• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.663-668
• /
• 2003

This paper presents a new observation system which is useful to observe the scene of the remote controlled robot vision. This system is composed of a motionless camera and head motion detector with a motion sensor. The motionless camera has a fish eye lens and is for observing a hemisphere space. The head motion detector has a motion sensor is for defining an arbitrary subspace of the hemisphere space from fish eye lens. Thus processing the angular information from the motion sensor appropriately, the direction of face is estimated. However, since the fisheye image is distorted, it is unclear image. The partial domain of a fish eye image is selected by head motion, and this is converted to perspective image. However, since this conversion enlarges the original image spatially and is based on discrete data, crevice is generated in the converted image. To solve this problem, interpolation based on an intensity of the image is performed for the crevice in the converted image (space problem). This paper provides the experimental results of the proposed observation system with the head motion detector and perspective image conversion using the proposed conversion and interpolation methods, and the adequacy and improving point of the proposed techniques are discussed.

• Fisheries and Aquatic Sciences
• /
• v.5 no.3
• /
• pp.212-218
• /
• 2002

The response behavior of a fish school to an approaching vessel was observed using scanning sonar. The evaluation using six parameters, which signify characteristics of school shape and behavior by sonar image processing, was proposed. Ten fish schools were analyzed and among them, three fish schools were identified for their changing shape, swimming direction, and swimming speed. Moreover, by tracing fish schools on stack of sonar images, these fish schools were seen to exhibit an apparent change of school shape and behavior. Therefore, the evaluation method of fish school behavior using six characteristic parameters indicating fish school shape and behavior by sonar image processing is useful.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4C
• /
• pp.226-231
• /
• 2011

To improve the conventional illustrated fish book, this paper introduces the concept of an electronic illustrated fish book which applies IT techniques to the conventional one, and proposes the image retrieval for it. The image retrieval is a core technology of the electronic illustrated fish book and make it overwhelm the conventional one. Since fishes, even if the same kind, have different features in shape, color, and texture and the same fish can even have different features by its pose or environment at that time for taking a picture, the conventional image retrieval, that uses simple features in shape, color, and texture, is not suitable for the electronic illustrated fish book. The proposed image retrieval adopts detail shape features extracted from head, body, and tail of a fish and different weights are given to the features depending on their invariability. The simulation results show that the proposed algorithm is far superior to the conventional algorithm.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.161-164
• /
• 2007

The paper studies in the wide-angle lens and distortion tendency and employs the correction techniques suitable to the fish-eye lens using the existing photographic survey methods. After carrying out the calibration of the the fish-eye lens, we calculated the correction parameters, and then developed the method that convert the original image-point to new image-point correcting distortion. The objectives of suggested calibration method in this paper are to calibrate the image of the the fish-eye lens used in the computer-vision and the control-instrumentation field widely. The proposed technique expects to improve the accuracy of the image of the fish-eye lens in the indoor tracking and monitoring field. Also the referenced cross point auto-extraction program is embodied for improving efficiency of the lens correction techniques. Consequently, this calibration method would be applied to the automated distorting correction method on not only the fish-eye lens also general lens.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4866-4888
• /
• 2020

One major and time-consuming task in fish production is obtaining an accurate estimate of the number of fish produced. In most Nigerian farms, fish counting is performed manually. Digital image processing (DIP) is an inexpensive solution, but its accuracy is affected by noise, overlapping fish, and interfering objects. This study developed a catfish recognition and counting algorithm that introduces detection before counting and consists of six steps: image acquisition, pre-processing, segmentation, feature extraction, recognition, and counting. Images were acquired and pre-processed. The segmentation was performed by applying three methods: image binarization using Otsu thresholding, morphological operations using fill hole, dilation, and opening operations, and boundary segmentation using edge detection. The boundary features were extracted using a chain code algorithm and Fourier descriptors (CH-FD), which were used to train an artificial neural network (ANN) to perform the recognition. The new counting approach, based on the geometry of the fish, was applied to determine the number of fish and was found to be suitable for counting fish of any size and handling overlap. The accuracies of the segmentation algorithm, boundary pixel and Fourier descriptors (BD-FD), and the proposed CH-FD method were 90.34%, 96.6%, and 100% respectively. The proposed counting algorithm demonstrated 100% accuracy.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.111-118
• /
• 2003

This paper proposes a two dimensional behavior analysis method for fish in a water tank based on the ARX method and the Kalman filter algorithm using image processing technology. In modeling the behavior of fish, the input is denoted as the environmental change and uses M-sequence. The output is expressed by the partnership between fish. The behavior model of individual fish is identified by the ARX method. It is then estimated by the Kalman filter algorithm. Finally, the fish behavior is analyzed by FFT. To prove the effectiveness of the pro-posed algorithm, it is applied to two tilapias in a water tank with dimensions of 100cm$\times$100cm$\times$50cm. The effectiveness of the proposed method is demonstrated through ARX identification, estimation of Kalman filter, and FFT analysis.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.51 no.1
• /
• pp.16-25
• /
• 2015

Visual census and hydro-acoustic survey was carried out at Ulju small scale marine ranching area (MRA) to estimate demersal fish aggregations on September and November 2013. In this hydro-acoustic survey, the authors combined an image sonar with a scientific echo sounder to monitor an underwater situation and compare two acoustic data. Consequently, visual census survey was useful to estimate fish species composition for hydro-acoustic survey, because it is easy to identify aggregated fish species and overcome limits on a fishing depth and ability of an conventional fishing gear like a bottom gill-net or a fish trap at marine ranching area. Mean fish density was estimated as $0.757g/m^2$ on September and $0.219g/m^2$ on November and Fish abundance was finally calculated as 1.51ton (coefficient of variation, CV=13.1%) on September and 0.44ton (CV=47.7%) on November, respectively. Hydro-acoustic survey combined with the image sonar was useful to monitor fish aggregations and estimate fish stocks around artificial reefs at shallow coastal MRA. We were able to easily identify the underwater structures like an artificial reef and a fishing rope as well as fish aggregations from image sonar data. Therefore, the method was effective to separate unwanted echo signals in acoustic data of scientific echo sounder.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.31 no.3
• /
• pp.317-322
• /
• 1998

Generally, the conventional fish size grading methods just adopt the mechanical technique. So the grading methods have a problem such that the graded fish is easy to hurt on the skin and in the internal organs. In this paper, a fish size grading machine is developed using an image processing method. The grading method is based on the principal axis theorem. The length and projected area of a fish are obtained by getting the principal axis and the product of inertia moment on the captured image of a target fish. The developed machine uses an uncontact technique that the target fishes go through the front side of the CCD camera. So the above stated problem can be improved. The performance of this method is discussed with the experimental results.

• Journal of information and communication convergence engineering
• /
• v.18 no.2
• /
• pp.106-114
• /
• 2020

We propose appropriate criteria for obtaining fish species data and number of learning data, as well as for selecting the most appropriate convolutional neural network (CNN) to efficiently classify exotic invasive fish species for their extermination. The acquisition of large amounts of fish species data for CNN learning is subject to several constraints. To solve these problems, we acquired a large number of fish images for various fish species in a laboratory environment, rather than a natural environment. We then converted the obtained fish images into fish images acquired in different natural environments through simple image synthesis to obtain the image data of the fish species. We used the images of largemouth bass and bluegill captured at a pond as test data to confirm the effectiveness of the proposed method. In addition, to classify the exotic invasive fish species accurately, we evaluated the trained CNNs in terms of classification performance, processing time, and the number of data; consequently, we proposed a method to select the most effective CNN.