• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1670-1683
• /
• 2017

Mitotic event recognition is a crucial and challenging task in biomedical applications. In this paper, we introduce the slow feature analysis and propose a fully-automated mitotic event recognition method for cell populations imaged with time-lapse phase contrast microscopy. The method includes three steps. First, a candidate sequence extraction method is utilized to exclude most of the sequences not containing mitosis. Next, slow feature is learned from the candidate sequences using slow feature analysis. Finally, a hidden conditional random field (HCRF) model is applied for the classification of the sequences. We use a supervised SFA learning strategy to learn the slow feature function because the strategy brings image content and discriminative information together to get a better encoding. Besides, the HCRF model is more suitable to describe the temporal structure of image sequences than nonsequential SVM approaches. In our experiment, the proposed recognition method achieved 0.93 area under curve (AUC) and 91% accuracy on a very challenging phase contrast microscopy dataset named C2C12.

• Journal of Satellite, Information and Communications
• /
• v.10 no.3
• /
• pp.16-21
• /
• 2015

In this paper, we presented Under Vehicle Inspection System by comparing two image signals. Two signals are generated by license plate number and under-vehicle pattern recognition. The test shows reliable precision within real-time of 2.8sec, which can be applicable commercially. In the future, more research will be conducted to enhance the precision by automatic image balance in many challenging situations.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.199-204
• /
• 2008

Visual surveillance is an active topic recently in Computer Vision. Event detection and recognition is one important and useful application of visual surveillance system. In this paper, we propose a new method to recognize the entering and exiting events based on the human's movement feature and the door's state. Without sensors, the proposed approach is based on novel and simple vision method as a combination of edge detection, motion history image and geometrical characteristic of the human shape. The proposed method includes several applications such as access control in visual surveillance and computer vision fields.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.987-994
• /
• 2018

In this paper, an automatic transmission system of traffic information is presented. Here, a traffic event is defined as an obstacle to an emergency vehicle such as an ambulance or a fire truck. When a traffic event is detected from a video recorded by a black box installed in a vehicle, the implemented system automatically transmits a proof image and corresponding information to the control center through an e-mail. For this purpose, we realize an algorithm of identifying the numbers and a character from the license plate, and an algorithm for determining the occurrence of a traffic event. To report the event, a function for automatic transmission of the text and image files through e-mail and file transfer protocol (FTP) is also appended. Therefore, if the traffic event is extended and applied to the presented system, it will be possible to establish a convenient reporting system for the violation of various traffic regulations. In addition, it will contribute to significantly reduce the number of traffic violations against the regulations.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.4
• /
• pp.47-57
• /
• 2009

Event detection and recognition is an active and challenging topic recent in Computer Vision. This paper describes a new method for recognizing events caused by human motion from video sequences in an office environment. The proposed approach analyzes human motions using Motion History Image (MHI) sequences, and is invariant to body shapes. types or colors of clothes and positions of target objects. The proposed method has two advantages; one is thant the proposed method is less sensitive to illumination changes comparing with the method using color information of objects of interest, and the other is scale invariance comparing with the method using a prior knowledge like appearances or shapes of objects of interest. Combined with edge detection, geometrical characteristics of the human shape in the MHI sequences are considered as the features. An advantage of the proposed method is that the event detection framework is easy to extend by inserting the descriptions of events. In addition, the proposed method is the core technology for event detection systems based on context-aware computing as well as surveillance systems based on computer vision techniques.

• The KIPS Transactions:PartB
• /
• v.18B no.3
• /
• pp.109-116
• /
• 2011

In this paper, we introduce non-touch style interface system technology without any touch style controlling mechanism, which is called as "Air-interface". To develop this system, we used the full reflection principle of infrared (IR) light and then user's hand is separated from the background with the obtained image at every frame. The segmented hand region at every frame is used as input data for an hand-motion recognition module, and the hand-motion recognition module performs a suitable control event that has been mapped into the specified hand-motion through verifying the hand-motion. In this paper, we introduce some developed and suggested methods for image processing and hand-motion recognition. The developed air-touch technology will be very useful for advertizement panel, entertainment presentation system, kiosk system and so many applications.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.219-222
• /
• 2009

최근 컴퓨터비젼 분야에서 이벤트 검출 및 인식이 활발히 연구되고 있으며, 도전적인 주제들 중 하나이다. 이벤트 검출 기술들은 많은 감시시스템들에서 유용하고 효율적인 응용 분야이다. 본 논문에서는 사무실 환경에서 발생할 수 있는 이벤트의 검출 및 인식을 위한 방법을 제안한다. 제안된 방법에서의 이벤트는 입장( entering), 퇴장(exiting), 착석(sitting-down), 기립(standing-up)으로 구성된다. 제안된 방법은 하드웨어적인 센서를 사용하지 않고, MHI(Motion History Image) 시퀀스(sequence)를 이용한 인간의 모션 분석을 통해 이벤트를 검출할 수 있는 방법이며, 사람의 체형과 착용한 옷의 종류와 색상, 그라고 카메라로부터의 위치관계에 불변한 특성을 가진다. 에지검출 기술을 HMI 시퀀스정보와 결합하여 사람 모션의 기하학적 특징을 추출한 후, 이 정보를 이벤트 인식의 기본 특징으로 사용한다. 제안된 방법은 단순한 이벤트 검출 프레임웍을 사용하기 때문에 검출하고자 하는 이벤트의 설명만을 첨가하는 것으로 확장이 가능하다. 또한, 제안된 방법은 컴퓨터비견 기술에 기반한 많은 감시시스템에 적용이 가능하다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.6
• /
• pp.177-186
• /
• 2020

Recent advances in deep learning technology have improved image recognition performance in the field of computer vision, and serverless computing is emerging as the next generation cloud computing technology for event-based cloud application development and services. Attempts to use deep learning and serverless computing technology to increase the number of real-world image recognition services are increasing. Therefore, this paper describes how to develop an efficient deep learning based image recognition service system using serverless computing technology. The proposed system suggests a method that can serve large neural network model to users at low cost by using AWS Lambda Server based on serverless computing. We also show that we can effectively build a serverless computing system that uses a large neural network model by addressing the shortcomings of AWS Lambda Server, cold start time and capacity limitation. Through experiments, we confirmed that the proposed system, using AWS Lambda Serverless Computing technology, is efficient for servicing large neural network models by solving processing time and capacity limitations as well as cost reduction.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.313-322
• /
• 2020

The recognition of the risk hazards is a vital step to effectively prevent accidents on a construction site. The advanced development in computer vision systems and the availability of the large visual database related to construction site made it possible to take quick action in the event of human error and disaster situations that may occur during management supervision. Therefore, it is necessary to analyze the risk factors that need to be managed at the construction site and review appropriate and effective technical methods for each risk factor. This research focuses on analyzing Occupational Safety and Health Agency (OSHA) related to risk zone identification rules that can be adopted by the image recognition technology and classify their risk factors depending on the effective technical method. Therefore, this research developed a pattern-oriented classification of OSHA rules that can employ a large scale of safety hazard recognition. This research uses joint reasoning of risk zone Identification and numeric input by utilizing a stereo camera integrated with an image detection algorithm such as (YOLOv3) and Pyramid Stereo Matching Network (PSMNet). The research result identifies risk zones and raises alarm if a target object enters this zone. It also determines numerical information of a target, which recognizes the length, spacing, and angle of the target. Applying image detection joint logic algorithms might leverage the speed and accuracy of hazard detection due to merging more than one factor to prevent accidents in the job site.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.3153-3158
• /
• 2014

Children in schoolzone accidents occur frequently in order to actively respond to the situation on the module for automated recognition research. By the vehicle penetration such like schoolzone, child object recognition, and GPS coordination information, the monitoring scenario can be constructed, and if an event occurs corresponding to strategic scenario so that suitable reaction can be provided to increase safety level to the schoolzone. In this paper, a GPS sensor and the image sensor and the monitoring server on the network based on the integration of context-aware methods have been studied. The image sensor section and the GPS section through analysis of the situation analysis and recognition of the object based on the scenario can actively cope with the situation according to the methods proposed.