• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.410-421
• /
• 2016

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.

• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.465-475
• /
• 2007

With the spread of Internet, web users express their daily life by articles, pictures and cartons to recollect personal memory or to share their experience. For the easier recollection and sharing process, this paper proposes diverse cartoon generation methods using the landmark lists which represent the behavior and emotional status of the user. From the priority and causality of each landmark, critical landmark is selected for composing the cartoon scenario, which is revised by story ontology. Using similarity between cartoon images and each landmark in the revised scenario, suitable cartoon cut for each landmark is composed. To make cartoon story more diverse, weather, nightscape, supporting character, exaggeration and animation effects are additionally applied. Through example scenarios and usability tests, the diversity of the generated cartoon is verified.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.31-40
• /
• 2012

This paper proposes a visual landmark, and presents a parking assistance system using the landmarks. The visual landmark is a feature corresponding to the parking slots, it must be selected considering the parking lot's environment. The parking lot has simple repetitive pattern environment without noticeable features. The previous landmarks are not proper to the parking lot's environment. We propose the visual landmark for this environment. We estimate the vehicle's location using the proposed landmarks, and expect the vehicle's trajectory according to the vehicle's state. The system's inputs are images from the camera fixed to the vehicle. The presented system estimates the vehicle's location using the input images, and assists a driver through displaying the expected vehicle's trajectory from the steering angle. The experimental results showed the proposed landmark's performance and the parking assistance system's performance.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.90-101
• /
• 2012

The landmark selection is crucial to successful perform in SLAM(Simultaneous Localization and Mapping) with a mono camera. Especially, in unknown environment, automatic landmark selection is needed since there is no advance information about landmark. In this paper, proposed visual attention system which modeled human's vision system will be used in order to select landmark automatically. The edge feature is one of the most important element for attention in previous visual attention system. However, when the edge feature is used in complicated indoor area, the response of complicated area disappears, and between flat surfaces are getting higher. Also, computation cost increases occurs due to the growth of the dimensionality since it uses the responses for 4 directions. This paper suggests to use a corner feature in order to solve or prevent the problems mentioned above. Using a corner feature can also increase the accuracy of data association by concentrating on area which is more complicated and informative in indoor environments. Finally, this paper will prove that visual attention system based on corner feature can be more effective in SLAM compared to previous method by experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.63-69
• /
• 2020

In this paper, we propose an indoor positioning technique using the landmark based on relative Access Point (AP) signal strengths. The absolute values of AP signals are used to conventional indoor positioning technologies, but they may be different because of the difference of the measuring device, the measuring environment, and the timing of the measurements. However, we found the fact that the flow of the AP's RSSI in certain places shows almost constant patterns. Based on theses characteristics, we identify the relative strength between the APs and store the certain places as landmarks where they show certain patterns. Once the deployment of the landmark map is complete, system calculate position of user using the IMU sensor of smartphone and calibrate it with stored landmarks. Our system shows 75.2% improvement over technology that used only sensors, and 39.6% improvement over technology that used landmarks that were selected with absolute values.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.736-747
• /
• 2006

Simultaneous Localization and Map Building(SLAM) is one of the fundamental problems in robot navigation. The Extended Kalman Filter(EKF), which is widely adopted in SLAM approaches, requires extensive computation. The conventional particle filter also needs intense computation to cover a high dimensional state space with particles. This paper proposes an efficient SLAM method based on the recursive unscented Kalman filtering in an environment including a large number of landmarks. The posterior probability distributions of the robot pose and the landmark locations are represented by their marginal Gaussian probability distributions. In particular, the posterior probability distribution of the robot pose is calculated recursively. Each landmark location is updated with the recursively updated robot pose. The proposed method reduces filtering dimensions and computational complexity significantly, and has produced very encouraging results for navigation experiments with noisy multiple simultaneous observations.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.313-315
• /
• 2024

본 논문에서는 이미지 검색기를 통한 랜드마크 인식 방법을 제안한다. 특정 랜드마크 데이터세트에서 라벨링을 하지 않은 비지도 학습을 통해서 이미지에서 랜드마크의 클래스 분류를 위한 특징을 추출한다. 학습된 모델을 랜드마크 데이터세트인 Paris6k 데이터세트와 Oxford5k 데이터세트에 적용하여 랜드마크 인식 정확도를 확인하였다. 성능과 속도를 강화하기 위해 이미지 특징 추출 모델로 ResNet 대신에 YOLO에서 사용된 CSPDarknet-53을 사용하여 모델의 크기를 줄이고 랜드마크 인식 정확도를 높였다. 그리고 모델로부터 추출된 특징의 수를 줄여 이미지 검색 시 소요되는 시간을 감소시켰다. 학습된 모델로 rOxford5k 데이터 세트에 적용 시 mAP 80.37, rParis6k에서 mAP 89.07을 얻었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.3
• /
• pp.296-301
• /
• 2011

This paper deals with the simultaneous localization and mapping system using cooperative robot. For recognizing environment, swarm robot uses the ultrasonic sensors and vision sensor. Ultrasonic sensors measure the distance information, and vision sensor recognizes the predefined landmark. we used SURF with excellent quality and fast matching in order to recognize landmark. Due to measurement error of sensors, we fusion them using particle filter for accurate localization and mapping. Finally, we show the feasibility of the proposed method through some experiments.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.1-6
• /
• 2021

The purpose of this study is to improve the performance of the artificial neural network system for facial image analysis through the image landmark selection technique. For landmark selection, a CNN-based multi-layer ResNet model for classification of facial image age is required. From the configured ResNet model, a heat map that detects the change of the output node according to the change of the input node is extracted. By combining a plurality of extracted heat maps, facial landmarks related to age classification prediction are created. The importance of each pixel location can be analyzed through facial landmarks. In addition, by removing the pixels with low weights, a significant amount of input data can be reduced.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.155-156
• /
• 2009