Video mosaicing for real-time field of view enhancement

Author(s):  
P. Wongsawatsuriyha ◽  
N. Khemthongcharoen ◽  
W. Piyawattanametha
Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2106
Author(s):  
Ahmed Afifi ◽  
Chisato Takada ◽  
Yuichiro Yoshimura ◽  
Toshiya Nakaguchi

Minimally invasive surgery is widely used because of its tremendous benefits to the patient. However, there are some challenges that surgeons face in this type of surgery, the most important of which is the narrow field of view. Therefore, we propose an approach to expand the field of view for minimally invasive surgery to enhance surgeons’ experience. It combines multiple views in real-time to produce a dynamic expanded view. The proposed approach extends the monocular Oriented features from an accelerated segment test and Rotated Binary robust independent elementary features—Simultaneous Localization And Mapping (ORB-SLAM) to work with a multi-camera setup. The ORB-SLAM’s three parallel threads, namely tracking, mapping and loop closing, are performed for each camera and new threads are added to calculate the relative cameras’ pose and to construct the expanded view. A new algorithm for estimating the optimal inter-camera correspondence matrix from a set of corresponding 3D map points is presented. This optimal transformation is then used to produce the final view. The proposed approach was evaluated using both human models and in vivo data. The evaluation results of the proposed correspondence matrix estimation algorithm prove its ability to reduce the error and to produce an accurate transformation. The results also show that when other approaches fail, the proposed approach can produce an expanded view. In this work, a real-time dynamic field-of-view expansion approach that can work in all situations regardless of images’ overlap is proposed. It outperforms the previous approaches and can also work at 21 fps.


Author(s):  
Pierluigi Carcagnì ◽  
Dario Cazzato ◽  
Marco Del Coco ◽  
Pier Luigi Mazzeo ◽  
Marco Leo ◽  
...  

AbstractIn thiswork, a real-time system able to automatically recognize soft-biometric traits is introduced and used to improve the capability of a humanoid robot to interact with humans. In particular the proposed system is able to estimate gender and age of humans in images acquired from the embedded camera of the robot. This knowledge allows the robot to properly react with customized behaviors related to the gender/age of the interacting individuals. The system is able to handle multiple persons in the same acquired image, recognizing the age and gender of each person in the robot’s field of view. These features make the robot particularly suitable to be used in socially assistive applications.


1989 ◽  
Vol 8 ◽  
pp. 565-566
Author(s):  
Fritz Merkle

Long baseline interferometry requires the full phasing of a telescope array. Especially for future arrays with large unit telescopes active control systems are mandatory. Adaptive optics can be applied for real-time phase compensation of the individual pupils due to atmospheric distortions. Additional to phasing of the individual pupils of independently mounted telescopes, the whole array has to be phased, including pupil position corrections due to pupil foreshortening and shift effects in order to reach a reasonable phased field-of-view.


2011 ◽  
Vol 403-408 ◽  
pp. 1451-1454 ◽  
Author(s):  
Wei Lu ◽  
Ting Ting Wang ◽  
Jing Hui Chu

The paper proposes a real-time monocular vision-based algorithm that can be applied to robot tracking. Unlike the models used in other papers, the model used in this paper is suitable for the condition that the camera is looking up. There is a common deficiency existing in previous models that the target point is constrained to some areas of the camera field. To overcome the shortcomings, the camera field of view is divided into three regions which also reduces the computational complexity. The intrinsic parameters of camera can be obtained by calibration. Pitch angle rectification, together with camera calibration, improves the ranging accuracy.


In this paper, a pivotal technique was proposed that reduces the haze and combines the haze free image to increase the Field of View (FoV) in real-time with a rapid prototype hardware device. The Initial focus is to reduce the haze in an image with Dark Channel Prior Technique and the FSD method is utilized to mosaic the haze free images. Low contrast may occur due to the scattering light, air particles or fog in nature which results in a haze image that needs to be reduced and enhance the image for better vicinity. Haze reduction approach depends on entropy and information fidelity. Our Haze free algorithm executes multiple phases such as dark channel prior computation, estimation and refinement of transmission map and restoration of RGB values. The second technique is the mosaic process that improves the field of view of a scene and the phases that execute are corner detection, extraction, geometric computation and blending. Our experimental results have shown better when compared to the other algorithms. The whole process is executed in real-time with a standalone device called Intel compute stick.


Sign in / Sign up

Export Citation Format

Share Document