• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.499-508
• /
• 2004

The Smart Home or intelligent home network control system has the need for home devices to cooperate for the purpose of providing the automated services to residents. The cooperation of home devices can be defined as the service for residents that it controls simultaneously two or more home devices with the same purpose about user's control request of specific home device. A object of home device cooperation are the function object of home device, it is well defined in each device model in AHAM(Association of Home Appliance Manufactures) nth(Connected Home Appliances). AMAM CHA is to promote new appliance services and features enabled through networking by describing generic appliance models, objects, and high-level messages, but does not consider the description and process of cooperation between objects of each device model. This paper defines the cooperation relationship that could be discovered in among home devices, and proposes the cooperation model that AHAM objects could process the cooperation relationship.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.375-380
• /
• 2010

Most of previous algorithms of object boundary extraction have been studied for extracting the boundary of single object. However, multiple objects are much common in the real image. The proposed algorithm of extracting the boundary of each of multiple objects has two steps. In the first step, we propose the fast method using the outer and inner products; the initial contour including multiple objects is split and connected and each of new contours includes only one object. In the second step, an improved active contour model is studied to extract the boundary of each object included each of contours. Experimental results with various test images have shown that our algorithm produces much better results than the previous algorithms.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.17-22
• /
• 2009

DaVinci processors are popular media processors for implementing embedded multimedia applications. They support dual core architecture: ARM9 core for video I/O handling as well as system management and peripheral handling, and DSP C64+ core for effective digital signal processing. In this paper, we propose our efforts for optimal implementation of object tracking algorithm in DaVinci-based smart camera which is being designed and implemented by our laboratory. The smart camera in this paper is supposed to support object detection, object tracking, object classification and detection of intrusion into surveillance regions and sending the detection event to remote clients using IP protocol. Object tracking algorithm is computationally expensive since it needs to process several procedures such as foreground mask extraction, foreground mask correction, connected component labeling, blob region calculation, object prediction, and etc. which require large amount of computation times. Thus, if it is not implemented optimally in Davinci-based processors, one cannot expect real-time performance of the smart camera.

• Spatial Information Research
• /
• v.16 no.1
• /
• pp.51-64
• /
• 2008

Recently, development and research of u-City established the ubiquitous environment which can be anytime, anywhere computing or network, has been much highlighted. Thus, current urban facilities should be managed by ubiquitous concept, and monitored location and status information in a real-time manner, and controled if necessary. In order to be establish in the purpose of management, indirect mapping through id-tag is better than facility management directly. For instance, RFID, UCODE, UFID. In this paper, we propose that represent facility object through UOID(Unique Object IDentification). UOID comprises three parts; 1) sensing object, 2) facility object, 3) cell object consists of facilities. and Life cycle management system in UOID, and network system connected with internet is proposed. We wish that proposed UOID and network system mange u-City facilities effectively, and also provide ubiquitous service to the citizen, one of the integrate service of u-City platform.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.481-485
• /
• 1989

The object of this parer is on the design of an broad board classifier for connected. Korean digit. Many approaches have been applied in speech recognition systems: parametric vector quantization, dynamic programming and hiden Markov model. In the 80's the neural network method, which is expected to solve complex speech recognition problems, came bach. We have chosen the rule based system for our model. The phoneme-groups that we wish to classify are vowel_like, plosive_like fricative_like, and stop_like.The data used are 1380 connected digits spoken by three untrained male speakers. We have seen 91.5% classification rate.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1297-1309
• /
• 2016

In this paper, an efficient connected component labeling (CCL) method was proposed. The proposed method is based on GPU parallelism. The CCL is very important in various applications where images are analysed. However, the label of each pixel is dependent on the connectivity of adjacent pixels so that it is not very easy to be parallelized. In this paper, a GPU-based parallel CCL techniques were proposed and applied to the analysis of radar signal. Since the radar signals contains complex and large data, the efficiency of the algorithm is crucial when realtime analysis is required. The experimental results show the proposed method is efficient enough to be successfully applied to this application.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.245-249
• /
• 2010

In the stereo vision system, information about an object could be gained by searching through images. Edges which are based on the information about an object are used to find the position of the object and send a message of its position coordinate to a unmanned crain. This thesis proposes an algorithm to find the center point of the object's surface which is connected to the unmanned crain's arm, and to recognize the shape of the object by using two CCD cameras. At first, getting information about the edges, and distinguishing each edge's characteristics depend on user's option, and then find the location information by a set of positions that are proposed. This thesis is expected to be devoted to the development of an automation system of unmanned moving equipment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.8
• /
• pp.1767-1775
• /
• 2010

As factory automation is getting popular, there has been a lot of research concerned with stereo vision systems as a part of an automation system with unmanned moving equipment. In the stereo vision system, information about an object could be gained by searching through images. Edges which are based on the information about an object are used to find the position of the object and send a message of its position coordinate to a unmanned crain. This thesis proposes an algorithm to find the center point of the object's surface which is connected to the unmanned crain's hookblock, and to recognize the shape of the object by using two CCD cameras. At first, getting information about the edges, and distinguishing each edge's characteristics depend on user's option, and then find the location information by a set of positions that are proposed. This thesis is expected to be devoted to the development of an automation system of unmanned moving equipment.