Fast Panoramic Image Generation Method Using Morphological Corner Detection

Lee, Jung-Ho; Lee, Woong-Ho; Cho, Ik-Hwan; Jeong, Dong-Seok

doi:10.1007/11581772_48

Cited by 2 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm makes use of OpenGL ES1.1 libraries. The results obtained are good, but far from the ones shown in [9]. In fact, despite a form of interpolation is applied, the border areas between the cameras are clearly recognizable.…”

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 60%

“…The process of merging graphical objects is a recent digital processing area, and it's still under study. A video stream is composed of a sequence of images, so it may think to be inspired by the algorithms for creating panoramic photos, like the one described in [9]. In this system, creators first locate the common parts of the images that have to be merged together.…”

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 99%

“…What emerges is one picture of fair quality, in which there aren't any sort of discontinuities on the scene. However, an algorithm like the one described in [9] cannot be implemented in real-time, because it would require a very powerful computational unit, which is not low-cost. A product closer to the constraints of the system proposed here is described in [10], in which the authors use four fish-eye cameras to propose to the driver a top-view of the vehicle, with the possibility to vary the viewing angle.…”

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 99%

“…However, current proposed systems are still too expensive to be equipped on medium-and low-end vehicles. For this reason, in academia and industry there is a lot of research to develop advanced but low-cost ADAS solutions, offering technologies for the obstacle's detection, brake assist and some other products to improve vision [1][2][3][4][5][6][7][8][9][10][11]. Among all the dangerous situations that can be encountered while driving, the most frequent is the one determined by the blind spots [1]: the driver is unable to see the zones around the vehicle.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-time and low-cost embedded platform for car's surrounding vision system

Saponara¹,

Franchi²

2016

SPIE Proceedings

View full text Add to dashboard Cite

The design and the implementation of a flexible and low-cost embedded system for real-time car's surrounding vision is presented. The target of the proposed multi-camera vision system is to provide the driver a better view of the objects that surround the vehicle. Fish-eye lenses are used to achieve a larger Field of View (FOV) but, on the other hand, introduce radial distortion of the images projected on the sensors. Using low-cost cameras there could be also some alignment issues. Since these complications are noticeable and dangerous, a real-time algorithm for their correction is presented. Then another real-time algorithm, used for merging 4 camera video streams together in a single view, is described. Real-time image processing is achieved through a hardware-software platform

show abstract

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 60%

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 99%

Section: State Of the Art Of Video Fusion Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time and low-cost embedded platform for car's surrounding vision system

Saponara¹,

Franchi²

2016

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…A video stream is composed of a sequence of images, so it may think to be inspired by the algorithms for creating panoramic photos, like the one described in [57]. In this system, creators first locate the common parts of the images that have to be merged together.…”

Section: Image Camera Fusion For Surrounding Viewmentioning

confidence: 99%

Hardware accelerator IP cores for real time Radar and camera-based ADAS

Saponara

2016

J Real-Time Image Proc

View full text Add to dashboard Cite

The paper presents the design of HDL macrocells, working as hardware accelerators to achieve real time processing of some key functions of Advanced Driver Assistance Systems (ADAS). Particularly, the macrocells process in real time images from Radar and video-camera sensors implementing computing-intensive operations such as: pixel-level filtering, correction of distortions in large field-of-view cameras, multi-camera image fusion for panoramic view of car’s surround, traffic and road signs recognition, detection of obstacles for collision avoidance, and estimation of their distance and speed. The HDL macrocells are fully configurable and are synthesized in low-cost Artix-7 FPGA family, satisfying automotive-grade requirements. They can be integrated as accelerators in embedded hardware–software platforms to build a complete ADAS solution. To this aim, the macrocells have been synthesized also in a Zynq FPSoC. With respect to the state of the art, the proposed macrocells stand for their low-power and real time performanc

show abstract

Fast Panoramic Image Generation Method Using Morphological Corner Detection

Cited by 2 publications

References 11 publications

Real-time and low-cost embedded platform for car's surrounding vision system

Real-time and low-cost embedded platform for car's surrounding vision system

Hardware accelerator IP cores for real time Radar and camera-based ADAS

Contact Info

Product

Resources

About