The Tyzx DeepSea G2 Vision System, ATaskable, Embedded Stereo Camera

Woodfill, John; Gordon, G.; Jurasek, D.; Brown, Ted; Buck, Ron

doi:10.1109/cvprw.2006.202

Cited by 31 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the top-ranking algorithms 1 prefer to focus on cost optimization due to the quality of results. In contrast, commercial implementations of stereo vision ( [3], [4]) utilize aggregationbased approaches due to their requirement for real-time and near-real-time behaviour.…”

Section: Introductionmentioning

confidence: 91%

Connected-component stereo aggregation

Oon-Ee

Ganapathy

Ponnambalam

2010

2010 IEEE Asia Pacific Conference on Circuits and Systems

View full text Add to dashboard Cite

Stereo vision algorithms can be divided into several general stages. Detailed analysis on each specific stage allows focused improvement of the entire algorithm. Existing stereo vision algorithms typically prioritize pixel and sub-pixel accuracy, focusing on the optimization stage, while commercial algorithms which prioritize real-time operation typically focus on the cost calculation stage. This paper presents a novel approach to cost aggregation, a module within the cost calculation stage, based on connected-component analysis. The conventional connectedcomponent analysis algorithm is extended for use in the stereo vision matching cost aggregation problem, resulting in an algorithm which is comparable in efficiency to the best current aggregation algorithms while performing well at object boundaries, typically the most difficult problem for aggregation-based approaches.

show abstract

Section: Introductionmentioning

confidence: 91%

Connected-component stereo aggregation

Oon-Ee

Ganapathy

Ponnambalam

2010

2010 IEEE Asia Pacific Conference on Circuits and Systems

View full text Add to dashboard Cite

show abstract

“…Although not all this processing is used by the stereo module, it produces 32 disparities on 320 × 240 pixel images with programmable matching regions ranging from 7×7 pixels to 13×7 pixels. Woodfill et al [26] implemented a DeapSea II stereo processor, an ASIC, designed for the specific computations in the census matching stereo correlation. They claimed the maximum performance of 200 fps for 16-bit disparity results with 5-bit sub-pixel accuracy on 512 × 480 pixel images and a disparity range up to 52 pixels.…”

Section: Binocular Stereo Vision Systemmentioning

confidence: 99%

An FPGA-based RGBD imager

Chen

Jia

2011

Machine Vision and Applications

View full text Add to dashboard Cite

This paper describes a trinocular stereo vision system using a single chip of FPGA to generate the composite color (RGB) and disparity data stream at video rate, called the RGBD imager. The system uses the triangular configuration of three cameras for synchronous image capture and the trinocular adaptive cooperative algorithm based on local aggregation for smooth and accurate dense disparity mapping. We design a fine-grain parallel and pipelining architecture in FPGA for implementation to achieve a high computational and real-time throughput. A binary floatingpoint format is customized for data representation to satisfy the wide data range and high computation precision demands in the disparity calculation. Memory management and data bit-width control are applied in the system to reduce the hardware resource consumption and accelerate the processing speed. The system is able to produce dense disparity maps with 320 × 240 pixels in a disparity search range of 64 pixels at the rate of 30 frames per second.

show abstract

“…Unfortunately, SAD is not robust to different illumination conditions between cameras, so image pairs are usually fed to high pass filters before matching [10] which increases computational complexity. Census transform is immune to different illumination conditions but it needs special hardware [11] to reach realtime performance which raises the total cost of the system. NCC is also robust to different illumination conditions.…”

Section: Introductionmentioning

confidence: 99%

Efficient normalized cross correlation calculation method for stereo vision based robot navigation

Shen

2011

Front. Comput. Sci. China

View full text Add to dashboard Cite

Stereo vision systems are widely used for autonomous robot navigation. Most of them apply local window based methods for real-time purposes. Normalized cross correlation (NCC) is notorious for its high computational cost, though it is robust to different illumination conditions between two cameras. It is rarely used in real-time stereo vision systems. This paper proposes an efficient normalized cross correlation calculation method based on the integral image technique. Its computational complexity has no relationship to the size of the matching window. Experimental results show that our algorithm can generate the same results as traditional normalized cross correlation with a much lower computational cost. Our algorithm is suitable for planet rover navigation.

show abstract

The Tyzx DeepSea G2 Vision System, ATaskable, Embedded Stereo Camera

Cited by 31 publications

References 5 publications

Connected-component stereo aggregation

Connected-component stereo aggregation

An FPGA-based RGBD imager

Efficient normalized cross correlation calculation method for stereo vision based robot navigation

Contact Info

Product

Resources

About