• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3C
• /
• pp.307-314
• /
• 2003

In the general multiple video object coder, more interested objects such as speaker or moving object is consistently coded with higher priority. Since the priority of each object may not be fixed in the whole sequence and be variable on frame basis, it must be adjusted in a frame. In this paper, we analyze the independent rate control algorithm and global algorithm that the QP value is controled by the static parameters, object importance or priority, target PSNR, weighted distortion. The priority among static parameters is analyzed and adjusted into dynamic parameters according to the visual interests or importance obtained by camera interface. Target PSNR and weighted distortion are proportionally derived by using magnitude, motion, and distortion. We apply those parameters for the weighted distortion control and the priority-based control resulting in the efficient bit-rate distribution. As results of this paper, we achieved that fewer bits are allocated for video objects which has less importance and more bits for those which has higher visual importance. The duration of stability in the visual quality is reduced to less than 15 frames of the coded sequence. In the aspect of PSNR, the proposed scheme shows higher quality of more than 2d13 against the conventional schemes. Thus the coding scheme interfaced to human- eye proves an efficient video coder dealing with the multiple number of video objects.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• 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 the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.17-25
• /
• 2007

In most electronic imaging applications, image with high resolution(HR) are desired. HR means that pixel density within an image is high, and therefore HR image can offer more details that may be critical in various applications. Digital images that are captured by CCD and CMOS cameras usually have a very low resolution, which significantly limits the performance of image recognition systems. Image super-resolution techniques can be applied to overcome the limits of these imaging systems. Super-resolution techniques have been proposed to increase the resolution by combining information from multiple images. To techniques were consisted of the registration algorithm for estimation and shift, the nearest neighbor interpolation using weight of acquired frames and presented frames. In this paper, it is proposed the image interpolation techniques using the wavelet base function. This is applied to embody a correct edge image and natural image when expend part of the still image by applying the wavelet base function coefficient to the conventional Super-Resolution interpolation method. And the proposal algorithm in this paper is confirmed to improve the image applying the nearest neighbor interpolation algorithm, bilinear interpolation algorithm.,bicubic interpolation algorithm through the computer simulation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.660-668
• /
• 2018

The main object of this study was to find a way to operate the marker for simulating a virtual construction using a MR(mixed reality) device. The secondary object was to find a way to extract the form-data from BIM data, and to represent the virtual object by the MR device. A tiny error of scale causes large errors of length because the architectural objects are very large. The scale was affected by the way that the camera of the MR device recognizes the marker. The method of installing and operating the marker causes length errors in the virtual object in the MR system. The experimental results showed that the error factor of the Virtual object's length was 0.47%. In addition, the distance between the markers can be decided through the results of an experiment for the multi-marker tracking system. The minimum distance between markers should be more than 5 m, and the error of length was approximately 23mm. If the represented virtual object must be less than 20mm in error, the particular mark should be installed within a 5 m radius of it. Based on this research, it is expected that utilization of the MR device will increase for the application of virtual construction simulations to construction sites.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.9-21
• /
• 2022

In this paper, we developed a 100% detection system for entering and leaving vehicles by improving the detection rate of existing detection cameras based on the LiDAR sensor, which is one of the core technologies of the 4th industrial revolution. Since the currently operating parking lot depends only on the recognition rate of the license plate number of about 98%, there are various problems such as inconsistency in the entry/exit count, inability to make a reservation in advance due to inaccurate information provision, and inconsistency in real-time parking information. Parking status information should be managed with 100% accuracy, and for this, we built a parking lot entrance/exit detection system using LIDAR. When a parking system is developed by applying the LIDAR sensor, which is mainly used to detect vehicles and objects in autonomous vehicles, it is possible to improve the accuracy of vehicle entry/exit information and the reliability of the entry/exit count with the detected sensing information. The resolution of LIDAR was guaranteed to be 100%, and it was possible to implement so that the sum of entering (+) and exiting (-) vehicles in the parking lot was 0. As a result of testing with 3,000 actual parking lot entrances and exits, the accuracy of entering and exiting parking vehicles was 100%.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.595-605
• /
• 2006

In this thesis, GPS and the electronic mapping were used to realize such a system by recognizing license plate numbers and identifying the location of objects that move at synchronous times with simulated movement in the electronic map. As well, throughout the study, a camera attached to a PDA, one of the mobile devices, automatically recognized and confirmed acquired license plate numbers from the front and back of each car. Using this mobile technique in a wireless network, searches for specific plate numbers and information about the location of the car is transmitted to a remote server. The use of such a GPS-based system allows for the measurement of topography and the effective acquisition of a car's location. The information is then transmitted to a central controlling center and stored as text to be reproduced later in the form of diagrams. Getting positional information through GPS and using image-processing with a PDA makes it possible to estimate the correct information of a car's location and to transmit the specific information of the car to a control center simultaneously, so that the center will get information such as type of the car, possibility of the defects that a car might have, and possibly to offer help with those functions. Such information can establish a mobile system that can recognize and accurately trace the location of cars.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.49-59
• /
• 2006

DAS(Driver Assistance Systems) support the driver's decision making to increase safety and comfort by issuing the naming signals or even exert the active control in case of dangerous conditions. Most previous research and products intend to offer only a single warning service like the lane departure warning, collision warning, lane change assistance, etc. Although these functions elevate the driving safety and convenience to a certain degree, New type of DAS will be developed to integrate all the important functions with an efficient HMI (Human-Machine Interface) framework for various driving conditions. We propose an all-around sensing based on the integrated DAS that can also remove the blind spots using 2 cameras and 8 sonars, recognize the driving environment by lane and vehicle detection, construct a novel birds-eye HMI for easy comprehension. it can give proper warning in case of imminent danger.