다중 초기 소실점을 이용한 소실점 검출 방법

이창형(Chang-Hyung Lee),최형일(Hyung-Il Choi) 한국콘텐츠학회 2018 한국콘텐츠학회논문지 Vol.18 No.2

본 논문은 다중 초기 소실점 후보를 사용해서 소실점을 검출하는 것을 제안한다. 소실점은 3차원 구조복원 등에 사용되는 중요한 기하정보이다. 소실점은 실내 환경의 경우 세 개의 소실점이 검출된다. 기존 초기 소실점을 하나만 검출하는 방식은 가장 높은 투표합의 초기 소실점이 최적의 소실점의 위치와 다를 수 있기에 부정확 할 수 있다. 따라서 여러 개의 초기 소실점 후보 중 가장 좋은 소실점 후보를 채택하는 방식을 사용하면 처음 구해지는 초기 소실점이 적절치 않은 소실점일 경우를 대비할 수 있다. 또한 본 논문에서는 검출된 소실점을 후처리를 통해서 소실점의 위치를 조정하는 방법을 제안한다. 후처리를 통해 기존보다 정확한 소실점을 검출할 수 있다. 실험 결과는 제안하는 방법을 통해 소실점 검출의 정확도가 기존방법보다 약 1~2% 가량 높음을 보여주며, 이에 따라 성능이 향상되었음을 알 수 있다. In this paper, we propose a vanishing point detection method using multiple initial vanishing points. Vanishing points are important geometric information that is used for reconstructing 3D structures. Three vanishing points are detected for indoor scenes. In the previous work, it could be inaccurate to detect only one initial vanishing point, because initial vanishing point getting most highest sum of voting could be deferent from the best initial vanishing point. Therefore the method which sets multiple initial vanishing point and detects a best vanishing point from them gives us preparation for the prior case. Also in this paper, we propose a adjusting vanishing point method by postprocessing of detected vanishing points. We could detect more accurate vanishing point by using postprocessing. Experimental results show that the accuracy of the vanishing point detection is about 1~2% higher than that of the existing method through the proposed method and the performance is improved accordingly.

소실점 추정 정확도 개선을 통한 SVM 성능 향상

안상근,서태규,전광길,조중휘,Ahn, Sang-Geun,Seo, Tae-Kyu,Jeon, Gwang-Gil,Cho, Joong-Hwee 대한임베디드공학회 2016 대한임베디드공학회논문지 Vol.11 No.6

In this paper, we propose an improved single view metrology (SVM) algorithm to accurately measure the height of objects. In order to accurately measure the size of objects, vanishing points have to be correctly estimated. There are two methods to estimate vanishing points. First, the user has to choose some horizontal and vertical lines in real world. Then, the user finds the cross points of the lines. Second, the user can obtain the vanishing points by using software algorithm such as [6-9]. In the former method, the user has to choose the lines manually to obtain accurate vanishing points. On the other hand, the latter method uses software algorithm to automatically obtain vanishing points. In this paper, we apply image resizing and edge sharpening as a pre-processing to the algorithm in order to improve performance. The estimated vanishing points algorithm create four vanishing point candidates: two points are horizontal candidates and the other two points are vertical candidates. However, a common image has two horizontal vanishing points and one vertical vanishing point. Thus, we eliminate a vertical vanishing point candidate by analyzing the histogram of angle distribution of vanishing point candidates. Experimental results show that the proposed algorithm outperforms conventional methods, [6] and [7]. In addition, the algorithm obtains similar performance with manual method with less than 5% of the measurement error.

다중 영상과 호모그래피 행렬을 이용한 소실점 위치 향상 알고리즘

이창형(Chang-Hyung Lee),최형일(Hyung-Il Choi) 한국산학기술학회 2019 한국산학기술학회논문지 Vol.20 No.1

본 논문은 다중 영상과 호모그래피 행렬을 통해 소실점 위치의 정확도를 향상시키는 알고리즘을 제안한다. 단일 영상만을 활용하여 소실점 검출이 가능하지만, 여러 영상의 정보를 활용하여 소실점의 위치를 보정하면 소실점 위치의 정확도를 더 향상시킬 수 있다. 위치 정확도가 향상된 소실점을 통해 더 정확한 실내공간 정보 검출이 가능하다. 이를 위해 본 논문에서는 3개의 영상을 입력받아 정보를 검출한 후 영상의 벽면 간의 호모그래피 행렬을 검출하고, 검출된 호모그래피를 이용하여 소실점의 위치를 변환한다. 최종적으로 변환된 소실점 중 최적의 위치에 있는 소실점을 찾아내어 소실점 위치를 보정 함으로써 소실점 위치의 정확도를 향상시킨다. 실험 결과를 통해 기존의 알고리즘과 제안하는 알고리즘의 정확도를 비교 분석한다. 제안하는 알고리즘을 통해 소실점 위치에 대한 오차 각도가 약 1.62% 감소함을 확인하였고, 이를 통해 더 정밀한 소실점 검출이 가능하였다. 또한, 제안한 알고리즘을 통해 향상된 소실점을 이용하여 검출한 레이아웃이 기존 알고리즘의 결과에 비교해 더 정확한 것을 확인 할 수 있었다. In this paper, we propose vanishing-point position-improvement algorithms by using multiple images and a homography matrix. Vanishing points can be detected from a single image, but the positions of detected vanishing points can be improved if we adjust their positions by using information from multiple images. More accurate indoor space information detection is possible through vanishing points with improved positional accuracy. To adjust a position, we take three images and detect the information, detect the homography matrix between the walls of the images, and convert the vanishing point positions using the detected homography. Finally, we find an optimal position among the converted vanishing points and improve the vanishing point position. The experimental results compared an existing algorithm and the proposed algorithm. With the proposed algorithm, we confirmed that the error angle to the vanishing point position was reduced by about 1.62%, and more accurate vanishing point detection was possible. In addition, we can confirm that the layout detected by using improved vanishing points through the proposed algorithm is more accurate than the result from the existing algorithm.

Vanishing Point Detection using Reference Objects

이상돈,Sudarshan Pant 한국멀티미디어학회 2018 멀티미디어학회논문지 Vol.21 No.2

Detection of vanishing point is a challenging task in the situations where there are several structures with straight lines. Commonly used approaches for determining vanishing points involves finding the straight lines using edge detection and Hough transform methods. This approach often fails to perform effectively when there are a lot of straight lines found. The lines not meeting at a vanishing point are considered to be noises. In such situation, finding right candidate lines for detecting vanishing points is not a simple task. This paper proposes to use reference objects for vanishing point detection. By analyzing a reference object, it identifies the contour of the object, and derives a polygon from the contour information. Then the edges of the detected polygon are used to find the vanishing points. Our experimental results show that the proposed approach can detect vanishing points with comparable accuracy to the existing edge detection based method. Our approach can also be applied effectively even to complex situations, where too many lines generated by the existing methods make it difficult to select right lines for the vanishing points.

Vanishing Point Detection using Reference Objects

Lee, Sangdon,Pant, Sudarshan Korea Multimedia Society 2018 멀티미디어학회논문지 Vol.21 No.2

Detection of vanishing point is a challenging task in the situations where there are several structures with straight lines. Commonly used approaches for determining vanishing points involves finding the straight lines using edge detection and Hough transform methods. This approach often fails to perform effectively when there are a lot of straight lines found. The lines not meeting at a vanishing point are considered to be noises. In such situation, finding right candidate lines for detecting vanishing points is not a simple task. This paper proposes to use reference objects for vanishing point detection. By analyzing a reference object, it identifies the contour of the object, and derives a polygon from the contour information. Then the edges of the detected polygon are used to find the vanishing points. Our experimental results show that the proposed approach can detect vanishing points with comparable accuracy to the existing edge detection based method. Our approach can also be applied effectively even to complex situations, where too many lines generated by the existing methods make it difficult to select right lines for the vanishing points.

Histogram of Oriented Gradient를 이용한 실시간 소실점 검출

최지원(Jiwon Choi),김창익(Changick Kim) 大韓電子工學會 2011 電子工學會論文誌-SP (Signal processing) Vol.48 No.2

소실점이란 실제 공간의 평행한 선들이 영상 내에 투영되면서 한곳에 모이는 점이다. 본 논문에서는 이러한 소실점의 특성을 이용한 실시간 소실점 검출 알고리즘을 제안한다. 기존의 소실점 검출 방법은 1) 복잡한 계산이 요구되거나 2) 알고리즘에 따라 소실점을 검출할 수 있는 영상이 제한되어 있다. 제안하는 방법은 블록 기반의 HOG(Histogram of Oriented Gradient)를 구하여 영상의 구조적 특성을 이용하는 것으로 영상 내에 존재하는 소실점을 실시간으로 검출한다. 먼저 영상의 블록 단위로 HOG 기술자를 구한 뒤, 제안하는 동적 프로그래밍(dynamic programing)을 이용하여 소실점의 위치를 예측한다. 본 논문에서는 다양한 영상에 대한 실험을 통해 제안하는 알고리즘이 효율적인 소실점 검출 방법임을 보이고자 한다. Vanishing point can be defined as a point generated by converged perspective lines, which are parallel in the real world. In this paper, we propose a real-time vanishing point detection algorithm using this fundamental feature of vanishing point. The existing methods 1) require high computational cost or 2) are restricted to specific image contents. The proposed method detects the vanishing point in images based on the block-wise HOG (Histogram of Oriented Gradient) descriptor. First, we compute the HOG descriptor in a block-wise manner, then estimate the location of the vanishing point using the proposed dynamic programing. Experiments are performed on diverse images to confirm the efficiency of the proposed method.

3D Mapping and Estimation from Moving Direction of Indoor Mobile Robot using Vanishing Points

Sung-Woo Song,Kang-Hyun Jo 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

There are many boundaries of artificial objects which are appeared as edges in the image. These line segments as edge impose information for understanding indoor environment. We obtain 3-dimension positional information as we use a stereo camera. There are three dominant vanishing points(VPs) in 3D world. We can separatelines and estimate forward direction by using VP. Groups of such coinciding lines which extend to the same VP aredetermined by angles between them. Also the crossing points transform to ICIS (Inverted Coordinates Image Space).The ICIS is proposed method to detect VPs in an infinite or finite image space. If the crossing points exist in the image, there is not transformation. However, crossing points are out of image, then, crossing points transform to ICIS. VPs are determined by distribution in ICIS. They impose maximally 3 groups. Disparity of depth direction VP calculates for its 3D position. Among them, we need to determine a dominant VP which comes from vertical lines for corresponding. Tocorrespond the line segments, the smallest SAD (Sum of Absolute Difference) value used beside area of them. We also compare the order and direction of lines. Disparities from corresponding lines between stereo images are calculated forthis so that 3D position is calculated by triangulation. Evading from the perspective effect which occur 3D sceneprojects into 2D image thus size or angle changes, geometric ratios are used for rectifying such changes. We alreadyknow 3D position of depth direction VP and vertical lines before rectifying. So, rectification is to add before rectifying values to obtained values which are geometric ratio between VP and vertical lines. 3D map is obtained from rectifying 3D position. Also, moving direction estimates from angle between VP and principal point. We experiment several slant,tilt or pan images. VP and principal point detected, when the robot also looked at floor or wall.

RANSAC을 이용한 실외 도로 환경의 소실점 예측 방법

원선희(Sun-Hee Weon),주성일(Sung-Il Joo),최형일(Hyung-Il Choi) 한국컴퓨터정보학회 2013 韓國컴퓨터情報學會論文誌 Vol.18 No.9

본 논문에서는 입력된 자연영상으로부터 도로 영역을 검출하기 위한 소실점 자동 예측 방법을 제안한다. 제안하는 방법에서는 도로 환경에서 안정적으로 소실점을 검출하기 위해 영상의 주방향성을 분석하여 영상 특징성분들이 집중되는 곳을 소실점으로 예측한다. 이를 위해 첫번째 단계에서는, 영상을 일정크기의 서브블록으로 분할하고 분할된 서브블록 내에서 임의의 에지 샘플을 선택하고 RANSAC을 적용하여 직선 모델을 예측함으로서 각 서브블록의 주방향성을 분석한다. 모든 블록에 대하여 주방향성을 검출한 후, 두 번째 단계에서 임의의 직선 샘플을 선택하고 RANSAC을 적용하여 교점 모델을 예측함으로서 각 직선들로 인한 교점 모델의 비용값을 측정하고 가장 높은 비용값의 교점 모델에 의한 평균점으로 소실점을 예측한다. 마지막으로 성능 검증을 위해 다양한 상황에 따른 정량적, 정성적 분석을 통해 제안하는 소실점 검출 알고리즘의 타당성과 효율성을 입증한다. This paper proposes a method of automatically predicting the vanishing point for the purpose of detecting the road region from natural images. The proposed method stably detects the vanishing point in the road environment by analyzing the dominant orientation of the image and predicting the vanishing point to be at the position where the feature components of the image are concentrated. For this purpose, in the first stage, the image is partitioned into sub-blocks, an edge sample is selected randomly from within the sub-block, and RANSAC is applied for line fitting in order to analyze the dominant orientation of each sub-block. Once the dominant orientation has been detected for all blocks, we proceed to the second stage and randomly select line samples and apply RANSAC to perform the fitting of the intersection point, then measure the cost of the intersection model arising from each line and we predict the vanishing point to be located at the average point, based on the intersection point model with the highest cost. Lastly, quantitative and qualitative analyses are performed to verify the performance in various situations and prove the efficiency of the proposed algorithm for detecting the vanishing point.

Fast and Accurate Self-calibration Using Vanishing Point Detection in Manmade Environments

Sang Jun Lee,Sung-Soo Hwang 제어·로봇·시스템학회 2020 International Journal of Control, Automation, and Vol.18 No.10

Interests of auto-calibration have been increased in several camera systems. This paper presents a novel self-calibration method using a fast and accurate vanishing point detection algorithm that works in manmade environments. The proposed algorithm estimates focal length assuming that the principal point is the center of an image to satisfy the orthogonality of three vanishing points. By using the proposed vanishing point detection algorithm and minimization of the proposed objective function, the proposed system detects accurate vanishing points with focal length outperforming other methods. The proposed vanishing point detection algorithm detects vanishing points by using J-linkage based method that is more delicate by fragmentation and re-merging strategies. The proposed objective function finally detects vanishing points that meet orthogonality among estimated hypotheses for vanishing points by checking several geometric relationships. We believe that the proposed method can be used for automatic camera calibration, localization of a camera in an autonomous navigation system, and three-dimensional reconstruction of a single-view image.

A Study on 3D Panorama System Using Depth-map Generation Techniques

Jong Chan Kim,Oh Hoon Cho,Eung Kon Kim 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.9

The point is a vanishing point and the lines which meet at the point are vanishing lines. Depth-map can be generated to restore a 3D space structure from the 2D images using the vanishing point. The research described in this paper compensates for the disadvantages of depth-map generation techniques that need to restore a 3D spatial structure from a 2D image. In addition, a 3D panorama system is proposed. The 3D panorama system using depth-map generation techniques creates a 3D effect in which users feel that they are standing at the shooting location and looking around. The 3D panorama system provides a free time for nearby objects and distant background in a wide area, and it creates realistic 3D images such as constant high-quality pictures. The 3D panorama system will offer the sense for the real and the immersion as it gets over the limit of 2D panorama technology and supports users with a natural navigation. The 3D panorama image using depth-map is worth noticing since it shows the possibility to use the construction of image based virtual system.