• ETRI Journal
• /
• v.39 no.4
• /
• pp.502-513
• /
• 2017

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

• Culinary science and hospitality research
• /
• v.11 no.4 s.27
• /
• pp.228-244
• /
• 2005

The objective of the study is to observe cooks first from the kitchen and those who care health and to grasp the impression regarding the kitchen environment. Also, it grasped the recognition degree of cooks against the elements of kitchen ventilation and kitchen ventilation equipments. We surveyed against 385 cooks who work in the kitchen of special grade hotels and family restaurants, used 5 scales for the object, and executed the analysis. The results of this study are as follows: (1) Health condition of the cooks appeared most highly pain in the shoulder and the neck. (2) for the impression regarding the kitchen environment, temperature was high and the insufficiency of ventilation is answered highly. (3) The importance of kitchen ventilation of cooks was recognized very high. (4) The combustion gas was recognized as very high percentage and the most effective element of the kitchen on the human body to remove first inside the kitchen. (5) Most cooks were recognized that the improvement of ventilation equipments is necessary. (6) The object of ventilation equipments is appeared to maintain comfortable kitchen environment. (7) The optimum operation method of ventilation equipment uses the automatic system of ventilation equipment from the kitchen and it is necessary to maintain the optimum. This research is based on preceding studies, investigating special grade hotels and family restaurants in Seoul. The ventilation plan of the kitchen should be accomplished to improve the health of cooks and productivity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1479-1484
• /
• 2005

This paper represents an intelligent sensor controller of mobile robot for object recognition in an indoor hon environment. A range finder sensor module has been developed by using optic PSD (Position Sensitive Detector) sensor way at a low Vice. While PSD sensor is cost effective and light weighting, it has switching noise and white noise. To remove these noises, we propose a heuristic filter. For line-based map building. also we prorosed advanced Hough transformation and navigation algorithm. Some experiments were illustrated for the validity of the developed system.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.386-398
• /
• 2020

We developed an integrative annotation program that can perform data labeling process for deep learning models in object recognition. The program utilizes the basic GUI library of Python and configures crawler functions that allow data collection in real time. Retinanet was used to implement an automatic annotation function. In addition, different data labeling formats for Pascal-VOC, YOLO and Retinanet were generated. Through the experiment of the proposed method, a domestic vehicle image dataset was built, and it is applied to Retinanet and YOLO as the training and test set. The proposed system classified the vehicle model with the accuracy of about 94%.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.2
• /
• pp.419-434
• /
• 2020

The purpose of the study is to design and propose metadata standard for building AI training dataset of landmark images. In order to achieve the purpose, we first examined and analyzed the state of art of the types of image retrieval systems and their indexing methods, comprehensively. We then investigated open training dataset and machine learning tools for image object recognition. Sequentially, we selected metadata elements optimized for the AI training dataset of landmark images and defined the input data for each element. We then concluded the study with implications and suggestions for the development of application services using the results of the study.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.4
• /
• pp.13-20
• /
• 2016

It is possible to implement an optical character recognition system using a high-resolution camera mounted on smart phones in the modern society. Further, characters extracted from the implemented application is possible to provide the voice service for the visually impaired person by using TTS. But, it is difficult for the visually impaired person to properly shoot the objects that character information are included, because it is very hard to accurately understand the current state of the object. In this paper, we propose a method of inducing an appropriate shooting for the visually impaired persons by using a smartphone gyro sensor. As a result of simulation using the implemented program, we were able to see that it is possible to recognize the more character from the same object using the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.191-194
• /
• 2005

This paper represents an intelligent sensor controller of mobile robot for object recognition in an indoor known environment. A range finder sensor module has been developed by using optic PSD (Position Sensitive Detector) sensor array at a low price. While PSD sensor is cost effective and light weighting, it has switching noise and while noise. To remove these noises, we propose a heuristic filter. For line-based map building, also we proposed advanced Hough transformation and navigation algorism. Some experiments were illustrated for the validity of the developed system.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.1-11
• /
• 2022

Recently, research on license plate recognition, which is a core technology of an intelligent transportation system(ITS), is being actively conducted. In this paper, we propose a method to extract numbers and characters from low-quality license plate images by applying the YOLOv4 algorithm. YOLOv4 is a one-stage object detection method using convolution neural network including BACKBONE, NECK, and HEAD parts. It is a method of detecting objects in real time rather than the previous two-stage object detection method such as the faster R-CNN. In this paper, we studied a method to directly extract number and character regions from low-quality license plate images without additional edge detection and image segmentation processes. In order to evaluate the performance of the proposed method we experimented with 500 license plate images. In this experiment, 350 images were used for training and the remaining 150 images were used for the testing process. Computer simulations show that the mean average precision of detecting number and character regions on vehicle license plates was about 93.8%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.479-480
• /
• 2022

고속으로 차량이 주행하는 도로에서 정지 차량이나 낙하물은 큰 사고를 유발하기에 이에 대한 대처 방안이 요구되고 있다. 갑작스런 정지 차량의 경우 예상 불가능하며, 낙하물은 순찰대를 편성하여 주기적으로 수거하고 있으나 즉각적인 대응이 어렵다. 해당 문제 해결을 위해 본 논문에서는 딥러닝 실시간 객체인식기술을 적용하여 정지 차량 및 도로 위 낙하물을 인식하며 이에 대한 정보를 제공하는 시스템을 개발하였다. 실시간 객체인식 알고리즘인 YOLOX와 실시간 객체추적기술인 deepSORT 알고리즘을 데스크톱 PC에 적용하여 구현하였다. 개발한 시스템은 정지 차량 및 낙하물에 대한 인식 결과를 제공한다. 기존 설치된 CCTV 영상을 대상으로 시스템 적용이 가능하여 저비용으로 넓은 지역에 대한 도로 위험 상황 인식을 기대할 수 있다.

• Journal of KIISE
• /
• v.41 no.10
• /
• pp.838-846
• /
• 2014

Three-dimensional (3D) object retrieval from user-drawn sketch queries is one of the important research issues in the areas of pattern recognition and computer graphics for simulation, visualization, and Computer Aided Design. The performance of content-based 3D object retrieval system depends on the availability of effective descriptors and similarity measures for this kind of data. In this paper, we present a sketch-based 3D object retrieval system by extracting a hybrid edge descriptor which is robust against rotation and translation. The experimental results which are based on HTML5 and WebGL show that proposed sketch-based 3D object retrieval method is very efficient to search and order the 3D objects according to user's intention.