Refinement of Depth Estimation Method via Energy Minimization

t has been proposed in this paper an idea of refining depth map obtained according to local stereo matching. Energy was calculated based on the entire image, meanwhile, energy minimization concept was adopted, and the area obtained according to color segmentation algorithm was adopted too. The lower the energy of an image, the better depth quality will be generated. The color feature and depth value among different regions and their neighboring regions are used to define the relation between the smooth and occluded regions in the energy function. Then the region energy was calculated repeatedly until the change was insignificant or the number of iterations was reached. The corrected left and right view was used first to perform local stereo matching to get initial depth estimation. The color information of the left view was used to perform color segmentation, and then the segmented region and initial depth estimation were used to calculate the parameter of disparity plane for each region. This process was performed iteratively on the disparity plane, where a more reasonable depth map can be obtained while the energy cost is minimized. From the experimental result, it is proved that the depth map after refinement showed better object shape and smooth region density as compared to that of the initial depth map.

Download Full-text

Weakly supervised monocular depth estimation method based on stereo matching labels

Journal of Electronic Imaging ◽

10.1117/1.jei.29.5.053013 ◽

2020 ◽

Vol 29 (05) ◽

Author(s):

Zhimin Zhang ◽

Jianzhong Qiao ◽

Shukuan Lin ◽

Han Liu

Keyword(s):

Stereo Matching ◽

Estimation Method ◽

Depth Estimation ◽

Monocular Depth ◽

Weakly Supervised

Download Full-text

Merging Static and Dynamic Depth Cues with Optical-Flow Recovery for Creating Stereo Videos

Mathematical Problems in Engineering ◽

10.1155/2013/725301 ◽

2013 ◽

Vol 2013 ◽

pp. 1-12

Author(s):

Fang-Hsuan Cheng ◽

Tze-Yun Sung

Keyword(s):

Optical Flow ◽

Estimation Method ◽

Depth Map ◽

Depth Estimation ◽

Depth Information ◽

Additional Information ◽

Optical Flow Method ◽

Block Motion ◽

Monocular Image ◽

Monocular Image Sequence

A method for estimating the depth information of a general monocular image sequence and then creating a 3D stereo video is proposed. Distinguishing between foreground and background is possible without additional information, and then foreground pixels are moved to create the binocular image. The proposed depth estimation method is based on coarse-to-fine strategy. By applying the CID method in the spatial domain, the sharpness and the contrast of an image can be improved by the distance of the region based on its color. Then a coarse depth map of the image can be generated. An optical-flow method based on temporal information is then used to search and compare the block motion status between previous and current frames, and then the distance of the block can be estimated according to the amount of block motion. Finally, the static and motion depth information is integrated to create the fine depth map. By shifting foreground pixels based on the depth information, a binocular image pair can be created. A sense of 3D stereo can be obtained without glasses by an autostereoscopic 3D display.

Download Full-text

A Dense Disparity Estimation Method using Color Segmentation and Energy Minimization

2006 International Conference on Image Processing ◽

10.1109/icip.2006.312731 ◽

2006 ◽

Cited By ~ 1

Author(s):

Han Shin Lim ◽

Hyunwook Park

Keyword(s):

Energy Minimization ◽

Estimation Method ◽

Disparity Estimation ◽

Color Segmentation

Download Full-text

Depth Estimation for Light-Field Images Using Stereo Matching and Convolutional Neural Networks

Sensors ◽

10.3390/s20216188 ◽

2020 ◽

Vol 20 (21) ◽

pp. 6188

Author(s):

Ségolène Rogge ◽

Ionut Schiopu ◽

Adrian Munteanu

Keyword(s):

Machine Learning ◽

Light Field ◽

Stereo Matching ◽

Estimation Method ◽

Similarity Index ◽

Depth Estimation ◽

Residual Error ◽

Disparity Estimation ◽

Machine Learning Techniques ◽

Disparity Map

The paper presents a novel depth-estimation method for light-field (LF) images based on innovative multi-stereo matching and machine-learning techniques. In the first stage, a novel block-based stereo matching algorithm is employed to compute the initial estimation. The proposed algorithm is specifically designed to operate on any pair of sub-aperture images (SAIs) in the LF image and to compute the pair’s corresponding disparity map. For the central SAI, a disparity fusion technique is proposed to compute the initial disparity map based on all available pairwise disparities. In the second stage, a novel pixel-wise deep-learning (DL)-based method for residual error prediction is employed to further refine the disparity estimation. A novel neural network architecture is proposed based on a new structure of layers. The proposed DL-based method is employed to predict the residual error of the initial estimation and to refine the final disparity map. The experimental results demonstrate the superiority of the proposed framework and reveal that the proposed method achieves an average improvement of 15.65% in root mean squared error (RMSE), 43.62% in mean absolute error (MAE), and 5.03% in structural similarity index (SSIM) over machine-learning-based state-of-the-art methods.

Download Full-text

Improving the Accuracy of Depth Estimation in Binocular Vision for Robotic Applications

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.284-287.1862 ◽

2013 ◽

Vol 284-287 ◽

pp. 1862-1866 ◽

Cited By ~ 7

Author(s):

Kuan Yu Chen ◽

Cheng Chin Chien ◽

Chien Te Tseng

Keyword(s):

Binocular Vision ◽

Stereo Vision ◽

Computational Models ◽

Stereo Matching ◽

Focal Length ◽

Three Dimensional ◽

Estimation Method ◽

Depth Estimation ◽

Estimation Algorithm ◽

Dimensional Structure

Binocular vision or stereo vision for extraction of three-dimensional information from stereo images has been widely used in many applications like robot navigation, recovering the three-dimensional structure of a scene, and optical inspection systems. More recently, the majority of research in binocular vision has focused on the establishment of stereo matching. However, to date, there has been relatively little research conducted on the effect of computational models of binocular vision with variable focal length of lens. In this paper, a modified computational model of binocular vision is presented to develop a new depth estimation algorithm with no effect of changes in focal length. This method provides an obvious advantage in accuracy of depth estimation by reducing the effect of changing the lens focal length. The experimental results show that the proposed depth estimation method in binocular vision provides better accuracy than conventional method. Finally, we apply the new depth estimation method to a stereo-vision-based automatic docking system for a mobile robot to verify its accuracy.

Download Full-text

A depth estimation method for edge precision improvement of depth map

2010 International Conference on Computer and Communication Technologies in Agriculture Engineering ◽

10.1109/cctae.2010.5544184 ◽

2010 ◽

Author(s):

Xiaoxian Liu ◽

Yilin Chang ◽

Zhibin Li ◽

Hui Yuan

Keyword(s):

Estimation Method ◽

Depth Map ◽

Depth Estimation

Download Full-text

The Design and Implementation of Postprocessing for Depth Map on Real-Time Extraction System

The Scientific World JOURNAL ◽

10.1155/2014/363287 ◽

2014 ◽

Vol 2014 ◽

pp. 1-10 ◽

Cited By ~ 2

Author(s):

Zhiwei Tang ◽

Bin Li ◽

Huosheng Li ◽

Zheng Xu

Keyword(s):

Real Time ◽

Stereo Matching ◽

Depth Map ◽

Depth Estimation ◽

Consistency Check ◽

Key Technology ◽

Design And Implementation ◽

Depth Maps ◽

Matching Cost

Depth estimation becomes the key technology to resolve the communications of the stereo vision. We can get the real-time depth map based on hardware, which cannot implement complicated algorithm as software, because there are some restrictions in the hardware structure. Eventually, some wrong stereo matching will inevitably exist in the process of depth estimation by hardware, such as FPGA. In order to solve the problem a postprocessing function is designed in this paper. After matching cost unique test, the both left-right and right-left consistency check solutions are implemented, respectively; then, the cavities in depth maps can be filled by right depth values on the basis of right-left consistency check solution. The results in the experiments have shown that the depth map extraction and postprocessing function can be implemented in real time in the same system; what is more, the quality of the depth maps is satisfactory.

Download Full-text

Estimation of resistance force at steady-state sinkage for cylindrical wheel-typed lunar/planetary exploration rovers with function of push–pull locomotion

ROBOMECH Journal ◽

10.1186/s40648-020-00183-0 ◽

2020 ◽

Vol 7 (1) ◽

Author(s):

Daisuke Fujiwara ◽

Naoki Tsujikawa ◽

Tetsuya Oshima ◽

Kojiro Iizuka

Keyword(s):

Steady State ◽

Estimation Method ◽

Planetary Exploration ◽

Experimental Result ◽

Resistance Force ◽

Estimation Model ◽

Loose Soil ◽

Key Factor ◽

The Relationship ◽

Resistance Forces

Abstract Planetary exploration rovers have required a high traveling performance to overcome obstacles such as loose soil and rocks. Push-pull locomotion rovers is a unique scheme, like an inchworm, and it has high traveling performance on loose soil. Push-pull locomotion uses the resistance force by keeping a locked-wheel related to the ground, whereas the conventional rotational traveling uses the shear force from loose soil. The locked-wheel is a key factor for traveling in the push-pull scheme. Understanding the sinking behavior and its resistance force is useful information for estimating the rover’s performance. Previous studies have reported the soil motion under the locked-wheel, the traction, and the traveling behavior of the rover. These studies were, however, limited to the investigation of the resistance force and amount of sinkage for the particular condition depending on the rover. Additionally, the locked-wheel sinks into the soil until it obtains the required force for supporting the other wheels’ motion. How the amount of sinkage and resistance forces are generated at different wheel sizes and mass of an individual wheel has remained unclear, and its estimation method hasn’t existed. This study, therefore, addresses the relationship between the sinkage and its resistance force, and we analyze and consider this relationship via the towing experiment and theoretical consideration. The results revealed that the sinkage reached a steady-state value and depended on the contact area and mass of each wheel, and the maximum resistance force also depends on this sinkage. Additionally, the estimation model did not capture the same trend as the experimental results when the wheel width changed, whereas, the model captured a relatively the same trend as the experimental result when the wheel mass and diameter changed.

Download Full-text