Spatio-temporal bird's-eye view images using multiple fish-eye cameras

Sato, Takaaki; Moro, Alessandro; Sugahara, Atsushi; Tasaki, Tomohiro; Yamashita, Atsushi; Asama, Hajime

doi:10.1109/sii.2013.6776674

Cited by 33 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relative poses of the floor and the fisheye cameras are estimated in the similar manner as done in [5] except that instead of estimating the homography matrix of each image, we estimate the actual camera poses. In the previous method, square boards as calibration targets are placed on the floor, so that two adjacent cameras are able to capture the same target as shown in Fig.…”

Section: Estimate the Relative Posesmentioning

confidence: 99%

“…Visualizing the surrounding environment of a robot is important for an efficient robot teleoperation. Therefore, visualization methods have been comprehensively studied over a long period [1][2][3][4][5][6][7]. One of the difficulties in robot teleoperation is the lack of depth perception.…”

Section: Introductionmentioning

confidence: 99%

“…Some studies have been conducted to provide thirdperson view images without the overhead cameras to deal with some spatial constraints, e.g., environments with a low ceiling. Sato et al demonstrated a system that generates bird's-eye view images from multiple first-person view images captured by the cameras on the robot [5]. They warped the first-person view images by homography transformation and combined them to generate bird's-eye view images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Free viewpoint image generation system using fisheye cameras and a laser rangefinder for indoor robot teleoperation

et al. 2020

Self Cite

View full text Add to dashboard Cite

In robot teleoperation, a lack of depth information often results in collisions between the robots and obstacles in its path or surroundings. To address this issue, free viewpoint images can greatly benefit the operators in terms of collision avoidance as the operators are able to view the robot's surrounding from the images at arbitrary points, giving them a better depth information. In this paper, a novel free viewpoint image generation system is proposed. One approach to generate free viewpoint images is to use multiple cameras and Light Detection and Ranging (LiDAR). Instead of using the expensive LiDAR, this study utilizes a cost-effective laser rangefinder (LRF) and a characteristic of man-made environments. In other words, we install multiple fisheye cameras and an LRF on a robot. Free viewpoint images are generated under the assumption that walls are perpendicular to the floor. Furthermore, an easy calibration for estimating the poses of the multiple fisheye cameras, the LRF, and the robot model is proposed. Experimental results show that the proposed method can generate free viewpoint images using cameras and an LRF. Finally, the proposed method is primarily implemented using OpenGL Shading Language to utilize a graphics processing unit computation to achieve a real-time processing of the multiple high-resolution images. Supplementary videos and our source code are available at our project page (https ://matsu ren.githu b.io/fvp).

show abstract

Section: Estimate the Relative Posesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Free viewpoint image generation system using fisheye cameras and a laser rangefinder for indoor robot teleoperation

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the image resolution per viewing angle of these cameras is low. Another special image is a bird's-eye view image [5,6]. An image looking down the robots is generated by combining multiple images.…”

Section: Related Workmentioning

confidence: 99%

A Method of Providing a Panoramic Image Using Single Image Transmission System

Hamamachi¹,

Kurisu²

2018

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

This paper describes a method of providing a panoramic image using single image transmission system. In recent years, demands for small robots performing inspection work by remote control are expanded. On the remote control of robots, to provide information of environment around the robots is important for operators. Multiple images are usually transmitted to the operators' sides. In some cases, a large or special image generated from multiple images by image processing units is transmitted to the operators' sides. In order to transmit multiple images, multiple image transmission systems are required. On the contrary, generating special images also require a dedicated image processing unit. However, small robots cannot mount such devices due to size limitation. Therefore, we develop a method of providing a panoramic image using single image transmission system. We assume that robots are too small to mount a dedicated image processing unit or multiple image transmission systems. This system is assumed to target cameras with analog outputs. An image which is different from a previously transmitted image is transmitted every transmission. Before the transmission, a special code is added into each frame to distinguish which camera acquires the frame. We develop a tiny processing board to mount the system on small robots. First, we explain a method of spherical projections to generate a panoramic image. Multiple images are transmitted with single image transmission system after adding the code into the images. Availability of our proposed system is shown by an experiment that providing a panoramic image using two cameras.

show abstract

“…As other conventional methods, spatio-temporal bird's-eye view images are proposed [7] using multiple fish-eye cameras. By using four fish-eye cameras mounted on the front, back, right, and left side, bird's-eye images are generated.…”

Section: Related Workmentioning

confidence: 99%

View Point Decision Algorithm for an Autonomous Robot to Provide Support Images in the Operability of a Teleoperated Robot

Maeyama

Okuno

Watanabe

2016

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

It is conceivable to use a teleoperated robot as a method for exploring a disaster environment quickly while avoiding secondary disaster. According to conventional researches, the image captured behind from the teleoperated robot is useful as information provided to an operator for operating a teleoperated robot. In this research, a teleoperated method to provide the image from behind is proposed by using an autonomous robot. This method allows one image to include both the teleoperated robot itself and the environment around the teleoperated robot. Here, it is important to develop an algorithm that can navigate the autonomous robot to the position where the camera image can be obtained so that the operability is enhanced for the teleoperated robot at the front. This paper describes a method for determining the movement position for the autonomous robot in consideration of each robot's position and obstacles around the robot. A method for changing three modes (Follow/Back/Wait) is also described according to the situation. Finally, the movement position of the autonomous robot and the captured images actually provided by each robot are shown through the experimental results using real mobile robots to verify the usefulness of the proposed method.

show abstract

Spatio-temporal bird's-eye view images using multiple fish-eye cameras

Cited by 33 publications

References 9 publications

Free viewpoint image generation system using fisheye cameras and a laser rangefinder for indoor robot teleoperation

Free viewpoint image generation system using fisheye cameras and a laser rangefinder for indoor robot teleoperation

A Method of Providing a Panoramic Image Using Single Image Transmission System

View Point Decision Algorithm for an Autonomous Robot to Provide Support Images in the Operability of a Teleoperated Robot

Contact Info

Product

Resources

About