• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1447-1453
• /
• 2020

In this paper, we propose a method for no-reference quality assessment of sports videos using 3D shearlet transform and deep residual neural networks. In the proposed method, 3D shearlet transform-based spatiotemporal features are extracted from the overlapped video blocks and applied to logistic regression concatenated with a deep residual neural network based on a conditional video block-wise constraint to learn the spatiotemporal correlation and predict the quality score. Our evaluation reveals that the proposed method predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.7
• /
• pp.70-78
• /
• 1992

In this paper, an approach for 3-D object segmentation and classification, which is based on eigen-values of polynomial function as their surface features, using neural network is proposed. The range images of 3-D objects are classified into surface primitives which are homogeneous in their intrinsic eigenvalue properties. The misclassified regions due to noise effect are merged into correct regions satisfying homogeneous constraints of Hopfield neural network. The proposed method has advantage of processing both segmentation and classification simultaneously.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.939-941
• /
• 1999

Recognition rates of 3-D underwater object using the SCL neural network and the SOFM neural network were 91.8% and 95.9%, respectively.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.8-15
• /
• 2018

This paper proposes a convolutional neural network model for distinguishing areas occupied by obstacles from a LiDAR image converted from a 3D point cloud. The channels of a LiDAR image used as input consist of the distances to 3D points, the reflectivities of 3D points, and the heights of 3D points from the ground. The proposed model uses a LiDAR image as an input and outputs a result of a segmented LiDAR image. The proposed model adopts refinement modules with skip connections to segment a LiDAR image. The refinement modules with skip connections in the proposed model make it possible to construct a complex structure with a small number of parameters than a convolutional neural network model with a linear structure. Using the proposed model, it is possible to distinguish areas in a LiDAR image occupied by obstacles such as vehicles, pedestrians, and bicyclists. The proposed model can be applied to recognize surrounding obstacles and to search for safe paths.

• Electrical & Electronic Materials
• /
• v.9 no.8
• /
• pp.825-830
• /
• 1996

In this study, Characteristics of Ultrasonic Transducer fabricated with porous piezoelectric resonator, 3-D underwater object restoration using the self made ultrasonic transducer and modified SCL(Simple Competitive Learning) neural network are investigated. The self-made transducer was satisfied the required condition of ultrasonic transducer in water, and the modified SCL neural network using the acquired object data 16*16 low resolution image was used for object restoration of $32{\times}32$ high resolution image. The experimental results have shown that the ultrasonic transducer fabricated with porous piezoelectric resonator could be applied for SONAR system.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.3
• /
• pp.166-173
• /
• 2005

Preserving image features, edges and details in the process of impulsive noise filtering is an important problem. To avoid image blurring, only corrupted pixels must be filtered. In this paper, we propose an effective impulse noise detection method using Self-Organizing Neural Network(SONN) which applies median filter selectively for removing random-valued impulse noises while preserving image features, edges and details. Using a $3\times3$ window, we obtain useful local features with which impulse noise patterns are classified. SONN is trained with sample image patterns and each pixel pattern is classified by its local information in the image. The results of the experiments with various images which are the noise range of $5-15\%$ show that our method performs better than other methods which use multiple threshold values for impulse noise detection.