• Korean Journal of Artificial Intelligence
• /
• v.12 no.3
• /
• pp.1-7
• /
• 2024

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1213-1218
• /
• 2018

Recently introduced Mask R - CNN presents a conceptually simple, flexible, general framework for instance segmentation of objects. In this paper, we propose an algorithm for efficiently searching objects of images, while creating a segmentation mask of heat generation part for an instance which is a heating element in a heat sensed image acquired from a thermal infrared camera. This method called a mask R - CNN is an algorithm that extends Faster R - CNN by adding a branch for predicting an object mask in parallel with an existing branch for recognition of a bounding box. The mask R - CNN is added to the high - speed R - CNN which training is easy and fast to execute. Also, it is easy to generalize the mask R - CNN to other tasks. In this research, we propose an infrared image detection algorithm based on R - CNN and detect heating elements which can not be distinguished by RGB images. As a result of the experiment, a heat-generating object which can not be discriminated from Mask R-CNN was detected normally.

• Korean Journal of Optics and Photonics
• /
• v.20 no.1
• /
• pp.6-15
• /
• 2009

A mobile phone camera consisting of two aspheric lenses is designed, and stray light distribution on the image plane is analyzed. We assume that most of the incident light is absorbed on the inner surfaces of the lens barrel and spacers, only a small fraction of the light is scattered uniformly. Assuming that 10% of the incident light is scattered on the barrel and spacers, the maximum value of stray light is 7.1% of the ideal image intensity. The result of analysis shows that stray light originated mostly from internal reflection on the ribs. The contributions of scattering by the barrel and spacers are relatively small. To reduce the internal reflection, thin absorbing plates are inserted between lenses, and the shapes of spacers are modified. After the redesigning of the lens barrel, the maximum value of stray light is reduced to 1.1% of the ideal image intensity.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1217-1232
• /
• 2009

In this paper, we propose a semi-automatic 3D building reconstruction method using uncalibrated images which includes the facade of target building. First, we extract feature points in all images and find corresponding points between each pair of images. Second, we extract lines on each image and estimate the vanishing points. Extracted lines are grouped with respect to their corresponding vanishing points. The adjacency graph is used to organize the image sequence based on the number of corresponding points between image pairs and camera calibration is performed. The initial solid model can be generated by some user interactions using grouped lines and camera pose information. From initial solid model, a detailed building model is reconstructed by a combination of predefined basic Euler operators on half-edge data structure. Automatically computed geometric information is visualized to help user's interaction during the detail modeling process. The proposed system allow the user to get a 3D building model with less user interaction by augmenting various automatically generated geometric information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.438-446
• /
• 2013

Generally, a camera isn't located at the center of display in a tele-presence system and it causes an incorrect eye contact between speakers which reduce the realistic feeling during the conversation. To solve this incorrect eye contact problem, we newly propose an intermediate view reconstruction algorithm using both a color camera and a depth camera and applying for the depth image based rendering (DIBR) algorithm. In the proposed algorithm, an efficient hole filling method using the arithmetic mean value of neighbor pixels and an efficient boundary noise removal method by expanding the edge region of depth image are included. We show that the generated eye-contacted image has good quality through experiments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.25-33
• /
• 2010

In this paper, we propose a simple and efficient algorithm for head pose estimation using a single camera. First, four subimages are obtained from the camera image for face feature extraction. These subimages are used as feature templates. The templates are then tracked by Kalman filtering, and camera projective matrix is computed by the projective mapping between the templates and their coordinate in the 3D coordinate system. And the user's face pose is estimated from the projective mapping between the user's face and image plane. The accuracy and the robustness of our technique is verified on the experimental results of several real video sequences.

• Journal of the Korean Society of Radiology
• /
• v.14 no.5
• /
• pp.511-515
• /
• 2020

In this study, we evaluated image quality for new Gadolinium Aluminum Gallium Garnet (GAGG) scintillation material based on the Geant4 Application for Tomographic Emission (GATE) simulation tool. The gamma camera detectors with GAGG and NaI scintillation were designed. In particular, we modeled modified body phantom by National Electrical Manufacturers Association International Electrotechnical Commission to evaluate the simulated images. To analysis the image performance, the contrast to noise ratio (CNR) and coefficient of variation (COV) were used by drawn the region of interests, respectively. Based on the CNR and COV results, the CNR value for GAGG material is higher approximately 17 % than NaI material. In addition, the COV value for GAGG material is lower approximately 17 % than NaI material. In conclusion, we confirmed the performnace of GAGG based gamma camera is useful to improve the image quality for the nuclear medicine instrumentation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.119-122
• /
• 2007

In this paper, we propose the method of hardware-design for the division operation of image frame-unit processing in mobile phone camera. Generally, there are two types of the data processing, which are the parallel and serial type. The parallel type makes it possible to process in realtime, but it needs significant hardware size due to many comparators and buffer memories. Compare the serial type with the parallel type, the hardware size of the serial type is smaller than the other because it uses only one comparator, but serial type is not able to process in realtime. To use the hardware resources efficiently, we employ the serial divider since frame-unit operation for image processing does not need realtime process. When compared with both in the same bit size and operating frequency, the hardware size of the serial divider is approximately in the ratio of 13 percentage compared with the parallel divider.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.839-846
• /
• 2016

Bin picking is a task of picking a small object from a bin. For accurate bin picking, the 3D pose information, position, and orientation of a small object is required because the object is mixed with other objects of the same type in the bin. Using this 3D pose information, a robotic gripper can pick an object using exact distance and orientation measurements. In this paper, we propose a 3D vision technique for accurate measurement of 3D position and orientation of small objects, on which a paper label is stuck to the surface. We use a maximally stable extremal regions (MSERs) algorithm to detect the label areas in a left bin image acquired from a stereo camera. In each label area, image features are detected and their correlation with a right image is determined by a stereo vision technique. Then, the 3D position and orientation of the objects are measured accurately using a transformation from the camera coordinate system to the new label coordinate system. For stable measurement during a bin picking task, the pose information is filtered by averaging at fixed time intervals. Our experimental results indicate that the proposed technique yields pose accuracy between 0.4~0.5mm in positional measurements and $0.2-0.6^{\circ}$ in angle measurements.

• Journal of Digital Convergence
• /
• v.14 no.1
• /
• pp.189-194
• /
• 2016

Recently, there is increasing demand for image processing technology while activated the use of equipments such as camera, camcorder and CCTV. In particular, research and development related to 3D image technology using the depth camera such as Kinect sensor has been more activated. Kinect sensor is a high-performance camera that can acquire a 3D human skeleton structure via a RGB, skeleton and depth image in real-time frame-by-frame. In this paper, we develop a system. This system captures the motion of a 3D human skeleton structure using the Kinect sensor. And this system can be stored by selecting the motion file format as trc and bvh that is used for general purposes. The system also has a function that converts TRC motion captured format file into BVH format. Finally, this paper confirms visually through the motion capture data viewer that motion data captured using the Kinect sensor is captured correctly.