• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.363-366
• /
• 2016

In this paper, we propose a method for detecting pedestrian, problem-solving situations that occur in a cross. When a pedestrian crossing and other, there occurs a problem of detecting the other pedestrians for detecting a specific pedestrian in the image. The proposed method for solving the problem is as follows. First, select a specific pedestrian detected by bounding box, and extracts the area as a template. Detecting a pedestrian from the image using the HOG, and designated as a candidate region. The final choice of the pedestrian detected by comparison with a candidate pedestrian with the specific pedestrian extracted for template. In comparison, using the Template matching, Histogram comparison and LBP.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.4120-4132
• /
• 2017

In this research, we implement a deformable object simulation system using OpenGL's shader language, GLSL4.3. Deformable object simulation is implemented by using volumetric mass-spring system suitable for real-time simulation among the methods of deformable object simulation. The compute shader in GLSL 4.3 which helps to access the GPU resources, is used to parallelize the operations of existing deformable object simulation systems. The proposed system is implemented using a compute shader for parallel processing and it includes a bounding box-based collision detection solution. In general, the collision detection is one of severe computing bottlenecks in simulation of multiple deformable objects. In order to validate an efficiency of the system, we performed the experiments using the 3D volumetric objects. We compared the performance of multiple deformable object simulations between CPU and GPU to analyze the effectiveness of parallel processing using GLSL. Moreover, we measured the computation time of bounding box-based collision detection to show that collision detection can be processed in real-time. The experiments using 3D volumetric models with 10K faces showed the GPU-based parallel simulation improves performance by 98% over the CPU-based simulation, and the overall steps including collision detection and rendering could be processed in real-time frame rate of 218.11 FPS.

• Journal of Broadcast Engineering
• /
• v.27 no.7
• /
• pp.999-1010
• /
• 2022

The increase in vehicle purchases worldwide is having a very significant impact on the availability of parking spaces. In particular, since it is difficult to secure a parking space in an urban area, it may be of great help to the driver to check vehicle parking information in advance. However, the current parking lot information is still operated semi-manually, such as notifications. Therefore, in this study, we propose a system for detecting a parking space using a relatively simple image processing method based on an image taken from the sky and evaluate its performance. The proposed method first converts the captured RGB image into a black-and-white binary image. This is to simplify the calculation for detection using discrete information. Next, a morphological operation is applied to increase the clarity of the binary image, and a template mask in the form of a bounding box indicating a parking space is applied to check the parking state. Twelve image samples and 2181 total of test, were used for the experiment, and a threshold of 40% was used to detect each parking space. The experimental results showed that information on the availability of parking spaces for parking users was provided with an accuracy of 95%. Although the number of experimental images is somewhat insufficient to address the generality of accuracy, it is possible to confirm the possibility of parking space detection with a simple image processing method.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.13-20
• /
• 2019

Recently, object detection technology based on CNN has been actively studied. Object detection technology is used as an important technology in autonomous vehicles, intelligent image analysis, and so on. In this paper, we propose a rotation change robust object detection system by applying MI-FL (Moment Invariant-Feature Layer) to SSD (Single Shot Multibox Detector) which is one of CNN-based object detectors. First, the features of the input image are extracted based on the VGG network. Then, a total of six feature layers are applied to generate bounding boxes by predicting the location and type of object. We then use the NMS algorithm to get the bounding box that is the most likely object. Once an object bounding box has been determined, the invariant moment feature of the corresponding region is extracted using MI-FL, and stored and learned in advance. In the detection process, it is possible to detect the rotated image more robust than the conventional method by using the previously stored moment invariant feature information. The performance improvement of about 4 ~ 5% was confirmed by comparing SSD with existing SSD and MI-FL.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.305-311
• /
• 2021

One of the highly reliable object tracking methods is to trace objects by associating objects detected by deep learning. The detected object is represented by a rectangular box. The box has information such as location and size. Since the tracker has motion information of the object in addition to the location and size, knowing additional information about the motion of the detected box can increase the reliability of object tracking. In this paper, we present a new method of reliably estimating the moving direction of the detected object in underground parking lot. First, the frame difference image is binarized for detecting motion energy, change due to the object motion. Then, a cumulative binary image is generated that shows how the motion energy changes over time. Next, the moving direction of the detected box is estimated from the accumulated image. We use a new cost function to accurately estimate the direction of movement of the detected box. The proposed method proves its performance through comparative experiments of the existing methods.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.77-86
• /
• 2018

Although separation of touching pigs in real-time is an important issue for a 24-h pig monitoring system, it is challenging to separate accurately the touching pigs in a crowded pig room. In this study, we propose a separation method for touching pigs using the information generated from Convolutional Neural Network(CNN). Especially, we apply one of the CNN-based object detection methods(i.e., You Look Only Once, YOLO) to solve the touching objects separation problem in an active manner. First, we evaluate and select the bounding boxes generated from YOLO, and then separate touching pigs by analyzing the relations between the selected bounding boxes. Our experimental results show that the proposed method is more effective than widely-used methods for separating touching pigs, in terms of both accuracy and execution time.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1557-1562
• /
• 2009

In the hydraulic room of a forging press machine, a system which can detect and prevent risks at its early stage is needed because there may be a leakage due to the damage of the connection parts of the piping which can endanger human life and mechanical damage. In this paper, the system to automatically recognize a leakage of hydraulic fluid in terms of using the pan/tilt camera from a remote place is implemented. It finds the bounding boxes which are recognized with object regions in the process of labeling and detects the proper leakage regions of hydraulic fluid with the ratios of width and height of the bounding boxes and compactness of the leakage shape. Also, it performs noise removal and calibration for transition and rotation of image as a preprocessing process. The experimental results show that the proposed system has been verified to detect the leakage regions accurately in various sources of light.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.1
• /
• pp.44-52
• /
• 2008

In this paper we consider detecting collisions between characters whose motion is specified by motion capture data. Since we are targeting on massive crowd simulation, we only consider rough collisions, modeling the characters as a disk in the floor plane. To provide efficient collision detection, we introduce a hierarchical bounding volume, the Motion Oriented Bounding Box tree (MOBB tree). A MOBBtree stores space-time bounds of a motion clip. In crowd animation tests, MOBB trees performance improvements ranging between two and an order of magnitude.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.105-114
• /
• 2015

This paper proposes methods to remove background area and segment region of interest (ROI) in chest X-ray images. Conventional algorithms to improve detail or contrast of images normally utilize brightness and frequency information. If we apply such algorithms to the entire images, we cannot obtain reliable visual quality due to unnecessary information such as background area. So, we propose two effective algorithms to remove background and segment ROI from the input X-ray images. First, the background removal algorithm analyzes the histogram distribution of the input X-ray image. Next, the initial background is estimated by a proper thresholding on histogram domain, and it is removed. Finally, the body contour or background area is refined by using a popular guided filter. On the other hand, the ROI, i.e., lung segmentation algorithm first determines an initial bounding box using the lung's inherent location information. Next, the main intensity value of the lung is computed by vertical cumulative sum within the initial bounding box. Then, probable outliers are removed by using a specific labeling and the pre-determined background information. Finally, a bounding box including lung is obtained. Simulation results show that the proposed background removal and ROI segmentation algorithms outperform the previous works.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.485-487
• /
• 1999

본 논문에서는 온라인 필기체 수식 인식을 위한 순차적인 구조 분석 방법을 제안한다. 제안된 방법은 캐블릿상에서 필기된 수식에 대한 심볼 인식 결과와 각 심볼의 Bounding Box이 좌표를 입력받아서 필기 순서를 기반으로 순차적으로 수식의 구조를 해석한다. 그래프 내의 이웃하는 두 노드 사이의 관계를 결정하기 위해서 심볼의 사용에 관한 표기 정보와 6단계 관계 결정 규칙을 사용하여 노드들 사이에 생성될 수 있는 에지의 수를 최소화하고 BackTracking을 피했다. 제안 방법의 성능을 평가하기 위해 100개의 테스트 샘플에 대해 구조 분석 실험을 수행하였다.