. Especially, a security for real world environments is essential. In this paper, in order to defend the sniffing attack in various hacking techniques, we propose a multipath routing scheme for physically avoiding the data transmission path from the risk factors. Our proposed scheme establishes the DEFCON of the sensor nodes that are geographically close to risk factors and the priorities according to the importance of the data. Our proposed scheme performs risk factor detour multipath routing through a safe path considering the DEFCON and data priority. Our experimental results show that although our proposed scheme takes the transmission delay time by about 5% over the existing scheme, it reduces the eavesdropping rate that can attack and intercept data by the risk factor by about 18%.