• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.885-887
• /
• 2024

딥러닝 모델이 다양한 분야에 적용되면서, 딥러닝 모델에 대한 보안이 큰 이슈가 되고 있다. 특히, 입력 데이터에 섭동(perturbation)을 추가하여 모델의 정상적인 추론을 방해하는 적대적 공격(Adversarial Attack)에 대한 연구가 활발하게 진행되고 있다. 본 논문에서는 객체 탐지 모델의 NMS(Non-Maximum Suppression) 알고리즘에 대한 적대적 공격 기법 중 하나인 Phantom Sponges 공격을 수행하여 적대적 예제(Adversarial Example)를 생성하고, 원본 이미지와의 유사성을 측정하여 분석하고자 한다.

• 대한기계학회논문집B
• /
• 제41권3호
• /
• pp.205-209
• /
• 2017

고온으로 가열된 고체 표면 위를 타원형 액적이 충돌할 때, 구형 액적 충돌 거동과 다른 비축대칭적인 퍼짐 거동이 발생하여 반동 높이 조절이 가능하다고 보고되었다. 본 연구에서는 타원형 액적 종횡비가 퍼짐 거동에 미치는 영향을 조사하였다. 충돌 거동은 동기화된 두 대의 고속카메라를 이용하여 두 측면에서 관찰하였고, 액적의 장축과 단축에서의 액적 퍼짐 너비를 각각 조사함으로써 퍼짐 특성을 분석하였다. 실험 결과에서 종횡비가 클수록, 액적 단축의 최대 퍼짐 너비는 증가하는 데 반해, 액적 장축의 것은 큰 변화가 없는 것으로 나타나는 데, 이는 수축 과정에서 액적 정렬을 촉진하고 반동 억제에 중요한 역할을 한다. 본 연구에서는 추가적으로 액적 종횡비와 충돌 속도가 동시에 큰 영역에서 발생하는 반동 거동과 액적 분열 현상에 대하여 고찰하였다.

• 한국미생물·생명공학회지
• /
• 제23권2호
• /
• pp.236-242
• /
• 1995

Biological control of soilborne plant pathogens by the addition of antagonistic microorganisms to the soil may offer a practical supplement or alternative to existing disease management strategies that depend heavily on chemical pesticides. Soil amendment with antagonistic microbes was non-effective because of high cost, low efficacy, and inconvenient usage on the treatment course. Therefore, seed coating formulation for the application of biological seed treatments has been being to apply successful disease suppression for many important crops. The objectives of this study were to investigate the optimal condition for the spore production of biocontrol agent Bacillus subtilis YBL-7 and the liquid coating formulation that contained a suspension of a proper aqueous binder, as well as a ground fine solid particulate material. The maximum yield has been obtained from 60 hrs-old culture at 30$\circ$C in spore forming (SF) medium containing 0.8% nutrient broth, 0.05% yeast extract, 10$^{-1}$ M MgCl$^{2}$, 10$^{-4}$ M MnCl$^{2}$, 10$^{-5}$ M dipicolinic acid, and pH 6.5. The optimal condition of dried spore preparation was achieved when cells of B. subtilis YBL-7 was heat-dried with 50$\circ$C for 2 hrs.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.77-80
• /
• 2013

SURF 알고리즘은 영상의 특징점 검출 및 서술자를 생성하는 알고리즘으로 크기와 회전, 조명 및 시점 등의 환경 변화에 강인한 특징을 가지고 있다. 이러한 특징 때문에 객체 인식, 파노라마 이미지, 3차원 영상 복원 등 영상처리 분야에서 많이 사용되고 있다. 하지만 SURF 알고리즘과 같은 대부분의 인식 알고리즘은 많은 양의 연산을 필요로 하기 때문에 실시간 구현이 어렵다. 본 논문은 SURF의 메모리 접근 횟수와 메모리 사용량을 분석하여 효율적인 메모리를 설계함으로써 메모리 접근 횟수와 메모리 사용량을 최소화하여 실시간 구현이 가능하도록 설계하였다.

• 제어로봇시스템학회논문지
• /
• 제11권5호
• /
• pp.423-428
• /
• 2005

This paper proposes a new edge detection method using a $3{\times}3$ ideal binary pattern and lookup table (LUT) for the mobile robot localization without any parameter adjustments. We take the mean of the pixels within the $3{\times}3$ block as a threshold by which the pixels are divided into two groups. The edge magnitude and orientation are calculated by taking the difference of average intensities of the two groups and by searching directional code in the LUT, respectively. And also the input image is not only partitioned into multiple groups according to their intensity similarities by the histogram, but also the threshold of each group is determined by fuzzy reasoning automatically. Finally, the edges are determined through non-maximum suppression using edge confidence measure and edge linking. Applying this edge detection method to the mobile robot localization using projective invariance of the cross ratio. we demonstrate the robustness of the proposed method to the illumination changes in a corridor environment.

• 한국군사과학기술학회지
• /
• 제22권1호
• /
• pp.1-10
• /
• 2019

In this paper, we propose the track initiation algorithm based on the weighted score for TWS radar tracking. This algorithm utilizes radar velocity information to calculate the probabilistic track score and applies the Non-Maximum-Suppression(NMS) to confirm the targets to track. This approach is understood as a modification of a conventional track initiation algorithm in a probabilistic manner. Also, we additionally apply the weighted Hough transform to compensate a measurement error, and it helps to improve the track detection probability. We designed the simulator in order to demonstrate the performance of the proposed track initiation algorithm. The simulation result show that the proposed algorithm, which reduces about 40 % of a false track probability, is better than the conventional algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• 한국전기전자재료학회논문지
• /
• 제34권1호
• /
• pp.73-77
• /
• 2021

Inorganic-organic hybrid perovskite solar cells have demonstrated considerable improvements, reaching 25.5% of certified power conversion efficiency in 2020 from 3.8% in 2009. In normal structured perovskite solar cells, TiO2 electron-transporting materials require heat treatment process at a high temperature over 450℃ to induce crystallinity. Inverted perovskite solar cells have also been studied to exclude the additional thermal process by using [6,6]-phenyl-C61-butyric acid methyl ester (PCBM) as a non-oxide electron-transporting layer. However, the drawback of the PCBM layer is a charge accumulation at the interface between PCBM and a metal electrode. The impact of bathocuproin (BCP) buffer layer on photovoltaic performance has been investigated herein to solve the problem of PCBM. 2-mM BCP-modified perovskite solar cells were observed to exhibit a maximum efficiency of 12.03% compared with BCP-free counterparts (5.82%) due to the suppression of the charge accumulation at the PCBM-Au interface and the resulting reduction of the charge recombination between perovskite and the PCBM layer.

• International journal of advanced smart convergence
• /
• 제11권2호
• /
• pp.22-29
• /
• 2022

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2^TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2^TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

• Smart Structures and Systems
• /
• 제33권2호
• /
• pp.105-118
• /
• 2024

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.