• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.4
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.29-35
• /
• 2010

This paper discusses a method that can enhance the exactness of depth estimation of an image by PCA(Principle Component Analysis) based on feature reduction through learning algorithm. In estimation of the depth of an image, hyphen such as energy of pixels and gradient of them are found, those selves and their relationship are used for depth estimation. In such a case, many features are obtained by various filter operations. If all of the obtained features are equally used without considering their contribution for depth estimation, The efficiency of depth estimation goes down. This paper proposes a method that can enhance the exactness of depth estimation of an image and its processing speed is considered as the contribution factor through PCA. The experiment shows that the proposed method(30% of an feature vector) is more exact(average 0.4%, maximum 2.5%) than using all of an image data in depth estimation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.3
• /
• pp.1058-1070
• /
• 2014

There are two major ways to implement depth estimation, multiple image depth estimation and single image depth estimation, respectively. The former has a high hardware cost because it uses multiple cameras but it has a simple software algorithm. Conversely, the latter has a low hardware cost but the software algorithm is complex. One of the recent trends in this field is to make a system compact, or even portable, and to simplify the optical elements to be attached to the conventional camera. In this paper, we present an implementation of depth estimation with a single image using a graphics processing unit (GPU) in a desktop PC, and achieve real-time application via our evolutional algorithm and parallel processing technique, employing a compute shader. The methods greatly accelerate the compute-intensive implementation of depth estimation with a single view image from 0.003 frames per second (fps) (implemented in MATLAB) to 53 fps, which is almost twice the real-time standard of 30 fps. In the previous literature, to the best of our knowledge, no paper discusses the optimization of depth estimation using a single image, and the frame rate of our final result is better than that of previous studies using multiple images, whose frame rate is about 20fps.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.527-532
• /
• 2013

Depth estimation is an essential factor for robot vision, 3D scene modeling, and motion control. The depth estimation method is based on focusing values calculated in a series of images by a single camera at different distance between lens and object. In this paper, we proposed a relative depth estimation method using focus measure. The proposed method is implemented by focus value calculated for each image obtained at different lens position and then depth is finally estimated by considering relative distance of two patterns. We performed various experiments on the effective focus measures for depth estimation by using various patterns and their usefulness.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.2
• /
• pp.96-105
• /
• 2004

The recovering 3D image from 2D requires the depth information for each picture element. The manual creation of those 3D models is time consuming and expensive. The goal in this paper is to estimate the relative depth information of every region from single view image with camera translation. The paper is based on the fact that the motion of every point within image which taken from camera translation depends on the depth. Motion vector using full-search motion estimation is compensated for camera rotation and zooming. We have developed a framework that estimates the average frame depth by analyzing motion vector and then calculates relative depth of region to average frame depth. Simulation results show that the depth of region belongs to a near or far object is consistent accord with relative depth that man recognizes.

• Current Optics and Photonics
• /
• v.5 no.5
• /
• pp.514-523
• /
• 2021

Methods for absolute depth estimation have received lots of interest, and most algorithms are concerned about how to minimize the difference between an input defocused image and an estimated defocused image. These approaches may increase the complexity of the algorithms to calculate the defocused image from the estimation of the focused image. In this paper, we present a new method to recover depth of scene based on a sharpness-assessment algorithm. The proposed algorithm estimates the depth of scene by calculating the sharpness of deconvolved images with a specific point-spread function (PSF). While most depth estimation studies evaluate depth of the scene only behind a focal plane, the proposed method evaluates a broad depth range both nearer and farther than the focal plane. This is accomplished using an asymmetric aperture, so the PSF at a position nearer than the focal plane is different from that at a position farther than the focal plane. From the image taken with a focal plane of 160 cm, the depth of object over the broad range from 60 to 350 cm is estimated at 10 cm resolution. With an asymmetric aperture, we demonstrate the feasibility of the sharpness-assessment algorithm to recover absolute depth of scene from a single defocused image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.11a
• /
• pp.114-115
• /
• 2013

The blur amount of an image changes proportional to scene depth. Depth from Defocus (DFD) is an approach in which a depth map can be obtained using blur amount calculation. In this paper, a novel DFD method is proposed in which depth is measured using an infocused and a defocused image. Subbaro's algorithm is used as a preliminary depth estimation method and edge blur estimation is provided to overcome drawbacks in edge.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.281-291
• /
• 2019

Depth from defocus estimates the 3D depth by using a phenomenon in which the object in the focal plane of the camera forms a clear image but the object away from the focal plane produces a blurred image. In this paper, algorithms are studied to estimate 3D depth by analyzing the degree of blur of the image taken with a single camera. The optimized object range was obtained by 3D depth estimation derived from depth from defocus using one image of a single camera or two images of different focus of a single camera. For depth estimation using one image, the best performance was achieved using a focal length of 250 mm for both smartphone and DSLR cameras. The depth estimation using two images showed the best 3D depth estimation range when the focal length was set to 150 mm and 250 mm for smartphone camera images and 200 mm and 300 mm for DSLR camera images.