• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.1311-1311
• /
• 2024

Recent advances in artificial intelligence technology have led to active research aimed at systematically managing the productivity and environmental impact of major management targets such as heavy equipment at construction sites. However, challenges arise due to phenomena like partial occlusions, resulting from the dynamic working environment of construction sites (e.g., equipment overlapping, obstruction by structures), which impose practical constraints on precisely monitoring heavy equipment. To address these challenges, this study aims to enhance automated multi-object tracking (MOT) in scenarios involving long-term occlusions across consecutive frames for heavy construction equipment. To achieve this, two methodologies are employed to address long-term occlusions at construction sites: (i) tracking-by-detection and (ii) video inpainting with generative adversarial networks (GANs). Firstly, this study proposes integrating FairMOT with a tracking-by-detection algorithm like ByteTrack or SMILEtrack, demonstrating the robustness of re-identification (Re-ID) in occlusion scenarios. This method maintains previously assigned IDs when heavy equipment is temporarily obscured and then reappears, analyzing location, appearance, or motion characteristics across consecutive frames. Secondly, adopting video inpainting with GAN algorithms such as ProPainter is proposed, demonstrating robustness in removing objects other than the target object (e.g., excavator) during the video preprocessing and filling removed areas using information from surrounding pixels or other frames. This approach addresses long-term occlusion issues by focusing on a single object rather than multiple objects. Through these proposed approaches, improvements in the efficiency and accuracy of detection, tracking, and activity recognition for multiple heavy equipment are expected, mitigating MOT challenges caused by occlusions in dynamic construction site environments. Consequently, these approaches are anticipated to play a significant role in systematically managing heavy equipment productivity, environmental impact, and worker safety through the development of advanced construction and management systems.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.558-570
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권8호
• /
• pp.591-595
• /
• 2009

센서 네트워크에서 개체 검출과 추적에 관한 기존 라우팅 프로토콜들은 사람, 동물, 차량 등과 같은 하나 또는 그 이상의 단일(individual) 개체들에 대한 검출과 추적을 하기 위한 방법에만 관심을 가질 뿐, 독가스, 생화학물질 등과 같은 연속적인 개체들을 검출하고 추적하는 프로토콜들은 많지 않다. 이러한 연속적인 개체들은 어느 지역에 계속적으로 분산되어 있고, 광범위한 지역을 차지한다는 점에서 단일 개체들과 차이가 있다. 따라서 많은 센서 노드들에 의해 검출되고 센싱되는 데이터들은 중복적이고 서로 깊이 관련되어 있다. 그러므로 지역적으로 센싱 데이터를 수집하고 통합하여 데이터를 보고하기 위한 효율적인 방안이 필요하다. 본 논문에서 우리는 연속적인 개체들을 검출, 추적하고 모니터링(monitoring)하기 위한 동적인 직사각형 영역에 기반한 연속적인 개체 추적 방안을 제안한다. 제안된 방안은 하나의 연속된 개체가 차지한 지역이 포함된 동적인 직사각형 영역을 구성하고, 영역에서 하나의 대표 노드가 연속된 개체를 검출하는 센서 노드들로부터 센싱 데이터를 수집하고 통합한다.

• 스마트미디어저널
• /
• 제13권5호
• /
• pp.9-18
• /
• 2024

객체 궤적 모델링은 다중 객체 추적(Multi Object Tracking, MOT)의 주요 과제다. CenterTrack은 객체 중심 위치를 추적하는 Heatmap 기반의 방법으로 이를 해결하고자 했다. 하지만 복잡한 움직임과 비선형성을 가진 객체를 추적할 때 제한적인 성능을 보였다. 우리는 CenterTrack의 성능 저하 요인을 보행자의 동적 움직임으로 간주하여 확장된 칼만 필터(Extended Kalman Filter, EKF)를 CenterTrack에 통합했다. 우리가 제안하는 방법의 우수성을 입증하기 위해 기존 칼만 필터(Kalman Filter, KF)와 무향 칼만 필터(Unscented Kalman Filter, UKF)를 CenterTrack에 적용 후 다양한 데이터셋에 비교 평가했다. 실험결과, EKF를 CenterTrack에 통합했을 때 73.7% MOTA(Multiple Object Tracking Accuracy)를 달성하며 CenterTrack에 가장 적합한 필터임을 확인했다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.445-448
• /
• 2003

In this paper, we present a hierarchical approach of an enhanced active shape model for video tracking. Kalman filter is used. To estimate a dynamic shape in video object tracking. The experimental results show that the proposed hierarchical active shape model using Kalman filter is efficient.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.367-374
• /
• 2024

The detection and tracking of construction workers in building sites generate valuable data on unsafe behavior, work productivity, and construction progress. Many computer vision-based tracking approaches have been investigated and their capabilities for tracking construction workers have been tested. However, the dynamic nature of real-world construction environments, where workers wear similar outfits and move around in often cluttered and occluded regions, has severely limited the accuracy of these methods. Herein, to enhance the performance of vision-based tracking, a new framework is proposed which seamlessly integrates three computer vision components: detection, tracking, and re-identification (DTR). In DTR, a tracking algorithm continuously tracks identified workers using a detector and tracker in combination. Then, a re-identification model extracts visual features and utilizes them as appearance descriptors in subsequent frames during tracking. Empirical results demonstrate that the proposed method has excellent multi-object-tracking accuracy with better accuracy than an existing approach. The DTR framework can efficiently and accurately monitor workers, ensuring safer and more productive dynamic work environments.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1299-1319
• /
• 2017

This paper presents a scalable multiple camera collaboration strategy for active tracking applications in large areas. The proposed approach is based on distributed mechanism but emulates the master-slave mechanism. The master and slave cameras are not designated but adaptively determined depending on the object dynamic and density distribution. Moreover, the number of cameras emulating the master is not fixed. The collaboration among the cameras utilizes global and local sectors in which the visual correspondences among different cameras are determined. The proposed method combines the local information to construct the global information for emulating the master-slave operations. Based on the global information, the load balancing of active tracking operations is performed to maximize active tracking coverage of the highly dynamic objects. The dynamics of all objects visible in the local camera views are estimated for effective coverage scheduling of the cameras. The active tracking synchronization timing information is chosen to maximize the overall monitoring time for general surveillance operations while minimizing the active tracking miss. The real-time simulation result demonstrates the effectiveness of the proposed method.

• 한국정밀공학회지
• /
• 제16권7호
• /
• pp.125-131
• /
• 1999

In this paper, the algorithms which can track the two dimensional moving circular object using simple vision system are described. In order to track the moving object, the process of finding the object feature points - such as centroid of the object, corner points, area - is indispensable. With the assumption of two-dimensional circular moving object, the centroid of the circular object is computed from three points on the object circumference. Different kinds of algorithms for computing three edge points - simple x directional detection method, stick method. T-shape method are suggested. Through the computer simulation and experiments, three algorithms are compared from the viewpoint of detection accuracy and computational time efficiency.

• 한국컴퓨터정보학회논문지
• /
• 제21권6호
• /
• pp.63-69
• /
• 2016

In this paper, we proposed the location tracking system based on MS-Based/Assisted(Mobile Station-Based and Assisted) location trigger service model with context-awareness for the intelligent location tracking of moving objects. It provides the proper resulting value that matches the context of users through the analysis about the situation of the user, physical environment, computing resource and the existing information on user input. In order to provide real-time data, we proposed the location tracking system which realizes the intelligent information such as the expecting arrival time and passing the specific area of the moving object by adopting the location trigger. So, it derives to minimize the costs of communication for the mobile object tracking applications. The proposed location tracking system based on context-awareness can be used for realtime monitoring, intelligent alarm/action, setting up of the optimized moving path, dynamic adjustment of strategies and policies. So it has the advantage to develop the application system which is aimed at optimization of the object tracking and movement.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.712-715
• /
• 1997

In image jacobian based visual servoing, generally, inverse jacobian should be calculated by complicated coordinate transformations. These are required excessive computation and the singularity of the image jacobian should be considered. This paper presents a visual servoing to control the pose of the robotic manipulator for tracking and grasping 3-D moving object whose pose and motion parameters are unknown. Because the object is in motion tracking and grasping must be done on-line and the controller must have continuous learning ability. In order to estimate parameters of a moving object we use the kalman filter. And for tracking and grasping a moving object we use a fuzzy inference based reinforcement learning algorithm of dynamic recurrent neural networks. Computer simulation results are presented to demonstrate the performance of this visual servoing