• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.687-694
• /
• 2022

In this paper, we proposed an autonomous vehicle platform that delivers goods to a designated destination based on the SLAM (Simultaneous Localization and Mapping) map generated indoors by applying the Visual SLAM technology. To generate a SLAM map indoors, a depth camera for SLAM map generation was installed on the top of a small autonomous vehicle platform, and a tracking camera was installed for accurate location estimation in the SLAM map. In addition, a convolutional neural network (CNN) was used to recognize the label of the destination, and the driving algorithm was applied to accurately arrive at the destination. A prototype of an indoor delivery autonomous vehicle was manufactured, and the accuracy of the SLAM map was verified and a destination label recognition experiment was performed through CNN. As a result, the suitability of the autonomous driving vehicle implemented by increasing the label recognition success rate for indoor delivery purposes was verified.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.182-189
• /
• 2023

Depth estimation is a key technology in 3D map generation for autonomous driving of vehicles, robots, and drones. The existing sensor-based method has high accuracy but is expensive and has low resolution, while the camera-based method is more affordable with higher resolution. In this study, we propose self-attention-based unsupervised monocular depth estimation for UAV camera system. Self-Attention operation is applied to the network to improve the global feature extraction performance. In addition, we reduce the weight size of the self-attention operation for a low computational amount. The estimated depth and camera pose are transformed into point cloud. The point cloud is mapped into 3D map using the occupancy grid of Octree structure. The proposed network is evaluated using synthesized images and depth sequences from the Mid-Air dataset. Our network demonstrates a 7.69% reduction in error compared to prior studies.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.207-210
• /
• 2003

In this paper, we have implemented the DVR system which is controlled far away, and added a function of TCP/IP Network for image data and control signal transmission, the DVR system has the advantage of easy to search and of no loss in stored quality. The continuously declining price of the hard drive presents the opportunity for the DVR system to displace the analog system. Also, with spread of the internet the needs of PC based the DVR system increase. Therefore, we have implemented DVR system within a function of network. When obtained image through the PTZ camera is transmitted to digital form, very large space of storage is required, hence image compression is essential. We use JPEG2000 for compression of image. JPEG2000 adopt DWT by means of transform. DWT concentrates important information of image on subband and has feature of multi-resolution. It is effective in order to express image. Thus JPEG2000 is suitable for image compression in DVR system. The significance of this paper is to design the DVR system which is controlled through TCP/IP network and to implement transmission of image compression using JPEG2000.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.7
• /
• pp.782-787
• /
• 2014

Due to the complicated steel structure and safety concern, it is very difficult to deploy wireless networks in power plants. This paper presents a hybrid network, named as $P^2HYMN$ (Power Plant HYbrid Maintenance Network), encompassing PLC (Power Line Communication), TLC (Telephone Line Communication), and Wireless LAN. The design goal of $P^2HYMN$ is to integrate multimedia data such as design drawings of control equipment, process data, and video image data for maintenance operation in electric power plants. A Multiplex Line Communication (MLC) device was designed and implemented to integrate PLC, TLC, and Wireless LAN into $P^2HYMN$. Performance test of $P^2HYMN$ has been conducted on a testbed under various conditions. The throughput of TLC was shown as 39 Mbps. Because the bandwidth requirement per camera is 8.5 Mbps on average, TLC is expected to support more thant four video camera at the same time.

• The KIPS Transactions:PartD
• /
• v.10D no.6
• /
• pp.1041-1048
• /
• 2003

This paper implements a remote image based metering(IBM) system which capture meter image, recognizes number automatically, and send the data wirelessly through PCS data network. We use existing gas/water meter and get NTSC camera image by installing small monochrome CMOS camera on the meter closely. For remote data transfer, we use SMS (short message service) that is provided by commercial PCS network. We developed DVR(digital video recorder) for capturing meter image and character recognition algorithm. In addition, hardware and software for SMS and meter selector were developed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.76-79
• /
• 2010

Internet of the Web-based Home Securiy, ITS (Intelligent Traffic System), the tourism industry, production field, etc In many fields, using a network camera imaging system has been spotlighted and Accordingly the demand for network cameras is growing rapidly. in order to control it according to the video server complex has a costly problem. In this paper, according to an increasing number of cameras cost and complexity of the video server problems to solve information from video cameras through multi-channel input single-channel multiplex and the fact that switching is handled and Also, the system automatically switches the image data is implemented.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.488-498
• /
• 2007

This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs) in Ubiquitous Smart Space (USS). The topology is determined by tracking moving objects and establishing object correspondence across multiple cameras. To track people successfully in multiple camera views, we used the Merge-Split (MS) approach for object occlusion in a single camera and the grid-based approach for extracting the accurate object feature. In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs. The main contribution of this paper is to estimate transition times between various entry and exit zones, and to graphically represent the camera topology as an undirected weighted graph using the transition probabilities.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.532-537
• /
• 2009

The necessity of intelligent surveillance system is gradually considered seriously from the space where the security is important. In this paper, we embodied unmanned intelligent system by developing embedded mobile robot based on images and sounds tracking. For objects tracking, we used block-matching algorithm and for sound source tracking, we calculated time differences and magnitude dissimilarities of sound. And we demonstrated the superiority of intruder tracking algorithm through the embodiment of Pan-Tilt camera and sound source tracking module using system, Network camera and mobile robot using system and mobile robot using system. By linking security system, the suggested system can provide some interfacing functions for the security service of the public facilities as well as that of home.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.667-674
• /
• 2023

In the event of a disaster occurring within a building, the prompt and efficient evacuation and rescue of occupants within the building becomes the foremost priority to minimize casualties. For the purpose of such rescue operations, it is essential to ascertain the distribution of individuals within the building. Nevertheless, there is a primary dependence on accounts provided by pertinent individuals like building proprietors or security staff, alongside fundamental data encompassing floor dimensions and maximum capacity. Consequently, accurate determination of the number of occupants within the building holds paramount significance in reducing uncertainties at the site and facilitating effective rescue activities during the golden hour. This research introduces a methodology employing computer vision algorithms to count the number of occupants within distinct building locations based on images captured by installed multiple CCTV cameras. The counting methodology consists of three stages: (1) establishing virtual Lines of Interest (LOI) for each camera to construct a multi-camera network environment, (2) detecting and tracking people within the monitoring area using deep learning, and (3) aggregating counts across the multi-camera network. The proposed methodology was validated through experiments conducted in a five-story building with the average accurary of 89.9% and the average MAE of 0.178 and RMSE of 0.339, and the advantages of using multiple cameras for occupant counting were explained. This paper showed the potential of the proposed methodology for more effective and timely disaster management through common surveillance systems by providing prompt occupancy information.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.39 no.2
• /
• pp.199-206
• /
• 2015

In this study, a new diagnosis method which can predict the working states of a pipe or its element in realtime is proposed by using an artificial neural network. The displacement data of an inspection element of a piping system are obtained by the use of PIV (particle image velocimetry), and are used for teaching a neural network. The measurement system consists of a camera, a light source and a host computer in which the artificial neural network is installed. In order to validate the constructed monitoring system, performance test was attempted for two kinds of mobile phone of which vibration modes are known. Three values of acceleration (minimum, maximum, mean) were tested for teaching the neural network. It was verified that mean values were appropriate to be used for monitoring data. The constructed diagnosis system could monitor the operation condition of a gas pipe.