• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.6
• /
• pp.177-186
• /
• 2020

Recent advances in deep learning technology have improved image recognition performance in the field of computer vision, and serverless computing is emerging as the next generation cloud computing technology for event-based cloud application development and services. Attempts to use deep learning and serverless computing technology to increase the number of real-world image recognition services are increasing. Therefore, this paper describes how to develop an efficient deep learning based image recognition service system using serverless computing technology. The proposed system suggests a method that can serve large neural network model to users at low cost by using AWS Lambda Server based on serverless computing. We also show that we can effectively build a serverless computing system that uses a large neural network model by addressing the shortcomings of AWS Lambda Server, cold start time and capacity limitation. Through experiments, we confirmed that the proposed system, using AWS Lambda Serverless Computing technology, is efficient for servicing large neural network models by solving processing time and capacity limitations as well as cost reduction.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1846-1856
• /
• 2016

This study proposes a novel feature point initialization method in order to improve the accuracy of feature point positions by fusing a vision sensor and a lidar. The initialization is a process that determines three dimensional positions of feature points through two dimensional image data, which has a direct influence on performance of a 6-DoF bearing-only SLAM. Prior to the initialization, an extrinsic calibration method which estimates rotational and translational relationships between a vision sensor and lidar using multiple calibration tools was employed, then the feature point initialization method based on the estimated extrinsic calibration parameters was presented. In this process, in order to improve performance of the accuracy of the initialized feature points, an iterative automatic scaling parameter tuning technique was presented. The validity of the proposed feature point initialization method was verified in a 6-DoF bearing-only SLAM framework through an indoor and outdoor tests that compare estimation performance with the previous initialization method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.9
• /
• pp.790-797
• /
• 2001

A simple computer vision technology to measure the middle-ranged depth with a mono camera and a plain mirror is proposed. The proposed system is structured with the rotating mirror in front of the fixed mono camera. In contrast to the previous stereo vision system in which the disparity of the closer object is larger than that of the distant object, the pixel movement caused by the rotating mirror is bigger for the pixels of the distant object in the proposed system. Being inspired by such distinguished feature in the proposed system, the principle of the depth measurement based on the relation of the pixel movement and the distance of object is investigated. Also, the factors to influence the precision of the measurement are analysed. The benefits of the proposed system are low price and less chance of occlusion. The robustness for practical usage is an additional benefit of the proposed vision system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.3
• /
• pp.179-186
• /
• 2015

In this paper, a novel lateral control system is proposed for the purpose of improving lane keeping performance which is independent from GPS signals. Lane keeping is a key function for the realization of unmanned driving systems. In order to obtain this objective, a vision sensor based real-time lane detection scheme is developed. Furthermore, we employ a data fusion along with a real-time steering angle of the test vehicle to improve its lane keeping performance. The fused direction data can be obtained by an IMU sensor and vision sensor. The performance of the proposed system was verified by computer simulations along with field tests using MOHAVE, a commercial vehicle from Kia Motors of Korea.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2366-2380
• /
• 2024

In this study, a high-speed template matching system is proposed for wafer-vision alignment. The proposed system is designed to rapidly locate markers in semiconductor equipment used for wafer-vision alignment. We optimized and implemented a template-matching algorithm for the high-speed processing of high-resolution wafer images. Owing to the simplicity of wafer markers, we removed unnecessary components in the algorithm and designed the system using a field-programmable gate array (FPGA) to implement high-speed processing. The hardware blocks were designed using the Xilinx ZCU104 board, and the pyramid and matching blocks were designed using programmable logic for accelerated operations. To validate the proposed system, we established a verification environment using stage equipment commonly used in industrial settings and reference-software-based validation frameworks. The output results from the FPGA were transmitted to the wafer-alignment controller for system verification. The proposed system reduced the data-processing time by approximately 30% and achieved a level of accuracy in detecting wafer markers that was comparable to that achieved by reference software, with minimal deviation. This system can be used to increase precision and productivity during semiconductor manufacturing processes.

• Journal of Advanced Marine Engineering and Technology
• /
• v.32 no.6
• /
• pp.989-996
• /
• 2008

Recently, a few types of fish-cage in open sea are researched. This fish-cage has to operate monitoring system for keeping an optimum living condition for fish. The most efficient monitoring system is WVMS(Wireless Vision Monitoring System) for fish-cage in open sea. WVMS should be able to transmit video signal and communicate with each controller. So. it needs to be based on WLAN(Wireless LAN) which has characteristic of higher transfer-rate, In this paper, we propose a structure of WVMS using WLAN equipments for maritime environment and prove its effectiveness. We present the propagation loss model of WVMS's communication channel. measured by field test, and discuss its validity compared with the predictive value based on the Friss propagation model and Plane earth reflection model. We present the number of frames that is received from WLAN modem connecting with underwater-camera in field test spots. As a result, we confirmed that proposed WVMS is suitable for maritime environment and it is possible to be applied to fish-cage in open sea on 'seogwipo'.

• Journal of Mechanical Science and Technology
• /
• v.15 no.8
• /
• pp.1097-1107
• /
• 2001

In this paper, the wall following navigation algorithm of the mobile robot using a mono vision system is described. The key points of the mobile robot navigation system are effective acquisition of the environmental information and fast recognition of the robot position. Also, from this information, the mobile robot should be appropriately controlled to follow a desired path. For the recognition of the relative position and orientation of the robot to the wall, the features of the corridor structure are extracted using the mono vision system, then the relative position, the offset distance and steering angle of the robot from the wall, is derived for a simple corridor geometry. For the alleviation of the computation burden of the image processing, the Kalman filter is used to reduce search region in the image space for line detection. Next, the robot is controlled by this information to follow the desired path. The wall following control scheme by the PD control scheme is composed of two control parts, the approaching control and the orientation control, and each control is performed by steering and forward-driving motion of the robot. To verify the effectiveness of the proposed algorithm, the real time navigation experiments are performed. Through the result of the experiments, the effectiveness and flexibility of the suggested algorithm are verified in comparison with a pure encoder-guided mobile robot navigation system.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.29-37
• /
• 2019

Since construction sites are exposed to outdoor environments, working conditions are significantly dangerous. Thus, wearing of the personal protective equipments such as safety helmet is very important for worker safety. However, construction workers are often wearing-off the helmet as inconvenient and uncomportable. As a result, a small mistake may lead to serious accident. For this, checking of wearing safety helmet is important task to safety managers in field. However, due to the limited time and manpower, the checking can not be executed for every individual worker spread over a large construction site. Therefore, if an automatic checking system is provided, field safety management should be performed more effectively and efficiently. In this study, applicability of deep learning based computer vision technology is investigated for automatic checking of wearing safety helmet in construction sites. Faster R-CNN deep learning algorithm for object detection and classification is employed to develop the automatic checking model. Digital camera images captured in real construction site are used to validate the proposed model. Based on the results, it is concluded that the proposed model may effectively be used for automatic checking of wearing safety helmet in construction site.

• Journal of Sensor Science and Technology
• /
• v.7 no.2
• /
• pp.124-130
• /
• 1998

High-speed 3D vision systems are essential for autonomous robot or vehicle control applications. In our study, a stereo vision process has been developed. It consists of three steps : extraction of edges in right and left images, matching corresponding edges and calculation of the 3D map. This process is implemented in a VME 150/40 Imaging Technology vision system. It is a modular system composed by a display, an acquisition, a four Mbytes image frame memory, and three computational cards. Programmable accelerator computational modules are running at 40 MHz and are based on TMS320C31 DSP with a $64{\times}32$ bit instruction cache and two $1024{\times}32$ bit internal RAMs. Each is equipped with 512 Kbytes static RAM, 4 Mbytes image memory, 1 Mbytes flash EEPROM and a serial port. Data transfers and communications between modules are provided by three 8 bit global video bus, and three local configurable pipeline 8 bit video bus. The VME bus is dedicated to system management. Tasks between DSPs are distributed as follows: two DSPs are used to edges detection, one for the right image and the other for the left one. The last processor computes the matching process and the 3D calculation. With $512{\times}512$ pixels images, this sensor generates dense 3D maps at a rate of about 1 Hz depending of the scene complexity. Results can surely be improved by using a special suited multiprocessors cards.