• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.182-189
• /
• 2023

Depth estimation is a key technology in 3D map generation for autonomous driving of vehicles, robots, and drones. The existing sensor-based method has high accuracy but is expensive and has low resolution, while the camera-based method is more affordable with higher resolution. In this study, we propose self-attention-based unsupervised monocular depth estimation for UAV camera system. Self-Attention operation is applied to the network to improve the global feature extraction performance. In addition, we reduce the weight size of the self-attention operation for a low computational amount. The estimated depth and camera pose are transformed into point cloud. The point cloud is mapped into 3D map using the occupancy grid of Octree structure. The proposed network is evaluated using synthesized images and depth sequences from the Mid-Air dataset. Our network demonstrates a 7.69% reduction in error compared to prior studies.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.466-468
• /
• 2022

3D reconstruction is important issue in many applications such as Augmented Reality (AR), eXtended Reality (XR), and Metaverse. For 3D reconstruction, depth map can be acquired by stereo camera and time-of-flight (ToF) sensor. We used both sensors complementarily to improve the accuracy of 3D information of the data. First, we applied general multi-camera calibration technique which uses both color and depth information. Next, the depth map of the two sensors are fused by 3D registration and reprojection approach. The fused data is compared with the ground truth data which is reconstructed using RTC360 sensor. We used Geomagic Wrap to analysis the average RMSE of the two data. The proposed procedure was implemented and tested with real-world data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.351-357
• /
• 2013

Two cameras which function like human eyes, are needed to make 3D stereoscopic image. That is, stereoscopic image is made via 3 dimensional image processing for combining two images from left and right camera. In this paper two high resolution zoom cameras are used to make HD resolution stereoscopic camera. And the algorithm which convert to stereoscopic image from HD resolution zoom camera image, is implemented using FPGA for real-time operation. The algorithm which measure the depth of object between left and right image is proposed.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.77-80
• /
• 2022

Automatic Vision Inspection (AVI) systems automatically detect defect features and measure their sizes via camera vision. It has been populated because of the accuracy and consistency in terms of QC (Quality Control) of inspection processes. Also, it is important to predict the performance of an AVI to meet customer's specification in advance. AVI are usually suffered from false negative and positives. It can be overcome by providing extra information such as 3D depth information. Stereo vision processing has been popular for depth extraction of the 3D images from 2D images. However, stereo vision methods usually take long time to process. In this paper, retro optical system using reflectors is proposed and experimented to overcome the problem. The optical system extracts the depth without special SW processes. The vision sensor and optical components such as illumination and depth detecting module are integrated as a unit. The depth information can be extracted on real-time basis and utilized and can improve the performance of an AVI system.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.6
• /
• pp.1431-1438
• /
• 1995

In this paper, we present a multiple-view stereo matching method in case of moving in the direction of optical axis with stereo camera. Also we analyze the obtainable depth precision to show that multiple-view stereo increases the virtual baseline with single-view stereo. This method decides candidate points for correspondence in each image pair and then search for the correct combinations of correspondences among them using the geometrical consistency they must satisfy. Adantages of this method are capability in increasing the accuracy in matching by using the multiple stereo images and less computation due to local processing. This method computes 3-D depth by averaging the depth obtained in each multiple-view stereo. We show that the resulting depth has more precision than depth obtainable by each independent stereo when the position of image feature is uncertain due to image noise. This paper first defines a multipleview stereo agorithm in case of moving in the direction of optical axis with stereo camera and analyze the obtainable precision of computed depth. Then we represent the effect of removing the incorrect matching candidate and precision enhancement with experimental result.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.44-52
• /
• 2019

We implement an educational indoor autonomous mobile robot system that integrates LiDAR sensing information with RGB-D camera image information and exploits the integrated information. This system uses the existing sensing method employing a LiDAR with a small number of scan channels to acquire LiDAR sensing information. To remedy the weakness of the existing LiDAR sensing method, we propose the 3D structure recognition technique using depth images from a RGB-D camera and the deep learning based object recognition algorithm and apply the proposed technique to the system.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.439-448
• /
• 2020

In this paper, we propose a modified optimization algorithm for point cloud matching of multi-view RGB-D cameras. In general, in the computer vision field, it is very important to accurately estimate the position of the camera. The 3D model generation methods proposed in the previous research require a large number of cameras or expensive 3D cameras. Also, the methods of obtaining the external parameters of the camera through the 2D image have a large error. In this paper, we propose a matching technique for generating a 3D point cloud and mesh model that can provide omnidirectional free viewpoint using 8 low-cost RGB-D cameras. We propose a method that uses a depth map-based function optimization method with RGB images and obtains coordinate transformation parameters that can generate a high-quality 3D model without obtaining initial parameters.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.395-399
• /
• 2006

A method to recognize unpaved road region using a 3D depth measurement system is proposed for mobile robots. For autonomous maneuvering of mobile robots, recognition of obstacles or recognition of road region is the essential task. In this paper, the 3D depth measurement system which is composed of a rotating mirror, a line laser and mono-camera is employed to detect depth, where the laser light is reflected by the mirror and projected to the scene objects whose locations are to be determined. The obtained depth information is converted into an image. Such depth images of the road region represent even and plane while that of off-road region is irregular or textured. Therefore, the problem falls into a texture identification problem. Road region is detected employing a simple spatial differentiation technique to detect the plain textured area. Identification results of the diverse situation of unpaved trail are included in this paper.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.580-587
• /
• 2019

In this paper, a plane detection method using depth information is proposed. 3-D characteristics of a pixel are defined as a direction and length of a normal vector whose is calculated from a plane consisting of a local region centered on the pixel. Image coordinates of each pixel are transformed to 3-D coordinates in order to obtain the local planes. Regions of each plane are detected by calculating similarity of the 3-D characteristics. The similarity of the characteristics consists of direction and distance similarities of normal vectors. If the similarity of the characteristics between two adjacent pixels is enough high, the two pixels are regarded as consisting of same plane. Simulation results show that the proposed method using the depth picture is more accurate for detecting plane areas than the conventional method.