• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.455-461
• /
• 2002

Object-based image retrieval method is addressed. A new image segmentation algorithm and image comparing method between segmented objects are proposed. For image segmentation, color and texture features are extracted from each pixel in the image. These features we used as inputs into VQ (Vector Quantization) clustering method, which yields homogeneous objects in terns of color and texture. In this procedure, colors are quantized into a few dominant colors for simple representation and efficient retrieval. In retrieval case, two comparing schemes are proposed. Comparing between one query object and multi objects of a database image and comparing between multi query objects and multi objects of a database image are proposed. For fast retrieval, dominant object colors are key-indexed into database.

• Journal of Elementary Mathematics Education in Korea
• /
• v.19 no.4
• /
• pp.527-544
• /
• 2015

Storytelling is one of the important features in the elementary school mathematics textbooks of the 2009 revised curriculum. In particular, the whole 'comparing objects' unit in the first grade mathematics textbook is based on storytelling method. In this study, we investigate the contents of the stories and the mathematical activities in the 'comparing objects' unit from both mathematical and character educational viewpoints. Based on our investigations, we analyze educational problems on teaching and learning mathematics as storytelling, suggest reconstructed alternative mathematical activities, and drew their educational implications.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.219-222
• /
• 2001

Moving objects in video data are main elements for video analysis and retrieval. In this paper, we propose a new algorithm for tracking and segmenting moving objects in color image sequences that include complex camera motion such as zoom, pan and rotating. The Proposed algorithm is based on the Mean-shift color segmentation and stochastic region matching method. For segmenting moving objects, each sequence is divided into a set of similar color regions using Mean-shift color segmentation algorithm. Each segmented region is matched to the corresponding region in the subsequent frame. The motion vector of each matched region is then estimated and these motion vectors are summed to estimate global motion. Once motion vectors are estimated for all frame of video sequences, independently moving regions can be segmented by comparing their trajectories with that of global motion. Finally, segmented regions are merged into the independently moving object by comparing the similarities of trajectories, positions and emerging period. The experimental results show that the proposed algorithm is capable of segmenting independently moving objects in the video sequences including complex camera motion.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1994.04a
• /
• pp.527-534
• /
• 1994

This paper presents a Bin-Picking method in which robot recognizes the positions and orientations of unoccluded objects at the top of jumbled objects placed in a bin, and picks up the unoccluded objects one by one from the jumble. A method using feasible region, painting, and hierarchical test is introduced for recognizing the unoccluded objects from the jumbled objects. The 3D information is obtained using the bipartite-matching method which finds the least difference of 3D by comparing vertexes of one camera with vertexes of the other camera, then hypothesis and test are done. The working order of unoccluded objects is made based on 3D, position, and orientation information. The robot picks up the unoccluded objects from the jumbled objects according to the working order. This all process continues to the empty bin.

• Journal of Sensor Science and Technology
• /
• v.33 no.2
• /
• pp.78-85
• /
• 2024

We proposed a method for visual place recognition that represents images using objects as visual words. Visual words represent the various objects present in urban environments. To detect various objects within the images, we implemented and used a zero-shot detector based on a large-scale image language model. This zero-shot detector enables the detection of various objects in urban environments without additional training. In the process of creating histograms using the proposed method, frequency-based weighting was applied to consider the importance of each object. Through experiments with open datasets, the potential of the proposed method was demonstrated by comparing it with another method, even in situations involving environmental or viewpoint changes.

• Journal of KIBIM
• /
• v.4 no.4
• /
• pp.13-23
• /
• 2014

After being introduced, Building Information Modeling (BIM) has been actively applied to the cost estimation of construction projects, and various studies on BIM based quantity take-off have been carried out. In practice, however, these calculations take considerable time, because BIM based quantity take-off is further conducted along with 2D-based quantity take-off. Studies on the quantity take-off using BIM spatial objects have been carried out on early stages of projects, but how this method differs from the existing quantity take-off method and how accurate it is in comparison have rarely been verified. Therefore, by comparing 2D based quantities with quantities through BIM spatial objects, this study analyzed the accuracy of quantity take-off using BIM spatial objects. To this end, the properties of BIM spatial objects and quantity calculable spatial types were analyzed, and existing 2D-based quantities and quantities extracted from BIM spatial objects were compared through a case study. As a result, the quantity of spatial objects found to be more by about 7.13% in 0.05% and therefore, this difference should be considered during quantity take-off using BIM spatial objects. Through the results of this study, we can improve the accuracy of quantity take-off using BIM spatial objects in the early stage of a construction project.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.5
• /
• pp.510-516
• /
• 2015

This paper describes an approach to detect interesting objects using satellite images. This paper focuses on the interesting objects that have common special patterns but do not have identical shapes and sizes. The previous technologies are still insufficient for automatic finding of the interesting objects based on operation of special pattern analysis. In order to overcome the circumstances, this paper proposes a methodology to obtain the special patterns of interesting objects considering their common features and their related characteristics. This paper applies MSER(Maximally Stable Extremal Regions) for the region detection and corner detector in order to extract the features of the interesting object. This paper conducts a case study and obtains the experimental results of the case study, which is efficient in reducing processing time and efforts comparing to the previous manual searching.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.155-160
• /
• 2022

In recent years, Unreal Engine has been increasingly included in the animation process produced in the studio. In this case, there will be more than one of main software, and it is very important to accurately transfer data between the software and Unreal Engine. In animation data, not only the animation data of the character but also the animation data of objects interacting with the character must be individually produced and transferred. Most of the objects that interact with the character have a condition of constraints with the part of character. In this paper, I tried to stipulate the production process for extracting animation data of constrained objects, and to analyze why users experience difficulties due to the complexity of the regulations in the process of executing them. And based on the flowchart prescribed for user convenience, I created a program using a Python script to prove the user's convenience. Finally, by comparing the results generated according to the manual flowchart with the results generated through the script command, it was found that the data were consistent.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.4_2
• /
• pp.1001-1007
• /
• 2024

Recent deep learning algorithms for object detection in real-time play a crucial role in various applications such as autonomous driving, traffic monitoring, health care, and water quality monitoring. The size of small objects, in particular, significantly impacts the accuracy of detection models. However, data containing small objects can lead to underfitting issues in models. Therefore, this study developed a deep learning model capable of quickly detecting small objects to provide more accurate predictions. The RE-SOD (Residual block based Small Object Detector) developed in this research enhances the detection performance for small objects by using RGB separation preprocessing and residual blocks. The model achieved an accuracy of 1.0 in image classification and an mAP50-95 score of 0.944 in object detection. The performance of this model was validated by comparing it with real-time detection models such as YOLOv5, YOLOv7, and YOLOv8.

• The Research Journal of the Costume Culture
• /
• v.9 no.5
• /
• pp.770-782
• /
• 2001

The definite objects of this study are as follows; 1. The study presents the methods of the designing collar pattern and bodice pattern by each concrete object after comparing and analyzing the factors among the features which are in need of clothes designing. 2. The object of this study is to make body-suitable ready-made clothes by comparing and analyzing the methods of designing collar pattern and bodices pattern presented by each concrete objects and Bunka Pattern. The results of this study are as follows; 1 . The results of this study developed the body-suitable bodice pattern of bend-forward type, straight type and lean-back type Compared with the Bunka pattern by physical function test, this study was rated high in the aspects of the shape of neck and shoulder. 2. The collar pattern was designed according to each type. The front center rising point of straight type is 2.5cm, lean-back type is 3.0cm and bend-forward type is 1.5cm. Compared with the Bunka pattern by physical function test, this study is rated high in the aspects of the shape. To confirm the increase and change of the measure definitely, the complete examination of each subject is necessary. This developed and investigated pattern must be supplemented more by comparing and analyzing with other pattern and body types.