• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.115-124
• /
• 2022

In this paper, YOLO and EAST models are tested to analyze their performance in text area detecting for real-world and normal text images. The earl ier YOLO models which include YOLOv3 have been known to underperform in detecting text areas for given images, but the recently released YOLOv4 and YOLOv5 achieved promising performances to detect text area included in various images. Experimental results show that both of YOLO v4 and v5 models are expected to be widely used for text detection in the filed of scene text recognition in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.2
• /
• pp.358-363
• /
• 2009

Text region detection from the natural scene images used in a variety of applications, many research are needed in this field. Recent research methods is to detect the text region using various algorithm which it is combination of edge based and connected component based. Therefore, this paper proposes an text region detection using edge and regional minima/maxima transformation algorithm from natural scene images, and then detect the connected components of edge and regional minima/maxima, labeling edge and regional minima/maxima connected components. Analysis the labeled regions and then detect a text candidate regions, each of detected text candidates combined and create a single text candidate image, Final text region validated by comparing the similarity and adjacency of individual characters, and then as the final text regions are detected. As the results of experiments, proposed algorithm improved the correctness of text regions detection using combined edge and regional minima/maxima connected components detection methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3858-3874
• /
• 2021

As an essential part of the urban transportation system, precise perception of the traffic flow parameters at the traffic signal intersection ensures traffic safety and fully improves the intersection's capacity. Traditional detection methods of road traffic flow parameter can be divided into the micro and the macro. The microscopic detection methods include geomagnetic induction coil technology, aerial detection technology based on the unmanned aerial vehicles (UAV) and camera video detection technology based on the fixed scene. The macroscopic detection methods include floating car data analysis technology. All the above methods have their advantages and disadvantages. Recently, indoor location methods based on wireless signals have attracted wide attention due to their applicability and low cost. This paper extends the wireless signal indoor location method to the outdoor intersection scene for traffic flow parameter estimation. In this paper, the detection scene is constructed at the intersection based on the received signal strength indication (RSSI) ranging technology extracted from the wireless signal. We extracted the RSSI data from the wireless signals sent to the road side unit (RSU) by the vehicle nodes, calibrated the RSSI ranging model, and finally obtained the traffic flow parameters of the intersection entrance road. We measured the average speed of traffic flow through multiple simulation experiments, the trajectory of traffic flow, and the spatiotemporal map at a single intersection inlet. Finally, we obtained the queue length of the inlet lane at the intersection. The simulation results of the experiment show that the RSSI ranging positioning method based on wireless signals can accurately estimate the traffic flow parameters at the intersection, which also provides a foundation for accurately estimating the traffic flow state in the future era of the Internet of Vehicles.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.1-13
• /
• 2009

Scene classification and concept-based procedures have been the great interest for image categorization applications for large database. Knowing the category to which scene belongs, we can filter out uninterested images when we try to search a specific scene category such as beach, mountain, forest and field from database. In this paper, we propose an adaptive segmentation method for real-world natural scene classification based on a semantic modeling. Semantic modeling stands for the classification of sub-regions into semantic concepts such as grass, water and sky. Our adaptive segmentation method utilizes the edge detection to split an image into sub-regions. Frequency of occurrences of these semantic concepts represents the information of the image and classifies it to the scene categories. K-Nearest Neighbor (k-NN) algorithm is also applied as a classifier. The empirical results demonstrate that the proposed adaptive segmentation method outperforms the Vogel and Schiele's method in terms of accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4A
• /
• pp.356-363
• /
• 2002

Video scene segmentation is fundamental role for content based video analysis and many kinds of scene segmentation schemes have been proposed in previous researches. However, there is a problem, which is to find optimal threshold value according to various kinds of movies and its content because only fixed single threshold value usually used for cut detection. In this paper, we proposed the variable dynamic threshold method, which change the threshold value by a probability distribution of cut detection interval and information of frame feature differences and cut detection interval in previous cut detection is used to determine the next cut detection. For this, we present a cut detection algorithm and a parameter generation method to change the threshold value in runtime. We also show the proposed method, which can minimize fault alarm rate than the existing methods efficiently by experimental results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.912-928
• /
• 2019

Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1157-1163
• /
• 2005

In this paper, an efficient and fast method to segment a video in the MPEG(motion picture expert group) video stream is proposed. For the real time processing of large amount of broadcasting data, we use DC images of I-frames in an MPEG compressed video with minimal decoding. Using the modified histogram comparison which counts on not only luminance but also chrominance information, the scene change detection was performed in the fast and accurate way Also, to discriminate anchorperson frame from non-anchor frame, a neural network method was introduced.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.103-104
• /
• 2014

본 논문에서는 범죄 행위중 하나인 흡연을 엘리베이터 내에서 행하는 범죄자를 추출하고자 한다. 추출 방법은 변형된 컬러-$X^2$ 히스토그램을를 이용하여 차이값을 추출하고 정규화를 수행한다. 그러고 나서 4-단계의 장면 전환 검출 알고리즘을 이용하여 연속적인 프레임들에서 장면 전환이 발생한 지점을 찾아낸다. 끝으로, 비디오에 저장된 대량의 영상에서 흡연 영상의 검색 및 추출을 위한 방법을 제시한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.179-180
• /
• 2009

We propose the method of analysis, separation, and express from normalized and standard method to reduce the problem with the existing scene change detection and the complicated and variety of images of real change. In this paper, we propose a new local ${\lambda}^2$-test which was combined the ${\lambda}^2$-existing test methods and local color histograms. This method is robust method of abrupt and gradual detection and solve the problem of traditional method.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.1-8
• /
• 2021

Coronavirus disease 2019 (COVID-19) has affected the world seriously. Every person is required for wearing a mask properly in a public area to prevent spreading the virus. However, many people are not wearing a mask properly. In this paper, we propose an efficient mask detection system. In our proposed system, we first detect the faces of input images using YOLOv5 and classify them as the one of three scene complexity classes (Simple, Moderate, and Complex) based on the number of detected faces. After that, the image is fed into the Faster-RCNN with the one of three ResNet (ResNet-18, 50, and 101) as backbone network depending on the scene complexity for detecting the face area and identifying whether the person is wearing the mask properly or not. We evaluated our proposed system using public mask detection datasets. The results show that our proposed system outperforms other models.