• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.407-418
• /
• 2023

The Multi-Object Goal Visual Navigation(MultiOn) is a visual navigation task in which an agent must visit to multiple object goals in an unknown indoor environment in a given order. Existing models for the MultiOn task suffer from the limitation that they cannot utilize an integrated view of multimodal context because use only a unimodal context map. To overcome this limitation, in this paper, we propose a novel deep neural network-based agent model for MultiOn task. The proposed model, MCFMO, uses a multimodal context map, containing visual appearance features, semantic features of environmental objects, and goal object features. Moreover, the proposed model effectively fuses these three heterogeneous features into a global multimodal context map by using a point-wise convolutional neural network module. Lastly, the proposed model adopts an auxiliary task learning module to predict the observation status, goal direction and the goal distance, which can guide to learn the navigational policy efficiently. Conducting various quantitative and qualitative experiments using the Habitat-Matterport3D simulation environment and scene dataset, we demonstrate the superiority of the proposed model.

• Korea Science and Art Forum
• /
• v.29
• /
• pp.279-292
• /
• 2017

This study was started by recognizing that visual storytelling(VST) is an important factor that determines the success of the work. The goal of this study is to analyze the VST study approaching from the narrative and visual dimension by analyzing the conflict intensity and VST factor. Therefore, in this paper, we analyzed the conflicts of the theater animation(4) that succeeded in the worldwide success and attempted the VST interpretation by approaching it technically. The results and contents of the study are as follows. Firstly, based on the narrative theory of Sung bong-Sun and Robert McKee, we classified the conflict scenes and found the kinds of conflicts. In addition, based on the 5B model, a total of 108 conflict shots were extracted. Secondly, through expert experiment, we found the conflict intensity of conflict shots. Thirdly, the visual elements of fifteen significant conflicts were extracted from internal and super individual conflicts. Fourth, as a result of the experiment, it was confirmed that the reliability of the visual elements in the inner and super personal conflicts was in the range of 100-83.33%, and the frequency of usage was found to be widely distributed in 5.88-70.59% and 5-70%. This means that the VST expression, which relied on the sense of the artist, can be engineered. Finally, I expect that it will be the basis of the development of the VST Tool which can predict the conflict expression of the work in the animation pre - production stage successfully.

• Journal of Digital Convergence
• /
• v.12 no.9
• /
• pp.343-351
• /
• 2014

This study poses questions on the role of a movie sequences partially deployed in the comic strips style in the movie. Though both the movie and the comic strips's image is expressed in the flat space, it is different to the reciever's manner in the interpretation of the media's narrative. Comic strip has a media's characteristic of the aggressive interpretation. It can be create the objective and critic point of view for an audience as the visual style in the ideology movie. Comic strip Style has a flat frame, a form of comic strip's mise-en-scene, montage and camera working. This paper studies expression of 'La Chinoise' using 'Comic strip style' for the objective point of view.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.1
• /
• pp.41-48
• /
• 2009

This Paper introduces representation and coding schemes of multiview texture and depth data for complex three-dimensional scenes. We represent input color and depth images using compressed texture and depth map pairs. The proposed X-codec encodes them further to increase compression ratio in a near-lossless way. Our system resolves two problems. First, rendering time and output visual quality depend on input image resolutions rather than scene complexity since a depth image-based rendering techniques is used. Second, the random access problem of conventional image-based rendering could be effectively solved using our image block-based compression schemes. From experimental results, the proposed approach is useful to graphics applications because it provides multiview rendering, selective decoding, and scene manipulation functionalities.

• Journal of the Korean Society of Costume
• /
• v.58 no.8
• /
• pp.170-183
• /
• 2008

The purpose of this study is to analyze the characteristics of different images of movie costume centering on the actresses. The perfect examples are the characters from the movie "The Devil Wears Prada", in which the film is about the fashion leaders of the world. This study consists of visual data as well as images including some scenes from the movie. The sources were collected from relative media, articles in journals, internet sites relating to the movies and photos and we have analyzed differentiated each of the character's wardrobes and its characteristics appearing in each image. The result of this study is as follows. First, the characteristic image of Andy, the main character (Anne Hathaway) in the movie changed dramatically. Andy'swardrobe is focused on the character's makeover in the movie as the character changes from a slob dresser to an assistant of the editor-in-chief of the number one fashion magazine in the world. Each scene definitely shows different styles of the latest premier designers' clothes and accessories. On the other hand, Miranda Priestly appears as the fashion leader and icon throughout the whole movie. Her career look in each scene was very chic and sophisticated in the office while her party dresses were sexy and glamorous in the movie where she was at many of the promotion parties and events. The second analysis of characteristic images of movie costumes is comparing the styles of Andy, Miranda and Emily(the other assistant of Miranda). Andy's wardrobe was divided Into two situations-before working for the magazine and while working for Miranda. As Andy's wardrobe began to upscale, the clothing images of Emily and Miranda became less fashionable. As a result of this study, the movie costumes played a vital role in expressing the changes and differentiating each character's images.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.554-568
• /
• 2005

We suggest the dynamic stroke generation algorithm that provides frame-to-frame coherence in 3D non-photorealistic animations. We use 3D particle system to eliminate the visual popping effect in the animated scene. Since we have located particles on the 3D object's surface, the coherence is maintained when the object or the camera is moving in the scene. Also, this algorithm maintains the coherence when camera is zooming in/out. However, the brush strokes on the surface also zoom in/out. This result(too large or too small brush strokes) can not represent hand-crafted brush strokes. To remove this problem, we suggest stroke generation algorithm that dynamically maintains the number of brush stroke and its size during camera zoom in/out.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.512-515
• /
• 2009

In this paper, we propose layout based multimodal contents authoring tool for Digilog Book. In authoring step, users create a virtual area using mouse or pen-type device and select property of the area repetitively. After finishing authoring step, system recognizes printed page number and generate page layout including areas and property information. Page layout is represented as a scene graph and stored as XML format. Digilog Book viewer loads stored page layout and analyze properties then augment virtual contents or execute functions based on area. Users can author visual and auditory contents easily by using hybrid interface. In AR environment, system provides area templates in order to help creating area. In addition, proposed authoring tool separates page recognition module from page tracking module. So, it is possible to author many pages using only single marker. As a result of experiment, we showed proposed authoring tool has reasonable performance time in AR environment. We expect that proposed authoring tool would be applicable to many fields such as education and publication.

• The Journal of the Korea Contents Association
• /
• v.16 no.9
• /
• pp.569-579
• /
• 2016

, 2007 firm by Joe Wright, deals with tragic love of Cecilia and Robbie. While the 2001 novel of the same name focuses on Briony narrative the movie is seen through romantic relationship of two lovers. However, Briony's narrative in the movie helps to accent the two's love story. The director's emphasis on the love story is unfortunately from Briony tragic story. The continuous build up of misunderstanding and irreconcilable regrets begins to materialize and explodes in the middle of the film. The director manages to use just one day and uses the same location to illustrate the background of the characters as well as build up of the plot's misunderstanding. The study will focus on the beginning of the film that enabled the beautiful love story through effect and symbolic visual expression and techniques- especially the use of mise-en-scene, camera movement, framing, and lighting and how it emphasis and use of specific color and sound.

• Korean Journal of Optics and Photonics
• /
• v.19 no.2
• /
• pp.95-102
• /
• 2008

An advantage of parallax barrier displays is that they can also display 2D and 3D contents and can be automatically switched between the two types. But, as the viewer changes position, different views of the scene will be directed by the barrier to the visual system. Moving horizontally beyond a certain point will produce "image flipping" of the different views of the scene. These limitations make unavoidable the use of another autostereoscopic display solutions like eye tracking or increasing the number of views. In this paper, a method of the moving parallax barrier design is introduced to supplement a disadvantage of the fixed parallax barrier that provides observation at specific locations. For making the moving parallax barrier, the cross connector with 640 lines FPC is designed. A commercially available web camera is utilized to implement eye-tracking system and shows the experimental result.

• Journal of architectural history
• /
• v.6 no.3 s.13
• /
• pp.129-143
• /
• 1997

The perspective representation and its effect that appeared in the tombs and mural paintings of koguryo are summarized as follows: First, The inside structure of the tombs is likely to show the deepness effect, placing each function in the front and both sides centering around the mane pillars and creating the boundaries and the spaces that have various visibility between the inside and outside spaces of the structure just like a traditional Korean house shows. In addition, The deepness effect is emphasized by suggesting that the spaces are countinued with a storage attached behind the main house or by forming the level and deployment in a narrow space like the scene that a large array is looked out from the main house. Second, The deepness effect is expressed by making the form of ceiling turn to a vertical space of an ascending image, constructing it just as the lotus lamp ceiling of a wooden architecture or drawing it just like the imaginary heavenly world with the sun the moon and mythical fairies and animals spread in it. Thried, The perspective effect is disclosed by drawing the mural pictures in an equally set bird's-eye view without regard to the disfance proportion according to the conceptual visualization which is not a visual penetration, adopting the multiple view points and moving view points that are moving around as an important manner of seeing. Fourth, The deepness effect is emphasized through the scene of changing spaces when they are looked out far or looked into depending on a viewpoint of the daily life by forming the fromes of paintings that we made up with actual pillars, Du Gong, crossbeams or that are painted in most tombs. Fifth, The rich spatial senses are reflected by originating the characters of the three directions, level, deployment and ascending. An example which can support the conclusion of this study can be given here. that is, the construction ground plan of a dwelling house of a nobleman at the end of Koguryo as a remain which was excavated at Dongdae Ja in Jip An.