• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.904-911
• /
• 2022

Occlusion is one of the most challenging problems for computer vision-based construction monitoring. Due to the intrinsic dynamics of construction scenes, vision-based technologies inevitably suffer from occlusions. Previous researchers have proposed the occlusion handling methods by leveraging the prior information from the sequential images. However, these methods cannot be employed for construction object detection in non-sequential images. As an alternative occlusion handling method, this study proposes a data augmentation-based framework that can enhance the detection performance under occlusions. The proposed approach is specially designed for rebar occlusions, the distinctive type of occlusions frequently happen during construction worker detection. In the proposed method, the artificial rebars are synthetically generated to emulate possible rebar occlusions in construction sites. In this regard, the proposed method enables the model to train a variety of occluded images, thereby improving the detection performance without requiring sequential information. The effectiveness of the proposed method is validated by showing that the proposed method outperforms the baseline model without augmentation. The outcomes demonstrate the great potential of the data augmentation techniques for occlusion handling that can be readily applied to typical object detectors without changing their model architecture.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.144-146
• /
• 2004

Stereo image analysis has been an important tool for reconstructing 3D terrain. By In its nature, occlusion is one of difficulties we cannot avoid in stereo matching. This paper presents a study on occlusion detection by employing LRC(Left-Right Check) and OCC(Occlusion Constraint). Experimental results show that these method can effectively detect occluded regions and those regions are usually occurred around object contours and scene discontinuity.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권4호
• /
• pp.267-273
• /
• 2005

Stereo image analysis has been an important tool for reconstructing 3D terrain. By In its nature, occlusion is one of difficulties Ive cannot avoid in stereo matching. This paper presents a study on occlusion detection by employing LRC(Left-Right Check) and OCC(Occlusion Constraint) and how we can improve the accuracy of DEM(Digital Elevation Model) y using interpolated data into the detected occluded area. Experimental results show that these method can effectively detect occluded regions and improve the accuarcy of DEM using the occlusion detection.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.55-61
• /
• 2017

In this paper, we propose a novel tracking method using target separation and detection that are based on discriminative correlation filter (DCF), which is studied a lot recently. 'Retainability' is one of the most important factor of tracking. There are some factors making retainability of tracking worse. Especially, fast movement and occlusion of a target frequently occur in image data, and when it happens, it would make target lost. As a result, the tracking cannot be retained. For maintaining a robust tracking, in this paper, separation of a target is used so that normal tracking is maintained even though some part of a target is occluded. The detection algorithm is executed and find new location of the target when the target gets out of tracking range due to occlusion of whole part of a target or fast movement speed of a target. A variety of experiments with various image data sets are conducted. The algorithm proposed in this paper showed better performance than other conventional algorithms when fast movement and occlusion of a target occur.

• 드라이브 ㆍ 컨트롤
• /
• 제19권3호
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

• 센서학회지
• /
• 제24권1호
• /
• pp.54-61
• /
• 2015

In recent years, there has been increasing use of automatic surveillance and monitoring systems based on vision sensors. Humans are often the most important target in the systems, but processing human images is difficult due to the small sizes and flexible motions. Particularly, occlusion among pedestrians in camera images brings practical problems. In this paper, we propose a novel method to separate image regions of occluded pedestrians. A camera equipped with a wide angle lens is attached to the ceiling of a building corridor for sensing pedestrians with a wide field of view. The output images of the camera are processed for the human detection, tracking, identification, distortion correction, and occlusion handling. We resolve the occlusion problem adaptively depending on the angles and positions of their heads. Experimental results showed that the proposed method is more efficient and accurate compared with existing methods.

• 방송공학회논문지
• /
• 제20권2호
• /
• pp.265-272
• /
• 2015

폐색영역 탐지(Occlusion detection)와 중간값 필터(Median filter)를 조합한 새로운 움직임 추정 기반의 프레임율 변환(Frame rate up-conversion based on motion estimation) 기술을 소개한다. 움직임 추정은 움직임 벡터(Motion vector)를 얻기 위해 수행한다. 그 후 폐색영역 탐지방법은 폐색된 부분에서 움직임 벡터를 개선한다. 폐색된 영역에서는 잘못된 움직임 벡터를 찾을 가능성이 높으므로 움직임 벡터 의존율이 적은 중간값 필터를 적용하고, 비폐색된 영역에서는 움직임 벡터가 연속적이고 신뢰도가 높으므로 BDMC(Bi-Directional Motion Compensated interpolation)를 적용하여 보간 영상을 생성한다. 양방향 움직임 벡터를 사용하는 BDMC는 움직임 벡터의 연속성과 신뢰도가 높을수록 좋은 결과를 얻는다. 실험결과에서 제안된 알고리즘이 기존의 방법보다 더 나은 성능을 갖는다. 실험에서의 평균 PSNR(Peak signal to noise ratio)은 테스트 시퀀스들에 대하여 BDMC 대비 약 0.16dB 향상되었다.

• 지적과 국토정보
• /
• 제48권2호
• /
• pp.213-225
• /
• 2018

3차원 공간정보 구축을 위해 건물 텍스처를 촬영하는 과정에서 폐색영역 문제가 발생한다. 이를 해결하기 위해선 폐색영역을 자동 인식하여 이를 검출하고 텍스처를 자동 보완하는 자동화 기법 연구가 필요하다. 현실적으로 매우 다양한 구조물 형상과 폐색을 발생시키는 경우가 있으므로 이를 극복하는 대안들이 고려되고 있다. 본 연구는 최근 대두되고 있는 딥러닝 기반의 알고리즘을 이용하여 폐색지역 패턴화하고, 학습기반 폐색영역 자동 검출하는 접근을 시도한다. 영상 내 객체 추출에서 우수한 성과를 발표하는 Convolutional Neural Network (CNN) 기법의 향상된 알고리즘인 Faster Region-based Convolutional Network (R-CNN)과 Mask R-CNN 2가지를 이용하여, 건물 벽면 촬영 시 폐색을 유발하는 사람, 현수막, 차량, 신호등에 대한 자동 탐지하는 성능을 알아보기 위해 실험하고, Mask R-CNN의 미리 학습된 모델에 현수막을 학습시켜 자동탐지하는 실험을 통해 적용이 높은 결과를 확인할 수 있었다.

• 대한토목학회논문집
• /
• 제28권3D호
• /
• pp.417-422
• /
• 2008

전통적인 정사영상 제작기법으로는 이중 투영으로 인한 원치 않는 구조물의 중복이 정사영상 안에 생길 수 있다. 특히 고층 빌딩이 밀집된 도심지역에서는 고도의 변화가 심하여 이러한 현상이 자주 발생한다. 이러한 문제들로 인하여 도심지역의 폐색영역 탐지는 정확한 엄밀 정사영상(true orthophoto)의 제작에 있어서 매우 중요한 문제이다. 본 논문은 항공영상과 LiDAR로부터 가시고도 기반의 폐색영역 탐지기법을 다루고 있다. 본 논문에서는 LiDAR의 포인트 클라우드 데이터로부터 격자형태의 수치표고모형(DSM)을 제작한 후, DSM과 항공영상의 촬영점을 이용한 가시고도 기반의 폐색영역 탐지기법을 제안하였다. 마지막으로 만들어진 DSM과 전 과정에서 만들어진 폐색맵을 이용한 엄밀 정사영상의 제작과정을 기술하였다. 제안된 알고리즘은 미국 인디애나 주의 퍼듀 캠퍼스 지역에 적용되었다.