• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.857-860
• /
• 2005

Several algorithms have been developed for the data processing of spotlight synthetic aperture radar (SAR). In particular, the range migration algorithm (RMA) does not assume that illuminating wavefronts are planar. Also, a high resolution image can be obtained by the RMA. This paper introduces an extension of the original RMA to enable a more efficient airborne SAR data processing. We consider more general motion and scene than the original RMA. The presented formulation is analyzed by using the principle of the stationary phase. Finally, the extended algorithm is tested with numerical simulations using the pulsed spotlight SAR.

• The Magazine of the IEIE
• /
• v.39 no.2
• /
• pp.45-54
• /
• 2012

Object detection is a fundamental task for many high-level computer vision applications such as image retrieval, scene understanding, activity recognition, visual surveillance and many others. Although object detection is one of the most popular problems in computer vision and various algorithms have been proposed thus far, it is also notoriously difficult, mainly due to lack of proper models for object representation, that handle large variations of object structure and appearance. In this article, we review a branch of object detection algorithms based on Support Vector Machines (SVMs), a well-known max-margin technique to minimize classification error. We introduce a few variations of SVMs-Structural SVMs and Latent SVMs-and discuss their applications to object detection and localization.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.9
• /
• pp.37-43
• /
• 2016

This paper introduces a method for video shot group detection needed for efficient management and summary of video. The proposed method detects shots based on low-level visual properties and performs temporal and spatial clustering based on visual similarity of neighboring shots. Shot groups created from temporal clustering are further clustered into small groups with respect to visual similarity. A set of representative shot frames are selected from each cluster of the smaller groups representing a scene. Shots excluded from temporal clustering are also clustered into groups from which representative shot frames are selected. A number of video clips are collected and applied to the method for accuracy of shot group detection. We achieved 91% of accuracy of the method for shot group detection. The number of representative shot frames is reduced to 1/3 of the total shot frames. The experiment also shows the inverse relationship between accuracy and compression rate.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.2_1
• /
• pp.217-223
• /
• 2023

With the rapid advancement of technologies, need for different research fields where this technology can be used is also increasing. One of the most researched topic in computer vision is object detection, which has widely been implemented in various fields which include healthcare, video surveillance and education. The main goal of object detection is to identify and categorize all the objects in a target environment. Specifically, methods of object detection consist of a variety of significant techniq ues, such as image processing and patterns recognition. Anomaly detection is a part of object detection, anomalies can be found various scenarios for example crowded places such as subway stations. An abnormal event can be assumed as a variation from the conventional scene. Since the abnormal event does not occur frequently, the distribution of normal and abnormal events is thoroughly imbalanced. In terms of public safety, abnormal events should be avoided and therefore immediate action need to be taken. When abnormal events occur in certain places, real time detection is required to prevent and protect the safety of the people. To solve the above problems, we propose a modified YOLOv5 object detection algorithm by implementing dilated convolutional layers which achieved 97% mAP50 compared to other five different models of YOLOv5. In addition to this, we also created a simple mobile application to avail the abnormal event detection on mobile phones.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.51-58
• /
• 2005

This paper proposes a robust scene change detection technique that uses the weighted chi-square test and the automated threshold-decision algorithms. The weighted chi-square test can subdivide the difference values of individual color channels by calculating the color intensities according to NTSC standard, and it can detect the scene change by joining the weighted color intensities to the predefined chi-square test which emphasize the comparative color difference values. The automated threshold-decision at algorithm uses the difference values of frame-to-frame that was obtained by the weighted chi-square test. At first, The Average of total difference values is calculated and then, another average value is calculated using the previous average value from the difference values, finally the most appropriate mid-average value is searched and considered the threshold value. Experimental results show that the proposed algorithms are effective and outperform the previous approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.629-634
• /
• 2008

디지털 영상 매체들이 등장한 후부터 장면전환 검출은 영상의 편집과 검색, 요약 등 여러 작업에 적용되기 위해 활발히 연구되어 왔다. 특히 디지털 방송이 MPEG2방식으로 송신되기 시작한 이후로 이러한 연구는 더욱 활발히 진행되었다. 그 결과로 MPEG2 영상에서 장면전환을 검출하기 위해서 압축영역에서의 검출법과 비압축영역에서의 검출법이 제시되었다. 특히 압축영역에서의 장면전환 검출방법은 전체를 디코딩하지 않고 장면전환을 빠르게 검색할 수 있는 방법들이 주로 등장되었다. 하지만, 이 방법들은 정확도가 떨어지거나 속력저하가 극심한 등 여러 가지 문제를 보였다. 따라서 우리는 좀 더 빠르고 정확도가 높은 장면전환 시점 검출을 위해서 GOP의 길이와 B 프레임의 용량 변화를 이용하고자 한다. 우리의 방법은 B 프레임의 용량 변화를 이용하여 장면 전환을 보다 빠르게 검색하고 보다 높은 정확도를 위해서 GOP 길이의 변화가 심한 곳을 추가로 지정하여 정확도를 보강한다. 이러한 방법은 기존의 장면전환 검출 방법보다 빠른 해결책이 된다. 그 뿐 아니라 정확도 면에서도 만족할만한 결과를 보여주고 있다. 본 논문에서 제시한 이러한 방법은 기존의 획일적인 방법에서 벗어나 MPEG2 영상내에서 좀 더 빠르고 정확한 장면검출을 위한 새로운 아이디어를 제공한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.889-894
• /
• 2009

Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection process is one of them. Shadow pixels are often misclassified as object pixels so that they cause errors in localization, segmentation, tracking and classification of objects. This paper proposes a novel cast shadow removal method. As opposed to previous conventional methods, which considers pixel properties like intensity properties, color distortion, HSV color system, and etc., the proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the background scene. Then, the product of the outcomes of application determines whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. The proposed method is simple but turns out practically very effective for Gaussian Mixture Model, which is verified through experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8C
• /
• pp.783-792
• /
• 2005

This paper proposes a feature extraction method for sketch-based image retrieval of animation character. We extract the specific regions using the detection of scene change and correlation points between two frames, and the property of animation production. We detect the area of focused similar colors in extracted specific region. And it is used as feature descriptor for image retrieval that focused color(FC) of regions, size, relation between FCs. Finally, an user can retrieve the similar character using property of animation production and user's sketch as a query Image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5583-5604
• /
• 2016

In this paper, we present a novel image operator to extract textual information in natural scene images. First, a powerful refiner called the Stroke Color Extension, which extends the widely used Stroke Width Transform by incorporating color information of strokes, is proposed to achieve significantly enhanced performance on intra-character connection and non-character removal. Second, a character classifier is trained by using gradient features. The classifier not only eliminates non-character components but also remains a large number of characters. Third, an effective extractor called the Character Color Transform combines color information of characters and geometry features. It is used to extract potential characters which are not correctly extracted in previous steps. Fourth, a Convolutional Neural Network model is used to verify text candidates, improving the performance of text detection. The proposed technique is tested on two public datasets, i.e., ICDAR2011 dataset and ICDAR2013 dataset. The experimental results show that our approach achieves state-of-the-art performance.