• 한국군사과학기술학회지
• /
• 제24권2호
• /
• pp.175-186
• /
• 2021

In the field of automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, it is usually impractical to obtain SAR target images covering a full range of aspect views. When the database consists of SAR target images with limited angular diversity, it can lead to performance degradation of the SAR-ATR system. To address this problem, this paper proposes a deep learning-based method where channel attention modules(CAMs) are inserted to a convolutional neural network(CNN). Motivated by the idea of the squeeze-and-excitation(SE) network, the CAM is considered to help improve recognition performance by selectively emphasizing discriminative features and suppressing ones with less information. After testing various CAM types included in the ResNet18-type base network, the SE CAM and its modified forms are applied to SAR target recognition using MSTAR dataset with different reduction ratios in order to validate recognition performance improvement under the limited angular diversity condition.

• 전자공학회논문지B
• /
• 제33B권6호
• /
• pp.198-207
• /
• 1996

A PSRI (position, scale, and rotation invariant ) feature extraction and automatic target recognition system using a cooperative network and an MLP is proposed. We can extract position invarient features by obtaining the target center using the projection and the moment in preprocessing stage. The scale and rotation invariant features are extracted from the contour projection of the number of edge pixels on each of the concentric circles, which is input to the cooperative network. By extracting the representative PSRI features form the features and their differentiations using max-net and min-net, we can rdduce the number of input neurons of the MLP, and make the resulted automatic target recognition system less sensitive to input variances. Experiments are conduted on various complex images which are shifted, rotated, or scaled, and the results show that the proposed system is very efficient for PSRI feature extractions and automatic target recognitions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1614-1632
• /
• 2017

Bag of visual words is a popular model in human action recognition, but usually suffers from loss of spatial and temporal configuration information of local features, and large quantization error in its feature coding procedure. In this paper, to overcome the two deficiencies, we combine sparse coding with spatio-temporal pyramid for human action recognition, and regard this method as the baseline. More importantly, which is also the focus of this paper, we find that there is a hierarchical structure in feature vector constructed by the baseline method. To exploit the hierarchical structure information for better recognition accuracy, we propose a tree regularized classifier to convey the hierarchical structure information. The main contributions of this paper can be summarized as: first, we introduce a tree regularized classifier to encode the hierarchical structure information in feature vector for human action recognition. Second, we present an optimization algorithm to learn the parameters of the proposed classifier. Third, the performance of the proposed classifier is evaluated on YouTube, Hollywood2, and UCF50 datasets, the experimental results show that the proposed tree regularized classifier obtains better performance than SVM and other popular classifiers, and achieves promising results on the three datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3762-3781
• /
• 2020

Infrared pedestrian target recognition is a vital problem of significant interest in computer vision. In this work, a novel infrared pedestrian target recognition method that uses heterogeneous features with multi-kernel transfer learning is proposed. Firstly, to exploit the characteristics of infrared pedestrian targets fully, a novel multi-scale monogenic filtering-based completed local binary pattern descriptor, referred to as MSMF-CLBP, is designed to extract the texture information, and then an improved histogram of oriented gradient-fisher vector descriptor, referred to as HOG-FV, is proposed to extract the shape information. Second, to enrich the semantic content of feature expression, these two heterogeneous features are integrated to get more complete representation for infrared pedestrian targets. Third, to overcome the defects, such as poor generalization, scarcity of tagged infrared samples, distributional and semantic deviations between the training and testing samples, of the state-of-the-art classifiers, an effective multi-kernel transfer learning classifier called MK-TrAdaBoost is designed. Experimental results show that the proposed method outperforms many state-of-the-art recognition approaches for infrared pedestrian targets.

• Molecules and Cells
• /
• 제39권5호
• /
• pp.375-381
• /
• 2016

MicroRNAs (miRNAs) are small non-coding RNAs (~22 nucleotides) regulating gene expression at the post-transcriptional level. By directing the RNA-induced silencing complex (RISC) to bind specific target mRNAs, miRNA can repress target genes and affect various biological phenotypes. Functional miRNA target recognition is known to majorly attribute specificity to consecutive pairing with seed region (position 2-8) of miRNA. Recent advances in a transcriptome-wide method of mapping miRNA binding sites (Ago HITS-CLIP) elucidated that a large portion of miRNA-target interactions in vivo are mediated not only through the canonical "seed sites" but also via non-canonical sites (~15-80%), setting the stage to expand and determine their properties. Here we focus on recent findings from transcriptome-wide non-canonical miRNA-target interactions, specifically regarding "nucleation bulges" and "seed-like motifs". We also discuss insights from Ago HITS-CLIP data alongside structural and biochemical studies, which highlight putative mechanisms of miRNA target recognition, and the biological significance of these non-canonical sites mediating marginal repression.

• 한국정보통신학회논문지
• /
• 제17권11호
• /
• pp.2505-2511
• /
• 2013

수중환경 하에서 표적을 탐지하고 식별하는 문제는 군사적인 목적은 물론 비군사적 목적으로도 많은 연구가 수행되어 왔다. 수중환경에서의 수중음향 신호가 시간 공간적으로 특성이 변화하며 천해 다중경로 환경을 반영하는 복잡한 특성을 보이는 점으로 인해 능동 표적인식 기술은 매우 어려운 기술로 여겨져 왔다. 또한 실제 데이터 수집의 어려움이 따르게 된다. 본 논문에서는 3차원 하이라이트 분포를 가지는 모델을 이용하여, 능동소나 표적신호를 음선 추적기법을 기반으로 하여 합성하였다. 합성된 표적신호를 대상으로 Fractional Fourier 변환을 적용하여 특징벡터를 추출하였고, 신경회로망 인식기를 이용하여 인식 실험을 수행하였다.

• 한국음향학회지
• /
• 제19권4호
• /
• pp.93-100
• /
• 2000

수중 능동소나에 의해 표적을 분류하는데 있어 표적신호의 특징파라미터는 매우 중요하다. 광대역이고 상관성이 높은 두 개의 펄스가 시간 T의 간격으로 분리되어 있을 때, 스펙트럼에서 리플간의 1/T Hz에 해당하는 TSP, 즉 피치 성분을 가진다. 음향산란 실험에 사용된 축소표적신호 또한 이러한 TSP 특징을 잘 반영하고 있다. 본 논문에서는 각 표적신호의 특징에 해당하는 TSP 정보를 FFT를 이용하여 효과적으로 추출하였다. 네 개의 표적과 각 표적의 자세각에 따라 추출된 TSP 특징파라미터를 패턴인식 기법에 적용하여 표적을 분류하고 각 표적의 특징을 분석하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.767-771
• /
• 2003

In this study, stereo vision system is applied to a mobile manipulator for effective tasks. The robot can recognize a target and compute the position of the target using a stereo vision system. While a monocular vision system needs properties such as geometric shape of a target, a stereo vision system enables the robot to find the position of a target without additional information. Many algorithms have been studied and developed for an object recognition. However, most of these approaches have a disadvantage of the complexity of computations and they are inadequate for real-time visual servoing. However, color information is useful for simple recognition in real-time visual servoing. In this paper, we refer to about object recognition using colors, stereo matching method, recovery of 3D space and the visual servoing.

• 제어로봇시스템학회논문지
• /
• 제11권5호
• /
• pp.411-417
• /
• 2005

In this study, stereo vision system is applied to a mobile manipulator for effective tasks. The robot can recognize a target and compute the potion of the target using a stereo vision system. While a monocular vision system needs properties such as geometric shape of a target, a stereo vision system enables the robot to find the position of a target without additional information. Many algorithms have been studied and developed for an object recognition. However, most of these approaches have a disadvantage of the complexity of computations and they are inadequate for real-time visual servoing. Color information is useful for simple recognition in real-time visual servoing. This paper addresses object recognition using colors, stereo matching method to reduce its calculation time, recovery of 3D space and the visual servoing.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1493-1503
• /
• 2018

We propose an object recognition system and experiential game contents using Kinect to maximize object recognition rate by utilizing underwater robots. we implement an ice hockey game based on object-aware interactive contents to validate the excellence of the proposed system. The object recognition system, which is a preprocessor module, is composed based on Kinect and OpenCV. Network sockets are utilized for object recognition communications between C/S. The problem of existing research, degradation of object recognition at long distance, is solved by combining the system development method suggested in the study. As a result of the performance evaluation, the underwater robot object recognized all target objects (90.49%) with 80% of accuracy from a 2m distance, revealing 42.46% of F-Measure. From a 2.5m distance, it recognized 82.87% of the target objects with 60.5% of accuracy, showing 34.96% of F-Measure. Finally, it recognized 98.50% of target objects with 59.4% of accuracy from a 3m distance, showing 37.04% of F-measure.