• 한국산업정보학회논문지
• /
• 제20권2호
• /
• pp.45-56
• /
• 2015

본 논문에서는 스마트폰 카메라의 객체기반 자동초점 기능을 위해, 움직이는 물체의 고속 추적 방법을 제안한다. 사양이 낮은 플랫폼에서의 비-학습 제약을 고려하여 히스토그램 특징 기반의 슬라이딩 윈도우 검출 기법을 사용한다. 각 부분 윈도우에 대한 히스토그램의 계산 시간문제는 적분 히스토그램을 통해 해결한다. 본 논문에서는 지역적 후보 검출, 적응적 템플릿 크기 방법을 제안한다. 또한 추적 위치의 안정화를 위해 정합 함수에 안정화 항을 추가하는 기법을 제안한다. 자체 수집한 데이터에 대한 실험결과는 PC 환경에서 초당 100 프레임 수준의 높은 처리 속도 달성을 보여주었다.

• 한국화재소방학회논문지
• /
• 제9권1호
• /
• pp.3-9
• /
• 1995

This paper is a study to dectect the tracking owing to deterioration of indoor wiring, and to prevent the electrical fire. After analysing the harmonics of waveshapes in load current and tracking current by FFT, a method of identifying the tracking was developed by using neural network. Fluoscent lamp, witch was mostly used in indoor, was chosen as the load used in this study. When the learning number in neural network was more then 30,000 times, an excellent neural net-work which could correctly identify the tracking was established. Therefore, the result of this study can be utilized as a basic material in various measuring instruments, such as an hotline inslation tester, earth tester in vehicles, and tracking fire alarm device, witch can detect the tracking under the condition of hotline.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.115-122
• /
• 2024

Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset,which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases.In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.439-449
• /
• 2023

In an era marked by the increasing use of drones and the growing demand for indoor surveillance, the development of a robust application for detecting and tracking both drones and humans within indoor spaces becomes imperative. This study presents an innovative application that uses FMCW radar to detect human and drone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applications with Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objects present in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clustering drone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned and classified into either humans or drones by employing a deep learning model. A trio of models, including Deep Neural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and the outcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy for identifying drone clusters and a noteworthy 96.75% accuracy for human clusters.

• The Korean journal of internal medicine
• /
• 제39권4호
• /
• pp.555-562
• /
• 2024

This study reviews the recent progress of artificial intelligence for colonoscopy from detection to diagnosis. The source of data was 27 original studies in PubMed. The search terms were "colonoscopy" (title) and "deep learning" (abstract). The eligibility criteria were: (1) the dependent variable of gastrointestinal disease; (2) the interventions of deep learning for classification, detection and/or segmentation for colonoscopy; (3) the outcomes of accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1, intersection of union (IOU), Dice and/or inference frames per second (FPS); (3) the publication year of 2021 or later; (4) the publication language of English. Based on the results of this study, different deep learning methods would be appropriate for different tasks for colonoscopy, e.g., Efficientnet with neural architecture search (AUC 99.8%) in the case of classification, You Only Look Once with the instance tracking head (F1 96.3%) in the case of detection, and Unet with dense-dilation-residual blocks (Dice 97.3%) in the case of segmentation. Their performance measures reported varied within 74.0-95.0% for accuracy, 60.0-93.0% for sensitivity, 60.0-100.0% for specificity, 71.0-99.8% for the AUC, 70.1-93.3% for precision, 81.0-96.3% for F1, 57.2-89.5% for the IOU, 75.1-97.3% for Dice and 66-182 for FPS. In conclusion, artificial intelligence provides an effective, non-invasive decision support system for colonoscopy from detection to diagnosis.

• Advances in nano research
• /
• 제12권2호
• /
• pp.223-239
• /
• 2022

Object detection has always been to pursue objects with particular properties or representations and to predict details on objects including the positions, sizes and angle of rotation in the current picture. This was a very important subject of computer vision science. While vision-based object tracking strategies for the analysis of competitive videos have been developed, it is still difficult to accurately identify and position a speedy small ball. In this study, deep learning (DP) network was developed to face these obstacles in the study of tennis motion tracking from a complex perspective to understand the performance of athletes. This research has used CNN-VGG 16 to tracking the tennis ball from broadcasting videos while their images are distorted, thin and often invisible not only to identify the image of the ball from a single frame, but also to learn patterns from consecutive frames, then VGG 16 takes images with 640 to 360 sizes to locate the ball and obtain high accuracy in public videos. VGG 16 tests 99.6%, 96.63%, and 99.5%, respectively, of accuracy. In order to avoid overfitting, 9 additional videos and a subset of the previous dataset are partly labelled for the 10-fold cross-validation. The results show that CNN-VGG 16 outperforms the standard approach by a wide margin and provides excellent ball tracking performance.

• 한국BIM학회 논문집
• /
• 제13권2호
• /
• pp.29-36
• /
• 2023

This study explores the potential of utilizing video-based data analysis and machine learning techniques to estimate the number of occupants within a building. The research methodology involves developing a sophisticated counting system capable of detecting and tracking individuals' entry and exit patterns. The proposed method demonstrates promising results in various scenarios; however, it also identifies the need for improvements in camera performance and external environmental conditions, such as lighting. The study emphasizes the significance of incorporating machine learning in architectural and urban planning applications, offering valuable insights for the field. In conclusion, the research calls for further investigation to address the limitations and enhance the system's accuracy, ultimately contributing to the development of a more robust and reliable solution for building occupancy estimation.

• 스마트미디어저널
• /
• 제1권3호
• /
• pp.48-55
• /
• 2012

In general, background subtraction based methods are used to detect the moving objects in visual tracking applications. In this paper we employed background subtraction based scheme to detect the temporarily stationary objects. We proposed two schemes for stationary object detection and we compare those in terms of detection performance and computational complexity. In the first approach we used single background and in the second approach we used dual backgrounds, generated with different learning rates, in order to detect temporarily stopped object. Finally, we used normalized cross correlation (NCC) based image comparison to monitor and track the detected stationary object in a video scene. The proposed method is robust with partial occlusion, short time fully occlusion and illumination changes, as well as it can operate in real time.

• 로봇학회논문지
• /
• 제16권4호
• /
• pp.336-344
• /
• 2021

This paper presents a robust deep learning-based human tracking framework in crowded environments. For practical human tracking applications, a target must be robustly tracked even in undetected or overcrowded situations. The proposed framework consists of two parts: robust deep learning-based human detection and tracking while recognizing the aforementioned situations. In the former part, target candidates are detected using Detectron2, which is one of the powerful deep learning tools, and their weights are computed and assigned. Subsequently, a candidate with the highest weight is extracted and is utilized to track the target human using a Kalman filter. If the bounding boxes of the extracted candidate and another candidate are overlapped, it is regarded as a crowded situation. In this situation, the center information of the extracted candidate is compensated using the state estimated prior to the crowded situation. When candidates are not detected from Detectron2, it means that the target is completely occluded and the next state of the target is estimated using the Kalman prediction step only. In two experiments, people wearing the same color clothes and having a similar height roam around the given place by overlapping one another. The average error of the proposed framework was measured and compared with one of the conventional approaches. In the error result, the proposed framework showed its robustness in the crowded environments.