• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 추계학술대회
• /
• pp.126-128
• /
• 2022

경량화 기법 중 하나인 Knowledge distillation 은 최근 object detection task 에 적용되고 있다. Knowledge distillation 은 3 가지 범주로 나뉘는데 그들 중에서 Self-Knowledge distillation 은 기존의 Knowledge distillation 에서의 pre-trained teacher 에 대한 의존성 문제를 완화시켜준다. Self-Knowledge distillation 또한 object detection task 에 적용되어 training cost 를 줄이고 고전적인 teacher-based methods 보다 좋은 성능을 성취했다.

• 대한조선학회논문집
• /
• 제58권5호
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.

• 융합정보논문지
• /
• 제12권1호
• /
• pp.39-44
• /
• 2022

본 연구의 목적은 딥러닝 알고리즘을 이용하여 영상 내 객체의 종류, 위치, 절대 크기를 추출하고, 객체간 상대적 거리를 예측하며, 이를 이용하여 객체 간의 접촉을 감지하기 위한 내용이다. 객체의 크기 비율을 분석하기 위하여, CNN 기반의 Object Detection 알고리즘인 YOLO를 이용한다. YOLO 알고리즘을 통하여 2D 형태의 이미지에서 각 개체의 절대적인 크기와 위치를 좌표의 형태로 추출한다. 추출 결과는 사전에 저장된 동일한 객체의 명칭과 크기를 가지는 표준 객체-크기 리스트로부터 영상 내 크기와 실제 크기 간의 비례를 추출하며, 영상 내 카메라-객체 간의 상대적인 거리를 예측한다. 예측된 값을 바탕으로 영상에서 객체 간 접촉 여부를 감지한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권9호
• /
• pp.4386-4404
• /
• 2016

Most existing salient object detection algorithms commonly employed segmentation techniques to eliminate background noise and reduce computation by treating each segment as a processing unit. However, individual small segments provide little information about global contents. Such schemes have limited capability on modeling global perceptual phenomena. In this paper, a novel salient object detection algorithm is proposed based on region merging. An adaptive-based merging scheme is developed to reassemble regions based on their color dissimilarities. The merging strategy can be described as that a region R is merged with its adjacent region Q if Q has the lowest dissimilarity with Q among all Q's adjacent regions. To guide the merging process, superpixels that located at the boundary of the image are treated as the seeds. However, it is possible for a boundary in the input image to be occupied by the foreground object. To avoid this case, we optimize the boundary influences by locating and eliminating erroneous boundaries before the region merging. We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained. Experiments on four benchmark datasets including MSRA-B, SOD, SED and iCoSeg show the proposed method results in uniform object enhancement and achieve state-of-the-art performance by comparing with nine existing methods.

• Journal of information and communication convergence engineering
• /
• 제9권1호
• /
• pp.21-26
• /
• 2011

In this paper, we suggest the object-oriented methodology for the design and implementation scheme for the program development in the application of control and instrumentation such as the detection system of RFID defective tags which needs the embedded programming. We apply the design methodology of UML in the system design phase, and suggest the implementation scheme of LabVIEW programs using LVOOP(LabVIEW Object Oriented Programming)in which make it possible to write the object-oriented programming. We design the class diagram and the sequence diagram using UML, and write the classes of LVOOP from the designed class diagram and the main VI from the sequence diagram, respectively. We show that it is possible to develop the embedded programs such as the RFID application through the implementation example of the detection system of RFID defective tags in this paper. And, we obtain the advantages based on the object-oriented design and implementation using the LVOOP approach such as the development of LabVIEW programs by adding the classes and the concept of object of the object-oriented language to LabVIEW.

• 방송공학회논문지
• /
• 제13권5호
• /
• pp.681-684
• /
• 2008

We proposed a method to improve moving object detection capability of Gaussian Mixture Model by suggesting shape adaptive bidirectional block matching algorithm. This method achieves more accurate detection and tracking performance at various motion types such as slow, fast, and bimodal motions than that of Gaussian Mixture Model. Experimental results showed that the proposed method outperformed the conventional methods.

• 반도체디스플레이기술학회지
• /
• 제19권1호
• /
• pp.85-92
• /
• 2020

Object detection plays a critical role in the field of computer vision, and various researches have rapidly increased along with applying convolutional neural network and its modified structures since 2012. There are representative object detection algorithms, which are convolutional neural networks and YOLO. This paper presents two representative algorithm series, based on CNN and YOLO which solves the problem of CNN bounding box. We compare the performance of algorithm series in terms of accuracy, speed and cost. Compared with the latest advanced solution, YOLO v3 achieves a good trade-off between speed and accuracy.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1268-1271
• /
• 2003

In the edge detection of RS image, the useful detail losing and the spurious edge often appear. To solve the problem, we use the dyadic wavelet to detect the edge of surface features by combining the edge detecting with the multi-resolution analyzing of the wavelet transform. Via the dyadic wavelet decomposing, we obtain the RS image of a certain appropriate scale, and figure out the edge data of the plane and the upright directions respectively, then work out the grads vector module of the surface features, at last by tracing them we get the edge data of the object therefore build the RS image which obtains the checked edge. This method can depress the effect of noise and examine exactly the edge data of the object by rule and line. With an experiment of a RS image which obtains an airport, we certificate the feasibility of the application of dyadic wavelet in the object edge detection.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.25-33
• /
• 2019

In this paper, we propose an intelligent CCTV technology which is applied to a recent attracted attention real-time object detection technology in a disaster alarm system. Natural disasters are rapidly increasing due to climate change (global warming). Various disaster alarm systems have been developed and operated to solve this problem. In this paper, we detect object through Neuron Network algorithm and test the difference from existing SVM classifier. Experimental results show that the proposed algorithm overcomes the limitations of existing object detection techniques and achieves higher detection performance by about 15%.

• 한국군사과학기술학회지
• /
• 제26권5호
• /
• pp.392-399
• /
• 2023

This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train deep neural networks for object detection tasks. Our approach involves the generation of a large dataset of synthetic images of military vehicles, which is then used to train a deep learning model. The resulting model is then evaluated on real-world images to measure its effectiveness. Our experimental results show that synthetic training data alone can achieve effective results in object detection. Our findings demonstrate the potential of CG-based synthetic data for deep learning and suggest its value as a tool for training models in a variety of applications, including military vehicle detection.