• 대한인간공학회지
• /
• 제23권1호
• /
• pp.23-38
• /
• 2004

This study examines different types of navigation aids when a navigator performs target search tasks in Virtual Environments. The factors manipulated in this study include target information (None/Landmark). navigational difficulty (Easy/Difficult). and map types (None/2D Map/3D Map). Navigation performance was measured by using task completion time and the number of target locations that was remembered by the navigator. In addition, user satisfaction on the navigation aids was also measured by using a 7-point Likert's scale. The results showed that the user satisfaction on the landmark was high when the 3D Map was provided. The task completion time shortened when navigational difficulty was set at "easy." The number of remembered target locations was large when there was no landmark. It was also large with an easy navigation task. or a map (20 or 3D) provided. Guidelines for selecting navigation aids were proposed based on the results.

• 아동학회지
• /
• 제32권1호
• /
• pp.51-69
• /
• 2011

This study examined how young children understand representational relations between referents and their representational objects. Ninety-four children aged 2- to 4.5-years of age were individually tested; firstly in the scale-model tasks, and then in the scale-map tasks. Data were analyzed both by means of Chi-Square test and by a more descriptive, micro analysis. According to the results, there were significant age differences in the understanding of representational relations, regardless of the type of representational objects. In the descriptive, micro analysis, it was found that before 3 years of age, young children have a great deal of difficulties in understanding representational relations. More importantly, young children under three seemed unable to understand representational relations, especially when the similarities as well as the differences between the representational object and the referent were very high. These results suggest that teachers of very young children need to select representational materials carefully, taking into consideration children's understanding of representational relations.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• 아동학회지
• /
• 제33권5호
• /
• pp.53-70
• /
• 2012

The purpose of this study was to investigate the effects of task conditions (physical similarity between the spatial product and the reference space, presentation place of the spatial product) on children's spatial representation. The participants consisted of 40 3-year-olds and 40 4-year-olds. The results of this study are as follows. Both 3-year-olds and 4-year-olds were capable of a greater degree of spatial representation when there was a high level of physical similarity between the spatial product and the reference space, and when the presentation place of the spatial product was in the reference space. 4-year-olds were capable of more accurate spatial representation than 3-year-olds. There was no significant difference in the children's spatial representation depending on the type of spatial product (scale model, map). The results revealed that the physical similarity between the spatial product and the reference space and the presentation place of the spatial product are essential in young children's spatial representation. Additionally, the results indicated that spatial representation of children develops gradually from when they are three to when they turn four.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1477-1491
• /
• 2017

Inspired by the multi-scale nature of hippocampal place cells, a biologically inspired model based on a multi-scale spatial representation for goal-directed navigation is proposed in order to achieve robotic spatial cognition and autonomous navigation. First, a map of the place cells is constructed in different scales, which is used for encoding the spatial environment. Then, the firing rate of the place cells in each layer is calculated by the Gaussian function as the input of the Q-learning process. The robot decides on its next direction for movement through several candidate actions according to the rules of action selection. After several training trials, the robot can accumulate experiential knowledge and thus learn an appropriate navigation policy to find its goal. The results in simulation show that, in contrast to the other two methods(G-Q, S-Q), the multi-scale model presented in this paper is not only in line with the multi-scale nature of place cells, but also has a faster learning potential to find the optimized path to the goal. Additionally, this method also has a good ability to complete the goal-directed navigation task in large space and in the environments with obstacles.

• 한국멀티미디어학회논문지
• /
• 제18권9호
• /
• pp.1098-1104
• /
• 2015

With the widespread use of smartphones and IoT (Internet of Things), data are being generated on a large scale, and there is increased for the analysis of such data. Hence, distributed processing systems have gained much attention. Hadoop, which is a distributed processing system, saves the metadata of stored files in name nodes; in this case, the main problems are as follows: the memory becomes insufficient; load occurs because of massive small files; scheduling and file processing time increases because of the increased number of small files. In this paper, we propose a solution to address the increase in processing time because of massive small files, and thus improve the processing performance, using the Reuse JVM method provided by Hadoop. Through environment setting, the Reuse JVM method modifies the JVM produced conventionally for every task, so that multiple tasks are reused sequentially in one JVM. As a final outcome, the Reuse JVM method showed the best processing performance when used together with CombineFileInputFormat.

• 항공우주시스템공학회지
• /
• 제18권2호
• /
• pp.56-63
• /
• 2024

무인 이동체의 안전성이 점차 증대되면서 빌딩과 같은 장애물이 많은 도심환경에서의 무인 이동체의 활용이 증가할 것으로 예상된다. 도심 환경에서 다수의 무인 이동체가 운용될 경우, 임무 할당 뿐만 아니라 정적 및 동적 장애물 회피와 더불어 상호 충돌 회피가 가능한 경로를 생성하는 알고리듬이 필요하다. 본 논문에서는 임무 할당 및 경로 계획을 수행하는 알고리듬을 제안한다. 장애물 및 경로 계획을 효율적으로 수행하기 위해 맵을 격자 기반으로 구성한 다음 경로를 도출하였다. 동적인 환경에서 빠르게 재계획하기 위해 계산 시간 단축에 집중하였다. 시뮬레이션을 통해 작은 규모의 문제에서 장애물 회피 및 상호 충돌 회피 방안에 대해 설명하였고, 큰 규모의 문제에서 임무 전체 종료 시간(Makespan)을 관찰하여 성능을 확인하였다.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.785-796
• /
• 2019

Due to the view point, illumination, personal gait and other background situation, person re-identification across cameras has been a challenging task in video surveillance area. In order to address the problem, a novel method called Joint Bayesian across different cameras for person re-identification (JBR) is proposed. Motivated by the superior measurement ability of Joint Bayesian, a set of Joint Bayesian matrices is obtained by learning with different camera pairs. With the global Joint Bayesian matrix, the proposed method combines the characteristics of multi-camera shooting and person re-identification. Then this method can improve the calculation precision of the similarity between two individuals by learning the transition between two cameras. For investigating the proposed method, it is implemented on two compare large-scale re-ID datasets, the Market-1501 and DukeMTMC-reID. The RANK-1 accuracy significantly increases about 3% and 4%, and the maximum a posterior (MAP) improves about 1% and 4%, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• 한국지리정보학회지
• /
• 제20권4호
• /
• pp.115-125
• /
• 2017

현재 국가기본도는 국토 전역에 동일한 축척과 정확도로 제작하여 배포됨으로서 국토개발 GIS, 차량용 내비게이션 등 각종 주제도 및 신속한 공간정보 산업에 의사결정용으로 다양한 분야에 활용되고 있으며 공간정보 산업의 전반적인 확대를 위해 많은 연구와 정책을 제시하고 있다. 이에 따른 일환으로 공간정보의 최신성에 대한 문제점을 해소하기 위해 전국을 권역으로 나누어 기본도를 수정했던 것을 2013년부터는 상시 수정으로 정책 변경하여 공간정보의 최신성 확보에 일조하고 있다. 따라서 본 연구에서는 현재 많은 연구와 다양한 산업에서 각광받고 있는 드론(Drone)을 활용하여 국가기본도의 수정 및 갱신 가능성을 평가하였다. 특히 저가형 드론에서 취득한 정사영상정보와 3차원 점군(Point Clouds)을 수치지형도와 중첩하여 3차원 위치정보를 동시에 취득하여 수정 갱신업무에 적용한 결과 0.2m 정밀도와 0.1m의 정확도를 나타내고 있다. 이는 국가 기본도(축척: 1/5,000) 제작 작업규정의 오차범위를 준수하고 있어 수치지도 수정 갱신 업무까지도 충분이 활용이 가능한 것으로 판단된다.