• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.279-279
• /
• 2022

최근 이미지분석 기술은 하드웨어 및 소프트웨어 기술의 급격한 발전으로 인해 의학, 생물학, 지리학, 재료공학 등에서 수많은 연구 분야에서 광범위하게 활용되고 있으며, 이미지분석은 다량의 토사에 대하여 입경을 포함한 형상학적 특성을 간편하게 정량화 할 수 있기 때문에 매우 효과적인 분석 방법으로 판단된다. 현재 모래의 입도분석 방법으로는 신뢰성 있는 체가름 시험법(KSF2302) 등이 있으나, 번거로운 처리과정과 많은 시간이 소요된다. 또한 입자형상은 입경이 세립 할수록 직접 측정이 어렵기 때문에, 최근에는 이미지 분석을 이용하는 방법이 시도되고 있다. 본 연구에서는 75㎛ 이상의 조립질 하상 토사 이미지를 취득하여, 입자들의 장·축단 길이, 면적, 둘레, 공칭직경 및 종횡비 등의 형상학적 특성인자를 자동으로 측정하는 프로그램 개발을 수행하였다. 프로그램은 이미지 분석에 특화된 라이브러리인 OpenCV(Open Source Computer Vision)를 적용하였다. 이미지 분석 절차는 크게 이미지 취득, 기하보정, 노이즈제거, 객체추출 및 형상인자 측정 단계로 구성되며, 이미지 취득시 패널의 하단에 Back light를 부착해 시료에 의해 발생되는 음영을 제거하였다. 기하보정은 원근변환(perspective transform)을 적용했으며, 노이즈 제거는 모폴로지 연산과 입자간의 중첩으로 인한 뭉침을 제거하기 위해 watershed 알고리즘을 적용하였다. 최종적으로 객체의 외곽선 추출하여 입자들의 다양한 정보(장축, 단축, 둘레, 면적, 공칭직경, 종횡비)를 산출하고, 분포형으로 제시하였다. 본 연구에서 제안하는 이미지분석을 적용한 토사의 형상학적 특성 측정 방법은 시간과 비용의 측면에서 보다 효율적으로 하상 토사에 대한 다양한 정보를 획득 할 수 있을 것으로 기대한다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.579-586
• /
• 2022

Modular building is a fast-growing construction method, mainly due to its ability to drastically reduce the amount of time it takes to construct a building and produce higher-quality buildings at a more consistent rate. However, while modular construction is relatively safer than traditional construction methods, workers are still exposed to hazards that lead to injuries and fatalities, and these hazards could be controlled using emerging smart technologies. Currently, limited information is available at the intersection of modular construction, safety risk, and smart safety technologies. This paper aims to investigate what aspects of modular construction are most dangerous for its workers, highlight specific risks in its processes, and propose ways to utilize smart technologies to mitigate these safety risks. Findings from the archival analysis of accident reports in Occupational Safety and Health Administration (OSHA) Fatality and Catastrophe Investigation Summaries indicate that 114 significant injuries were reported between 2002 and 2021, of which 67 were fatalities. About 72% of fatalities occurred during the installation phase, while 57% were caused by crushing and 85% of crash-related incidents were caused by jack failure/slippage. IoT-enabled wearable sensing devices, computer vision, smart safety harness, and Augment and Virtual Reality were identified as potential solutions for mitigating identified safety risks. The present study contributes to knowledge by identifying important safety trends, critical safety risk factors and proposing practical emerging methods for controlling these risks.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.313-322
• /
• 2020

The recognition of the risk hazards is a vital step to effectively prevent accidents on a construction site. The advanced development in computer vision systems and the availability of the large visual database related to construction site made it possible to take quick action in the event of human error and disaster situations that may occur during management supervision. Therefore, it is necessary to analyze the risk factors that need to be managed at the construction site and review appropriate and effective technical methods for each risk factor. This research focuses on analyzing Occupational Safety and Health Agency (OSHA) related to risk zone identification rules that can be adopted by the image recognition technology and classify their risk factors depending on the effective technical method. Therefore, this research developed a pattern-oriented classification of OSHA rules that can employ a large scale of safety hazard recognition. This research uses joint reasoning of risk zone Identification and numeric input by utilizing a stereo camera integrated with an image detection algorithm such as (YOLOv3) and Pyramid Stereo Matching Network (PSMNet). The research result identifies risk zones and raises alarm if a target object enters this zone. It also determines numerical information of a target, which recognizes the length, spacing, and angle of the target. Applying image detection joint logic algorithms might leverage the speed and accuracy of hazard detection due to merging more than one factor to prevent accidents in the job site.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.1-6
• /
• 2023

In the realm of dental prosthesis fabrication, obtaining accurate impressions has historically been a challenging and inefficient process, often hindered by hygiene concerns and patient discomfort. Addressing these limitations, Company D recently introduced a cutting-edge solution by harnessing the potential of intraoral scan images to create 3D dental models. However, the complexity of these scan images, encompassing not only teeth and gums but also the palate, tongue, and other structures, posed a new set of challenges. In response, we propose a sophisticated real-time image segmentation algorithm that selectively extracts pertinent data, specifically focusing on teeth and gums, from oral scan images obtained through Company D's oral scanner for 3D model generation. A key challenge we tackled was the detection of the intricate molar regions, common in dental imaging, which we effectively addressed through intelligent data augmentation for enhanced training. By placing significant emphasis on both accuracy and speed, critical factors for real-time intraoral scanning, our proposed algorithm demonstrated exceptional performance, boasting an impressive accuracy rate of 0.91 and an unrivaled FPS of 92.4. Compared to existing algorithms, our solution exhibited superior outcomes when integrated into Company D's oral scanner. This algorithm is scheduled for deployment and commercialization within Company D's intraoral scanner.

• 반도체공학회 논문지
• /
• 제2권1호
• /
• pp.17-20
• /
• 2024

본 논문은 전통적인 자원 집약적인 컴퓨터 비전 모델의 한계를 해결하기 위해 저전력 엣지 장치에 최적화된 새로운 경량 객체 검출 모델을 제안합니다. 제안된 검출기는 Single Shot Detector (SSD)에 기반하여 소형이면서도 견고한 네트워크를 설계하였고, 작은 객체를 효율적으로 감지하는 데 있어 효율성을 크게 향상시키도록 모델을 구성하였다. 이 모델은 주로 두 가지 구성요소로 구성되어 있습니다: Depthwise 와 Pointwise Convolution 레이어를 사용하여 효율적인 특징 추출을 위한 Light_Block, 그리고 작은 객체의 향상된 감지를 위한 Enhancer_Block 으로 나누었다. 우리의 모델은 300x480 의 이미지 크기를 가진 Udacity 주석이 달린 데이터셋에서 처음부터 훈련되었으며, 사전 훈련된 분류 가중치의 필요성을 제거하였다. 약 0.43M 의 파라미터로 5.5MB 만의 무게를 가진 우리의 검출기는 평균 정밀도 (mAP) 27.7%와 140 FPS 의 처리 속도를 달성하여, 정밀도와 효율성 모두에서 기존 모델을 능가하였다. 따라서, 본 논문은 추론의 정확성을 손상시키지 않으면서 엣지 장치를 위한 객체 검출에서의 효과적인 경량화를 보여주고 있다.

• 한국건축시공학회지
• /
• 제23권5호
• /
• pp.629-638
• /
• 2023

본 논문에서는 건설현장 작업자의 실내 위치 추적을 위한 새로운 방법을 소개한다. 전통적으로 GPS및 NTRIP과 같은 기술은 주로 야외에서 효과적인 위치 확인을 제공하는 데 사용되었습니다. 그러나 이러한 기술은 실내에서 사용할 경우 정확도가 떨어지는 문제가 있습니다. 이러한 문제를 해결하기 위해 본 논문에서는 Aruco marker를 활용하여 작업자의 위치를 추적하는 방법을 제안한다. Aruco marker는 작업자와 마커 사이의 거리를 측정하는 데 사용됩니다. 이 새로운 접근 방식은 기존 위치 확인 방법에 비해 더욱 정확한 실내 위치 확인을 제공합니다. 작업자 위치를 실시간으로 확인할 수 있어 작업 일정을 최적화하고 작업자 간 협업을 촉진합니다. 따라서 Aruco marker를 활용한 실내 측위 방식은 기존의 기술의 문제점을 보완하는 실내 위치 확인 시스템으로 활용될 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.938-958
• /
• 2024

Unsupervised Video Object Segmentation (UVOS) is a highly challenging problem in computer vision as the annotation of the target object in the testing video is unknown at all. The main difficulty is to effectively handle the complicated and changeable motion state of the target object and the confusion of similar background objects in video sequence. In this paper, we propose a novel deep Dual-stream Co-enhanced Network (DC-Net) for UVOS via bidirectional motion cues refinement and multi-level feature aggregation, which can fully take advantage of motion cues and effectively integrate different level features to produce high-quality segmentation mask. DC-Net is a dual-stream architecture where the two streams are co-enhanced by each other. One is a motion stream with a Motion-cues Refine Module (MRM), which learns from bidirectional optical flow images and produces fine-grained and complete distinctive motion saliency map, and the other is an appearance stream with a Multi-level Feature Aggregation Module (MFAM) and a Context Attention Module (CAM) which are designed to integrate the different level features effectively. Specifically, the motion saliency map obtained by the motion stream is fused with each stage of the decoder in the appearance stream to improve the segmentation, and in turn the segmentation loss in the appearance stream feeds back into the motion stream to enhance the motion refinement. Experimental results on three datasets (Davis2016, VideoSD, SegTrack-v2) demonstrate that DC-Net has achieved comparable results with some state-of-the-art methods.

• Journal of Periodontal and Implant Science
• /
• 제54권1호
• /
• pp.3-12
• /
• 2024

Deep learning (DL) offers promising performance in computer vision tasks and is highly suitable for dental image recognition and analysis. We evaluated the accuracy of DL algorithms in identifying and classifying dental implant systems (DISs) using dental imaging. In this systematic review and meta-analysis, we explored the MEDLINE/PubMed, Scopus, Embase, and Google Scholar databases and identified studies published between January 2011 and March 2022. Studies conducted on DL approaches for DIS identification or classification were included, and the accuracy of the DL models was evaluated using panoramic and periapical radiographic images. The quality of the selected studies was assessed using QUADAS-2. This review was registered with PROSPERO (CRDCRD42022309624). From 1,293 identified records, 9 studies were included in this systematic review and meta-analysis. The DL-based implant classification accuracy was no less than 70.75% (95% confidence interval [CI], 65.6%-75.9%) and no higher than 98.19 (95% CI, 97.8%-98.5%). The weighted accuracy was calculated, and the pooled sample size was 46,645, with an overall accuracy of 92.16% (95% CI, 90.8%-93.5%). The risk of bias and applicability concerns were judged as high for most studies, mainly regarding data selection and reference standards. DL models showed high accuracy in identifying and classifying DISs using panoramic and periapical radiographic images. Therefore, DL models are promising prospects for use as decision aids and decision-making tools; however, there are limitations with respect to their application in actual clinical practice.

• 한국산업정보학회논문지
• /
• 제29권1호
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer(CFD)는 냉동 및 냉방 시스템에서 냉매의 순환 시 불순물을 제거하여 깨끗한 냉매를 유지하는 역할을 하며, CFD의 결함은 냉동 및 냉방 시스템의 누수, 수명 저하 등 제품의 결함으로 이어질 수 있어 품질보증이 필수적이다. 기존에는 품질 검사 단계에서 작업자가 검사하고 결함을 판단하는 방법이 주로 사용되었으나, 이러한 방법은 주관적으로 판단하기 때문에 정확하지 못하다. 본 논문에서는 CFD 축관 및 용접 공정 과정에서 발생하는 결함을 검출하고 기존의 품질 검사를 대체하기 위해 YOLOv7 객체 감지 알고리즘을 사용하여 결함을 검출했고, F1-Score 0.954, 0.895의 검출 성능을 확인하였다. 또한, 결함 이미지의 Timestamp에 해당하는 센서 데이터 분석을 통해 용접 과정 중 발생하는 결함의 원인을 분석하였다. 본 논문은 CFD 공정 중 발생하는 결함을 검출하고 원인을 분석함으로써 제조 품질보증과 개선 방안을 제시한다.