• 한국군사과학기술학회지
• /
• 제25권5호
• /
• pp.462-475
• /
• 2022

Different from the field of electro-optical(EO) image analysis, there has been less interest in similarity metrics between synthetic aperture radar(SAR) target images. A reliable and objective similarity analysis for SAR target images is expected to enable the verification of the SAR measurement process or provide the guidelines of target CAD modeling that can be used for simulating realistic SAR target images. For this purpose, this paper presents a similarity analysis method based on the siamese network that quantifies the subjective assessment through the distance learning of similar and dissimilar SAR target image pairs. The proposed method is applied to MSTAR SAR target images of slightly different depression angles and the resultant metrics are compared and analyzed with qualitative evaluation. Since the image similarity is somewhat related to recognition performance, the capacity of the proposed method for target recognition is further checked experimentally with the confusion matrix.

• 방송공학회논문지
• /
• 제26권1호
• /
• pp.14-25
• /
• 2021

서로 다른 시간에 촬영된 같은 위치의 원격 탐사 영상에서 변화된 사항을 찾는 변화 탐지는 다양한 영역에 적용되기 때문에 매우 중요하다. 그러나 정합 오차, 건물 변위 오차, 그림자 오차 등이 오탐지를 발생시킨다. 이러한 문제점을 해결하기 위해 본 논문은 CADNet(Change Attention Dense Siamese Network)을 제안한다. CADNet은 다양한 크기의 변화 영역을 탐지하기 위해 FPN(Feature Pyramid Network)을 사용하며, 변화 영역에 주목하는 변화 주목 모듈을 적용하고, 낮은 수준 (Low-level)의 특징과 높은 수준 (High-level)의 특징을 모두 포함하고 있는 피처 맵을 변화 탐지에 사용하기 위해 DenseNet을 피처 추출기로 사용한다. CADNet의 성능을 Precision, Recall, F1 측면에서 측정하였을 때 WHU 데이터 세트에 대하여 98.44%, 98.47%, 98.46%이었고, LEVIR-CD 데이터 세트에 대해 90.72%, 91.89%, 91.30%이었다. 이 실험의 결과는 CADNet이 기존 변화 탐지 방법들보다 향상된 성능을 제공한다는 것을 보여준다.

• 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.

• International journal of advanced smart convergence
• /
• 제11권2호
• /
• pp.128-134
• /
• 2022

Nowadays, people consume a lot of content such as web dramas or K-pop videos through mobile devices such as smartphones, and the market for indirect advertisements through these web dramas or K-pop videos is also increasing every year. In order to lead to the immediate purchase of indirect products in web dramas, a system that allows consumers to purchase immediately at the time the products appear in the drama is needed. In this paper, we propose a system to allow viewers to purchase products worn by celebrities immediately when viewers see and click on them. When a user clicks on a video, it recognizes the product worn by the celebrity, and displays information on the screen on the most similar product corresponding to the recognized product, allowing them to go to the seller's site where they can purchase it. In order for such a system to operate stably, a pose estimation and siamese network-based system is proposed. The proposed system will primarily be released as a streaming service in the form of an app or web page that connects the products in web dramas or other K-pop video contents screened on the mobile with e-commerce. Furthermore, in the future, the technology is expected to be used globally in various industries such as smart mobility and display kiosks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.108-111
• /
• 2022

제품의 결함 탐지를 위한 머신 비전 시스템에 딥러닝을 적용하기 위해서는 다양한 결함 사례에 대한 방대한 학습 데이터가 필요하다. 하지만 실제 제조 산업에서는 결함의 종류에 따른 데이터 불균형이 생기기 때문에 결함 사례를 일반화할 수 있을 만큼의 제품 이미지를 수집하기 위해서는 많은 시간이 소요된다. 본 논문에서는 적은 데이터로도 학습이 가능한 샴 신경망을 제품 결함 탐지에 적용하고, 제품 결함 이미지 데이터의 속성을 고려하여 이미지 쌍 구성법과 대조 손실 함수를 수정하였다. AUC-ROC로 샴 신경망의 임베딩 성능을 간접적으로 확인한 결과, 같은 제품끼리만 쌍을 구성하고 결함이 있는 제품 간에는 쌍을 구성하였을 때, 그리고 지수 대조 손실로 학습하였을 때 좋은 임베딩 성능을 보였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.691-694
• /
• 2020

최근 원격 탐사 영상의 발달로 인해 작지만 중요한 객체에 대한 탐지 가능성이 커져 건물 변화 탐지에 대한 관심이 높아지고 있다. 본 논문은 건물 변화 탐지 방법 중 가장 좋은 성능을 가진 PGA-SiamNet 의 세부 변화 탐지의 정확도가 낮은 한계점을 개선시키기 위해 DensNet 기반의 Dense Siamese Network 를 제안한다. 제안하는 방법은 공개된 WHU 데이터 세트에 대해 변화 탐지 측정 지표인 TPR, OA, F1, Kappa 에 대해 97.02%, 99.5%, 97.44%, 97.16%의 성능을 얻었다. 기존 PGA-SiamNet 에 비해 TPR 은 0.83%, F1 은 0.02%, Kappa 는 0.02% 증가하였으며, 세부 변화 탐지의 성능이 우수함을 확인할 수 있다.