• 융합정보논문지
• /
• 제11권9호
• /
• pp.28-34
• /
• 2021

딥러닝을 이용한 객체 검출의 경우 정확도와 실시간성을 모두 요구한다. 그러나, 한정된 자원 환경에서는 수 많은 양의 데이터를 처리하는 딥러닝 모델을 사용하기 어렵다. 이러한 문제 해결을 위해 본 논문에서는 소형임베디드 장치를 위한 객체 검출을 모델을 제안하였다. 일반적인 검출 모델과 달리 사전 학습된 특징 추출기를 제거한 구조를 사용하여 모델 크기를 최소화하였다. 모델의 구조는 경량화된 컨볼루션 블록을 반복해서 쌓는 구조로 설계하였다. 또한, 검출 오버헤드를 줄이기 위해 영역 제안 횟수를 크게 줄였다. 제안하는 모델은 공개 데이터 셋인 PASCAL VOC를 사용하여 학습 및 평가하였다. 모델의 정량적 평가를 위해 검출 분야에서 사용하는 average precision으로 검출 성능을 측정하였다. 그리고 실제 임베디드 장치와 유사한 라즈베리 파이에서 검출 속도를 측정하였다. 실험을 통해 기존 검출 방법 대비 향상된 정확도와 빠른 추론 속도를 달성하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.400-403
• /
• 2003

This paper presents the signal processing of the panoramic thermal warning system that detects the small target such as aircraft and helicopter from afar. We develope the all round looking thermal imaging system which can scan all the way. This system acquires the panoramic images to reconstruct the IR images by revolving head of sensor typed line sensor at high speed. For detection, where the object of interest may be small, it is sometimes difficult to specify from object and background by conventional contrast enhancement methods. Therefore we use the adaptive plateau equalization algorithm each region to improve the contrast and make the hardware system which consists of the signal processing board for real-time display. We can verify the proposed method by the computer simulation and the hardware implementation.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권1호
• /
• pp.9-14
• /
• 2017

최근 컴퓨터 기술의 발전과 함께 임베디드 기기 또한 다양한 기능을 갖추기 시작했다. 본 연구에서는 최근 활발하게 진행되고 있는 영상센서를 사용한 임베디드 기기 등 자원이 적은 기기에서 효율적인 얼굴 추적 방식을 제안한다. 정확한 얼굴을 얻기 위하여 MB-LBP 특징을 사용한 얼굴 검출 방식을 사용했으며, 다음 영상에서 얼굴 객체 추적을 위하여 얼굴 검출시 얼굴 주변 영역(Region of Interest)을 지정하였다. 그리고 얼굴을 검출을 못하는 영상에서는 기존의 객체 추적 방식인 CAM-Shift를 사용해 객체를 추적해 객체 정보의 손실 없이 정보를 유지할 수 있도록 하였다. 본 연구는 기존 연구와의 비교를 통하여 객체 추적 시스템의 정확성과 빠른 성능을 확인하였다.

• 대한원격탐사학회지
• /
• 제37권2호
• /
• pp.177-198
• /
• 2021

변화탐지 연구는 주로 토지이용/피복의 변화, 재난/재해 피해지역과 같은 토지의 변화, 수역, 식생과 같은 특정 넓게 분포하는 객체의 변화에 대한 연구가 진행되어 왔다. 한편, 위성영상의 공간/시간 해상도가 지속적으로 향상됨에 따라 위성영상으로부터 선박, 차량과 같은 면적이 작은 객체의 변화탐지의 가능성이 높아지고 있다. 이러한 가능성을 확인하기 위하여 본 논문에서는 위성영상으로부터 소형객체 변화탐지를 수행하기 위해 기존 화소기반 변화탐지기법의 성능을 분석하였다. 10일 이내의 짧은 시기에서 촬영된 Kompsat 3A 위성영상 및 Google Earth 영상을 이용하여 대표적인 화소기반 변화탐지기법인 차분, 주성분 분석, MAD 및 IR-MAD을 적용하였다. 영상에서 관측 가능한 소형 객체 주변으로 변화/비변화 참조자료를 정의하고 각 기법을 적용하여 얻어진 변화탐지 결과영상과 참조자료를 비교하여 성능을 분석하였다. 성능분석 결과 실험에 사용한 모든 영상에서 MAD, IR-MAD 기법이 상대적으로 우수한 성능을 제공하였다. LULC, 식생변화 등 대규모 지역의 변화탐지에 우수한 성능을 보인 MAD, IR-MAD 기법이 소형객체의 변화탐지에도 적용될 수 있음을 확인할 수 있었다. 아울러 변화탐지 대상인 소형객체에 높은 반사율 특성을 가지는 분광밴드를 변화탐지를 위한 분석에 포함하는 것이 소형객체 변화탐지율을 높일 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• pp.281-288
• /
• 2022

According to statistics conducted by the Korea Coast Guard, the number of accidents on small boats under 5 tons is increasing every year. This is because only a small number of people are on board. The previously developed maritime distress and safety systems are not well distributed because passengers must be equipped with additional remote equipment. The purpose of this study is to develop a distress awareness system that recognizes man over-board situations in real time. This study aims to present the part of the passenger tracking system among the small ship's distress awareness situational system that can generate passenger's location information in real time using deep learning based object detection and tracking technologies. The system consisted of the following steps. 1) the passenger location information is generated in the form of Bounding box using its detection model (YOLOv3). 2) Based on the Bounding box data, Deep SORT predicts the Bounding box's position in the next frame of the image with Kalman filter. 3) When the actual Bounding Box is created within the range predicted by Kalman-filter, Deep SORT repeats the process of recognizing it as the same object. 4) If the Bounding box deviates the ship's area or an error occurs in the number of tracking occupant, the system is decided the distress situation and issues an alert. This study is expected to complement the problems of existing technologies and ensure the safety of individuals aboard small boats.

• 방송공학회논문지
• /
• 제23권6호
• /
• pp.780-789
• /
• 2018

전 세계적으로 총기 사고는 인적이 드문 장소뿐만 아니라 사람들이 많이 모여 있는 공공장소에서도 빈번하게 일어난다. 특히, 권총과 같은 소형 총기 사고의 빈도수가 매우 높다. 그러므로 사람에 비해 상대적으로 매우 작은 크기의 객체인 권총을 가진 사람을 탐지하는 것은 사고의 피해를 최소화하는데 핵심적이다. '권총 든 사람'을 탐지하는 연구가 수행되고 있지만, 사람보다 권총은 상대적으로 크기가 작기 때문에 단일 객체만을 탐지하는 기존 객체 탐지 방법으로 '권총 든 사람'을 탐지하면 오류 발생 빈도수가 매우 높다. 이러한 문제점을 해결하기 위하여 권총으로 무장한 사람을 탐지하는 방법으로 APDA(Armed Person Detection Algorithm)를 제안한다. APDA는 입력 영상에서 합성곱신경망(Convolutional Neural Network, CNN) 기반의 인체 특징점 탐지 모델과 객체 탐지 모델을 병행하여 획득한 양 손목과 권총의 위치를 후처리 작업에서 이용하여 '권총 든 사람'을 탐지한다. APDA는 기존 방식보다 객관적 평가에서 재현율이 46.3% 향상되었고, 정밀도는 14.04% 향상되었다.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.745-755
• /
• 2023

The wire rope is an indispensable production machinery in coal mines. It is the main force-bearing equipment of the underground traction system. Accurate detection of wire rope defects and positions exerts an exceedingly crucial role in safe production. The existing defect detection solutions exhibit some deficiencies pertaining to the flexibility, accuracy and real-time performance of wire rope defect detection. To solve the aforementioned problems, this study utilizes the camera to sample the wire rope before the well entry, and proposes an object based on YOLOv5. The surface small-defect detection model realizes the accurate detection of small defects outside the wire rope. The transfer learning method is also introduced to enhance the model accuracy of small sample training. Herein, the enhanced YOLOv5 algorithm effectively enhances the accuracy of target detection and solves the defect detection problem of wire rope utilized in mine, and somewhat avoids accidents occasioned by wire rope damage. After a large number of experiments, it is revealed that in the task of wire rope defect detection, the average correctness rate and the average accuracy rate of the model are significantly enhanced with those before the modification, and that the detection speed can be maintained at a real-time level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.