• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.8
• /
• pp.1819-1826
• /
• 2010

This paper proposes the image segmentation algorithm to extracts a fish object from a fish image for fish image retrieval. The conventional algorithm using gray level similarity causes wrong image segmentation result in the boundary area of the object and the background with similar gray level. The proposed algorithm uses the reinforced edge and the adaptive block-based threshold for the boundary area with weak contrast and the virtual object to improve the eroded or disconnected object in the boundary area without contrast. The simulation results show that the percentage of extracting the visual-fine object from the test images is under 90% in the conventional algorithm while it is 97.7% in the proposed algorithms.

• The Journal of the Korea Contents Association
• /
• v.7 no.3
• /
• pp.68-78
• /
• 2007

In a virtual aquarium, the behavior of fish objects is the most important factor in respect of visual effects. In addition to the individual behavior of fish object, the interactions between objects due to their attributes, can improve the dynamics and reality of the virtual world. In this paper, we analyze the principal habits of fish objects such as the vitality, the range of movement, the maximum depth of water they can live, and the cycle of eating. Then, we suggest a method for simulating the stable marine ecosystem with controlling the behaviors, the interaction with other species, the average span of life, and all that sort of thing based on the result of analysis. Because we can freely modify the behavior of fish object by altering the values of attributes, it can be utilized in the dynamic virtual aquarium, the 3D aquarium screen saver, and the virtual fish game, and so on.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.528-532
• /
• 2006

In a cyber aquarium, the behavior of fish objects is the most important factor in respect of visual effects. In this paper, we analyze the principal habits of fish objects such as the vitality, the range of movement, the maximum depth of water they can live, and the cycle of eating. Then, we suggest a method for simulating the stable marine ecosystem with controlling the behaviors, the interaction with other species, the average span of life, and all that sort of thing based on the result of analysis. Because we can freely modify the behavior of fish object by altering the values of attributes, it can be utilized in the dynamic cyber aquarium, the 3D aquarium screen saver, and the cyber fish game, and so on.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.552-560
• /
• 2021

Currently, the domestic aquaculture industry is pursuing smartization, but it is still proceeding with human subjective judgment in many processes in the aquaculture stage. The prerequisite for the smart aquaculture industry is to effectively grasp the condition of fish in the farm. If real-time monitoring is possible by identifying the number of fish populations, size, pathways, and speed of movement, various forms of automation such as automatic feed supply and disease determination can be carried out. In this study, we proposed an algorithm to identify the state of fish in real time using underwater video data. The fish detection performance was compared and evaluated by applying the latest deep learning-based object detection models, and an algorithm was proposed to measure fish object identification, path tracking, and moving speed in continuous image frames in the video using the fish detection results. The proposed algorithm showed 92% object detection performance (based on F1-score), and it was confirmed that it effectively tracks a large number of fish objects in real time on the actual test video. It is expected that the algorithm proposed in this paper can be effectively used in various smart farming technologies such as automatic feed feeding and fish disease prediction in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.5
• /
• pp.1005-1010
• /
• 2012

The Augmented Reality, as a technology caught the spotlight as a next generation's technology of inserting 3D virtual objects in the space of reality seen through the camera, can maximize the learning effects by inducing user's absorption and interest using interaction between user and objects. Recently, as the movile devices having excellent mobility and portability are generalized, the diversified augmented reality are introduced using mobile devices. In this article, a 3D fish encyclopedia system augmented from the mobile environment was designed to provide the user with learning contents focusing on the sense of absorption and an interest. This system is intened to provide helps to learn about the fishes by recognizing the pictures of fishes in the encyclopedia as marker, bringing out the 3D model stored in server and displaying in the mobile environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.415-420
• /
• 2010

Due to the improvement in PC performance and the development of computer graphics technology, high quality computer animation in various industrials is on the rise. This study suggests pivot interpolation to realize the process of expressing dynamic and natural motion of fish, the key of expressing the ocean landscape through the morphing technique. By applying fish tail motion, this study solves unnatural speed of the previous morphing technique and realizes the realistic swimming way without simple motion.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.759-764
• /
• 2009

With its rapid growth, the digital contents-related industry is drawing attention as an industry generating a high value added. Specifically, the 3D morphing technology often used in the appearance or movement of each object comprising contents makes it possible to compose various contents by inferring the appearance and movement of the object. For a realistic swimming appearance of fish by using fish that swim in the water, this paper proposes a technique that applies the same speed concept as a physical pendulum to a swimming cycle and applies a frame morphing technique that is able to express the growth process from fry to adult fish. This article is capable of realistically reviving the fish growth process, and can through magnified applying can be applied to in 3D fishes encyclopedias or virtual underwater expressions etc. in the viewpoint which is oceanography.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.653-657
• /
• 2008

Industry related to digital contents is growing rapidly and is noticed as a higher value-added business. In digital reflex contents industry, computer graphics techniques are core techniques. Because they make production or scene that is difficult to photograph possible with real camera, expand a range of contents making. Lately, computer graphics techniques apply various fields such as blockbuster movie, game, educational contents, simulation etc, and there are many studies about movement of each object made up of contents or automation of object change. This paper shows the process of fishes growth, from spawn to a full-grown fish making use of 3D morphing techniques and want to plan fish growth process system that can know difference between fishes that are applied to 3D morphing techniques and normal full-grown fishes according to various environmental factors that affect growth.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.83-90
• /
• 2010

In this paper, we use VR technologies including touch processing technologies and haptic devices to offer touch of fish objects to users. The Omni, a kind of haptic device and made by Sensable Inc., is used to implement multi touch model in VR space. In addition, Matlab/Simulink and proSENSE Virtual Touch Toolbox of Handshake Inc., are used as programing tools. Functions needed to describe the movement of x, y, and z axis respectively are applied to delineate the natural movement of fish objects modeled with 3D. Such movements offer realistic physical interactions to two users controlling multi point respectively. In experiment, to perceive the appearance of 3D object by touch and to feel the respiration by touch are well conducted. We also verify that it is possible to develop games or contents through multi participation in VR Space by using multi point.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.322-330
• /
• 2021

In modern aquaculture, mass mortality is a very important issue that determines the success of aquaculture business. If a fish disease is not detected at an early stage in the farm, the disease spreads quickly because the farm is a closed environment. Therefore, early detection of diseases is crucial to prevent mass mortality of fish raised in farms. Recently deep learning-based automatic identification of fish diseases has been widely used, but there are many difficulties in identifying objects due to insufficient images of fish diseases. Therefore, this paper suggests a method to generate a large number of fish disease images by synthesizing normal images and disease images using SinGAN deep learning model in order to to solve the lack of fish disease images. We generate images from the three most frequently occurring Paralichthys Olivaceus diseases such as Scuticociliatida, Vibriosis, and Lymphocytosis and compare them with the original image. In this study, a total of 330 sheets of scutica disease, 110 sheets of vibrioemia, and 110 sheets of limphosis were made by synthesizing 10 disease patterns with 11 normal halibut images, and 1,320 images were produced by quadrupling the images.