• 디지털융복합연구
• /
• 제11권12호
• /
• pp.345-352
• /
• 2013

본 논문에서는 GPU(Graphics Processing Unit)에서 데이터를 처리할 수 있게 하여 단일 영상에서 효율적으로 깊이를 추정하는 방법을 제안한다. 단일 영상은 카메라의 투영 과정에 의해 깊이 정보가 소실되게 되며 영상에서 소실된 깊이를 추정하기 위해서 단안 단서를 이용한다. 제안하는 깊이 추정 알고리즘은 좀 더 신뢰성 있는 깊이를 추정하고자 여러 단안 단서를 이용하며 에너지 최소화를 통해 단안 단서들을 결합한다. 그러나 여러 단안 단서들을 고려해야하기 때문에 처리해야 할 데이터가 많은 단점이 존재한다. 따라서 GPGPU(General Purpose Graphics Processing Unit)를 통해 데이터를 병렬적으로 처리하게 하여 효율적으로 깊이를 추정하는 방법을 제안한다. 객관적인 효율성을 검증하기 위해 PSNR(Peak Signal to Noise Ratio)을 통해 실험하였으며 GPGPU을 이용함으로써 알고리즘의 수행시간을 평균 61.22% 감소시켰다.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• Journal of Information Processing Systems
• /
• 제16권1호
• /
• pp.155-170
• /
• 2020

Passive ranging is a critical part of machine vision measurement. Most of passive ranging methods based on machine vision use binocular technology which need strict hardware conditions and lack of universality. To measure the distance of an object placed on horizontal plane, we present a passive ranging method based on monocular vision system by smartphone. Experimental results show that given the same abscissas, the ordinatesis of the image points linearly related to their actual imaging angles. According to this principle, we first establish a depth extraction model by assuming a linear function and substituting the actual imaging angles and ordinates of the special conjugate points into the linear function. The vertical distance of the target object to the optical axis is then calculated according to imaging principle of camera, and the passive ranging can be derived by depth and vertical distance to the optical axis of target object. Experimental results show that ranging by this method has a higher accuracy compare with others based on binocular vision system. The mean relative error of the depth measurement is 0.937% when the distance is within 3 m. When it is 3-10 m, the mean relative error is 1.71%. Compared with other methods based on monocular vision system, the method does not need to calibrate before ranging and avoids the error caused by data fitting.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.588-591
• /
• 2004

In this paper, we propose a ground plane detection algorithm, using a new image processing method (IPD). To extract the ground plane from the color image acquired by monocular camera, we use a new identical pixel detection method (IPD) and an edge detection method. This IPD method decides whether the pixel is identical with the ground plane pixel or not. The IPD method needs the reference area and its performance depends on the reference area size. So we propose the reference area auto-expanding algorithm in accordance with situation. And we evaluated the proposed algorithm by the experiments in the various environments. From the experiments results, we know that the proposed algorithm is efficient in the real indoor environment.

• International Journal of Aeronautical and Space Sciences
• /
• 제16권4호
• /
• pp.581-589
• /
• 2015

This paper describes a monocular vision-based formation flight technology using two fixed wing unmanned aerial vehicles. To measuring relative position and attitude of a leader aircraft, a monocular camera installed in the front of the follower aircraft captures an image of the leader, and position and attitude are measured from the image using the KLT feature point tracker and POSIT algorithm. To verify the feasibility of this vision processing algorithm, a field test was performed using two light sports aircraft, and our experimental results show that the proposed monocular vision-based measurement algorithm is feasible. Performance verification for the proposed formation flight technology was carried out using the X-Plane flight simulator. The formation flight simulation system consists of two PCs playing the role of leader and follower. When the leader flies by the command of user, the follower aircraft tracks the leader by designed guidance and a PI control law, and all the information about leader was measured using monocular vision. This simulation shows that guidance using relative attitude information tracks the leader aircraft better than not using attitude information. This simulation shows absolute average errors for the relative position as follows: X-axis: 2.88 m, Y-axis: 2.09 m, and Z-axis: 0.44 m.

• 한국항공우주학회지
• /
• 제43권4호
• /
• pp.289-295
• /
• 2015

본 논문은 지상에서 단안 영상센서를 이용하여 항공기의 상대 위치를 측정하는 방법에 대하여 기술하는데, 알고 있는 항공기의 날개전폭과 카메라의 광학 파라미터를 이용하여 상대 거리 및 상대 위치를 측정하는 방법을 제시하였다. 또한 항공기 영상을 추출하기 위하여 차영상 기법을 이용하는 방법을 제시하였다. 이러한 기술은 ILS를 대신할 영상기반 자동착륙 시스템으로 이용될 수 있다. 상대 위치 및 거리 측정 성능을 검증하기 위하여 경비행기와 GPS를 이용하여 성능을 검증하였으며 1.85m의 평균제곱근 오차가 발생함을 확인하였다.

• 로봇학회논문지
• /
• 제14권4호
• /
• pp.357-362
• /
• 2019

This paper proposes a model and train method that can real-time detect objects and distances estimation based on a monocular camera by applying deep learning. It used YOLOv2 model which is applied to autonomous or robot due to the fast image processing speed. We have changed and learned the loss function so that the YOLOv2 model can detect objects and distances at the same time. The YOLOv2 loss function added a term for learning bounding box values x, y, w, h, and distance values z as 클래스ification losses. In addition, the learning was carried out by multiplying the distance term with parameters for the balance of learning. we trained the model location, recognition by camera and distance data measured by lidar so that we enable the model to estimate distance and objects from a monocular camera, even when the vehicle is going up or down hill. To evaluate the performance of object detection and distance estimation, MAP (Mean Average Precision) and Adjust R square were used and performance was compared with previous research papers. In addition, we compared the original YOLOv2 model FPS (Frame Per Second) for speed measurement with FPS of our model.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.241-243
• /
• 2010

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

• 정보처리학회논문지B
• /
• 제17B권6호
• /
• pp.429-436
• /
• 2010

본 논문에서는 단일 카메라로부터 획득한 영상으로부터 물체의 3차원 윤곽선을 구성하는 방법을 제안한다. MOPS(Multi-Scale Oriented Patches) 알고리즘을 이용하여 물체의 대략적인 윤곽선을 검출하고 윤곽선 위에 분포한 특징점의 공간좌표를 획득한다. 동시에 SIFT(Scale Invariant Feature Transform) 알고리즘을 통하여 물체의 윤곽선 내부에 존재하는 특징점 공간좌표를 획득한다. 이러한 정보를 병합하여 물체의 전체 3차원 윤곽선 정보를 구성한다. 본 논문에서 제안하는 방법은 대략적인 물체의 윤곽선만 구성하기 때문에 빠른 계산이 가능하며 SIFT 특징점을 통해 윤곽선 내부 정보를 보완하기 때문에 물체의 자세한 3차원 정보를 얻을 수 있는 장점이 있다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.216-223
• /
• 2015

The autonomous underwater vehicle (AUV) is being widely researched in order to achieve superior performance when working in hazardous environments. This research focuses on using image processing techniques to estimate the AUV's egomotion and the changes in orientation, based on image frames from different time frames captured from a single high-definition web camera attached to the bottom of the AUV. A visual odometry application is integrated with other sensors. An internal measurement unit (IMU) sensor is used to determine a correct set of answers corresponding to a homography motion equation. A pressure sensor is used to resolve image scale ambiguity. Uncertainty estimation is computed to correct drift that occurs in the system by using a Jacobian method, singular value decomposition, and backward and forward error propagation.