• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• Journal of Korea Game Society
• /
• v.15 no.5
• /
• pp.99-108
• /
• 2015

To identify the location of the object and improve the realism in 3D game, shadow mapping is widely used to compute the depth values of vertices in view of the light position. Since the depth value of the shadow map is calculated by the world coordinate, the depth values of the static object don't need to be updated. In this paper, (1) in order to improve the rendering speed, using multiple render targets the depth values of static objects stored only once are separated from those of dynamic objects stored each time. And (2) in order to improve the shadow quality in the quarter view 3D game, the position of the light is located close to dynamic objects traveled along the camera each time. The effectiveness of the proposed method is verified by the experiments according to the different static and dynamics object configuration in 3D game.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.571-575
• /
• 2015

This paper propose a temporal histogram -based behavior pattern analysis algorithm to analyze the movement features of moving objects from the image inputted in real-time. For the purpose of tracking and analysis of moving objects, it needs to be performed background learning which separated moving objects from the background. Moving object is extracted as a background learning after identifying the object by using the center of gravity and the coordinate correlation is performed by the object tracking. The start frame of each of the tracked object, the end frame, the coordinates information and size information are stored and managed by the linked list. Temporal histogram defines movement features pattern using x, y coordinates based on time axis, it compares each coordinates of objects for understanding its movement features and behavior pattern. Behavior pattern analysis system based on temporal histogram confirmed high tracking rate over 95% with sustaining high processing speed 45~50fps through the demo experiment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.6
• /
• pp.583-591
• /
• 2000

Caching mechanisms have been studied extensively to buffer the speed gap of hierarchical storages in the context of cache memory, paging system, and buffer management system. As the wide-area distributed environments such as the WWW extend broadly, caching of remote objects becomes more and more important. In the wide-area distributed environments, the cost and the benefit of caching an object is not uniform due to the location of the object; which should be considered in the cache replacement algorithms. For online operation, the time complexity of the replacement algorithm should not be excessive. To date, most replacement algorithms for the wide-area distributed environments do not meet both the non-uniformity of objects and the time complexity constraint. This paper proposes a replacement algorithm which considers the non-uniformity of objects properly; it also allows for an efficient implementation. Trace-driven simulations show that proposed algorithm outperforms existing replacement algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.12
• /
• pp.2836-2842
• /
• 2010

An NPC grouping method is proposed for various 3D games depending on their characteristics. Immovable objects tend to have particular orientation features in their Gabor filtering results whereas the movable objects controlled by AI appearing as a human or an animal do not. First of all, We analyzed directional and frequency domain features in the NPC object and configured them as 24 Gabor filter banks. Then, 24-dimensional feature vectors according to the scale and direction of the filter are calculated. Each extracted vector represents the energy of a certain direction. This energy indicates the particular direction strength of the object texture. Thus, using this property, NPCs could be grouped as artificial objects and natural objects effectively and it draws the game more speed and strategic actions as a result.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1992.04a
• /
• pp.256-261
• /
• 1992

Acquisition of 3D points is an essential process for modelling of physical 3D objects. Although Coordinate Measuring Machine(CMM) is most accurate for this purpose, it is very time consuming. To enhance the data aquisition speed for scuptured surfaces, active vision with reflecctometric method was used for our system. A fter the data acquisition, the system automatically generates cutting tool path for the 3-axis milling of the object. The fullyintegrated system from the data acquisition to the NC-code generation was implemented with IBN-PC/386 and necessary hardwears.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2865-2867
• /
• 2000

In machine vision fields around FA, there have been demands for functions to capture high speed moving objects as blur-free images. By electronic shutters, progressive scan cameras can do it. This paper develops a module to connect a progressive scan camera, XC-55.

• Journal of information and communication convergence engineering
• /
• v.3 no.2
• /
• pp.93-95
• /
• 2005

In order to create security session, security keys are preconfigured between communication objects. For this purpose, Handshake Protocol exists. The pre-master secret key that is used in this process needs to interpreted by a server to create master secret key, whose process requires a big calculation, resulting in deteriorating system's transmission performance. Therefore, it is helpful in increasing transmission speed to reuse secret keys rather than to create them at every connection.

• Transactions on Electrical and Electronic Materials
• /
• v.18 no.5
• /
• pp.273-278
• /
• 2017

Recently, one of the areas where research is being actively conducted is the Internet of Things (IoT). The field of using the Internet of Things system is increasing, coupled with a remarkable increase of the use of the camera. However, general cameras used in the Internet of Things have limited viewing angles as compared to those available to the human eye. Also, cameras restrict observation of objects and the performance of observation. Therefore, in this paper, we propose a panoramic image stitching method using feature extraction and matching based on an embedded system. After extracting the feature of the image, the speed of image stitching is improved by reducing the amount of computation using the necessary information so that it can be used in the embedded system. Experimental results show that it is possible to improve the speed of feature matching and panoramic image stitching while generating a smooth image.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2323-2326
• /
• 2003

Theoretical analysis of the depth measurement system with the use of a single camera and a rotating mirror has hem done. A camera in front of a rotating mirror acquires a sequence of reflected images, from which depth information is extracted. For an object pint at a longer distance, the corresponding pixel in the sequence of images moves at a higher speed. In this paper, the principle d the depth measurement-based on the relation of the pixel movement speed and the depth of objects have been investigated. Also, necessary mathematics to implement the technique is derived and presented. The factors affecting the measurement precision have been studied Analysis shows that the measurement m increases with the increase of depth. The rotational angle of the mirror between two image-takings also affects the measurement precision. Experimental results using the real camera-mirror setup are reported.