• Journal of Positioning, Navigation, and Timing
• /
• 제10권4호
• /
• pp.297-305
• /
• 2021

Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learning-based monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense ground-truth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.

• 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.

• 제어로봇시스템학회논문지
• /
• 제21권4호
• /
• pp.367-371
• /
• 2015

In this paper, a novel localization method for a monocular camera is proposed by using a feature-based probabilistic map. The localization of a camera is generally estimated from 3D-to-2D correspondences between a 3D map and an image plane through the PnP algorithm. In the computer vision communities, an accurate 3D map is generated by optimization using a large number of image dataset for camera pose estimation. In robotics communities, a camera pose is estimated by probabilistic approaches with lack of feature. Thus, it needs an extra system because the camera system cannot estimate a full state of the robot pose. Therefore, we propose an accurate localization method for a monocular camera using a probabilistic approach in the case of an insufficient image dataset without any extra system. In our system, features from a probabilistic map are projected into an image plane using linear approximation. By minimizing Mahalanobis distance between the projected features from the probabilistic map and extracted features from a query image, the accurate pose of the monocular camera is estimated from an initial pose obtained by the PnP algorithm. The proposed algorithm is demonstrated through simulations in a 3D space.

• 센서학회지
• /
• 제33권2호
• /
• pp.98-104
• /
• 2024

This study proposes a method to overcome the limited detection range of short-baseline stereo cameras (SBSCs). The proposed method includes two steps: (1) predicting an unscaled initial depth using monocular depth estimation (MDE) and (2) adjusting the unscaled initial depth by a scale factor. The scale factor is computed by triangulating the sparse visual keypoints extracted from the left and right images of the SBSC. The proposed method allows the use of any pre-trained MDE model without the need for additional training or data collection, making it efficient even when considering the computational constraints of small platforms. Using an open dataset, the performance of the proposed method was demonstrated by comparing it with other conventional stereo-based depth estimation methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.50-58
• /
• 2013

Estimating a driver's head pose is an important task in driver-assistance systems because it can provide information about where a driver is looking, thereby giving useful cues about the status of the driver (i.e., paying proper attention, fatigued, etc.). This study proposes a system for estimating the head pose using monocular images, which includes a novel use of backprojection. The system can use a single image to estimate a driver's head pose at a particular time stamp, or an image sequence to support the analysis of a driver's status. Using our proposed system, we compared two previous pose estimation approaches. We introduced an approach for providing ground-truth reference data using a mannequin model. Our experimental results demonstrate that the proposed system provides relatively accurate estimations of the yaw, tilt, and roll angle. The results also show that one of the pose estimation approaches (perspective-n-point, PnP) provided a consistently better estimate compared to the other (pose from orthography and scaling with iterations, POSIT) using our proposed system.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1659-1668
• /
• 2016

Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image. The key idea of our approach is to take advantages both of parametric learning and non-parametric sampling method. Using a parametric convolutional network, our approach learns the relation of various monocular cues, which make a coarse global prediction. We also leverage the local prediction to refine the global prediction. It is practically estimated in a non-parametric framework. The integration of local and global predictions is accomplished by concatenating the feature maps of the global prediction with those from local ones. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• 한국항행학회논문지
• /
• 제27권2호
• /
• pp.182-189
• /
• 2023

깊이 추정은 차량, 로봇, 드론의 자율주행을 위한 3차원 지도 생성의 핵심 기술이다. 기존의 센서 기반 깊이 추정 방식은 정확도는 높지만 가격이 비싸고 해상도가 낮다. 반면 카메라 기반 깊이 추정 방식은 해상도가 높고 가격이 저렴하지만 정확도가 낮다. 본 연구에서는 무인항공기 카메라의 깊이 추정 성능 향상을 위해 Self-Attention 기반의 비지도 단안 카메라 영상 깊이 추정을 제안한다. 네트워크에 Self-Attention 연산을 적용하여 전역 특징 추출 성능을 향상시킨다. 또한 카메라 파라미터를 학습하는 네트워크를 추가하여 카메라 칼리브레이션이 안되어있는 이미지 데이터에서도 사용 가능하게 한다. 공간 데이터 생성을 위해 추정된 깊이와 카메라 포즈는 카메라 파라미터를 이용하여 포인트 클라우드로 변환되고, 포인트 클라우드는 Octree 구조의 점유 그리드를 사용하여 3D 맵으로 매핑된다. 제안된 네트워크는 합성 이미지와 Mid-Air 데이터 세트의 깊이 시퀀스를 사용하여 평가된다. 제안하는 네트워크는 이전 연구에 비해 7.69% 더 낮은 오류 값을 보여주었다.

• 한국정보컨버전스학회논문지
• /
• 제6권2호
• /
• pp.51-55
• /
• 2013

가까운 물체를 보기 위해서 조절이 일어난다. 이 조절은 개인마다 다른 특징이 있다. 이론적 조절력과 실제 조절력도 차이가 생긴다. 이를 조절지체라 한다. 조절지체에 직접적인 영향을 미치는 것은 초점심도이다. 초점심도는 동공크기와 굴절력에 영향을 받는다. 동공크기가 작을수록, 굴절력이 높을수록 초점심도가 깊어지게 된다. 초점심도가 깊어짐에 따라 조절지체가 많이 발생하게 된다. 본 논문에서는 굴절력과 조절지체의 관계에 대한 연구를 하였다. 조절지체를 측정하기 위해서 단안평가법을 이용하였다. 단연평가법으로 측정한 결과 조절지체는 굴절력이 증가함에 따라 같이 증가하는 경향을 나타내었다. 전체 조절 지체량은 0.51D로 측정되었다. 남성은 0.52D, 여성은 0.49D로 측정되었다. 성별에 따른 조절지체량도 굴절력이 증가함에 따라 같이 증가하는 경향을 보였다.

• Journal of Positioning, Navigation, and Timing
• /
• 제3권1호
• /
• pp.1-10
• /
• 2014

Recently, monitoring of two-body ground vehicles carrying extremely hazardous materials has been considered as one of the most important national issues. This issue induces large cost in terms of national economy and social benefit. To monitor and counteract accidents promptly, an efficient methodology is required. For accident monitoring, GPS can be utilized in most cases. However, it is widely known that GPS cannot provide sufficient continuity in urban cannons and tunnels. To complement the weakness of GPS, this paper proposes an accident monitoring method based on a monocular vision sensor. The proposed method estimates angular acceleration from a sequence of image frames captured by a monocular vision sensor. The possibility of using angular acceleration is investigated to determine the occurrence of accidents such as jackknifing and rollover. By an experiment based on actual measurements, the feasibility of the proposed method is evaluated.