• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.39-47
• /
• 2020

In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.263-271
• /
• 2016

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.192-199
• /
• 2020

Recently, the utilization of the object tracking algorithm based on the deep learning model is increasing. A system for tracking multiple objects in an image is typically composed of a chain form of an object detection algorithm and an object tracking algorithm. However, chain-type systems composed of several modules require a high performance computing environment and have limitations in their application to actual applications. In this paper, we propose a method that enables real-time operation in low-performance computing environment by adjusting the computational process of object detection module in the object detection-tracking chain type system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.1027-1030
• /
• 2013

For the detection of objects in the videos, there are various ways that use the frequency transformation. In the videos, the images of objects could be changed slightly. Object detection methods using frequency transformation such as ASEF and MOSSE have the ability to renew the detection filter in order to deal with the change of object images. But these approaches are likely to fail the detection because the image changes often occur when they come out again after being hidden by other objects. What is worse, when they show up again, they appear in another place, not the original one. In this paper, a new proposal is present so that the detection can be carried out efficiently even when the images come out in other place, and the failure of the detection can be reduced.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.844-847
• /
• 2014

본 논문에서는 다양한 형태의 어플리케이션 중 스마트폰에 탑재된 카메라를 이용하여 명함을 인식할 때 발생하는 문제점을 해결하기 위한 기법을 제시하고자 한다. 스마트폰의 카메라를 이용하여 이미지를 얻을 경우 카메라의 각도에 따라 객체의 모양이 변형된다. 명함인식에서 이러한 이미지 왜곡문제는 인식률에 많은 영향을 미친다. 본 논문에서는 카메라의 각도에 따른 이미지의 왜곡 문제를 해결하기 위해 캐니 에지를 이용하여 객체를 검출하고, 검출된 객체의 간단한 정보를 이용하여 명함 영역을 검출하고, 영역 내에 명함을 검출하는 기법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1378-1380
• /
• 2015

본 논문은 흉부 CT 영상을 활용하여 폐결절을 자동으로 검출하는 알고리즘에 관한 연구내용을 담고 있다. 폐 결절 자동 검출을 위해 폐 CT 영상 내에 있는 객체를 검출하고, 검출된 객체의 특징들 중, 이동성 및 기하학적 특징을 가지고 폐혈관과 폐결절을 구분하였다. 실험한 영상은 폐결절이 있는 26명의 원광대학교 병원 환자의 흉부 CT 영상을 사용하였으며, 그 결과 96.15%의 정확도와 3.54 False Positves / Scan이 발생하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.371-373
• /
• 2015

This paper describes an analysis of hardware design conditions of moving object detection algorithm which is based on effective Gaussian mixture learning (EGML). The simulation model of EGML algorithm is implemented using OpenCV, and it is analyzed that the effects of parameter values on background learning time and moving object detection sensitivity for various images. In addition, optimal design conditions for hardware implementation of EGML-based MOD algorithm are extracted from fixed-point simulations for various bit-width parameters.

• 전자공학회논문지 IE
• /
• v.43 no.2
• /
• pp.30-38
• /
• 2006

This paper is used the color space distribution HMMD model presented in MPEG-7 in order to segment and detect the wanted image parts as a real time without the user's manufacturing in the video object segmentation. Here, it is applied the wavelet morphology to remove a small part that is regarded as a noise in image and a part excepting for the face image. Also, it did the optimal composition by the rough set. In this paper, tile proposed video object detection algorithm is confirmed to be superior as detecting the face object exactly than the conventional algorithm by applying those to the different size images.put the of paper here.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.97-99
• /
• 2022

Recently, the amount of data is increasing with the development of industries and technologies. Research on the processing and transmission of large amounts of data is attracting attention. Therefore, in this paper, compressed sensing was used to reduce the amount of data and its effect on Mask R-CNN algorithm was analyzed. We confirmed that as the compressed sensing rate increases, the amount of data in the image and the resolution decreases. However, it was confirmed that there was no significant degradation in the performance of object detection.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.81-86
• /
• 2003

In this paper, we propose the tracking method of moving object which use extracted object by difference between background image and target image in fixed domain. As a extraction method of object, calculate not pixel of full image but predefined some edge pixel of image to get a position of new object. Since the center area Is excluded from calculation, the extraction time is efficiently reduced. To extract object in the predefined area, get a starting point in advance and then extract size of width and height of object. Central coordinate is used to track moved object.