Motion stereo for navigation of autonomous vehicles in man-made environments

Tsukiyama, Toshifumi; Huang, Thomas S.

doi:10.1016/0031-3203(87)90021-5

Cited by 19 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, these trigonometric operators are independent of the given order of lines, whereas lines connected to a vertex cannot be ordered and, hence, distinguished in this manner. seg(lineJ') = (seg(linel) + 4) mod8 (1) for linel and linel', its extension from the current vertex.…”

Section: Lower Level-operatorsmentioning

confidence: 99%

“…The current vertex is assigned to the T-group if there exist lines LineX and Line Y connected to the current vertex which constitute the extension of each other, i.e., form a straight line. Relations (1) and (3) are employed for this test. Otherwise, the current vertex is assigned to the Arrow-and Forkgroup.…”

Section: Higher Level-the Decision Treementioning

confidence: 99%

“…The AVSneeds to capture, prepare, analyze, and understand the current 2-D image captured from the 3-D scene in order to guide the robot in an intelligent, nonrandom manner through an area cluttered with objects from the well-known blocks-world domain (i.e., rectangular-faced objects found in a well-defined and constrained office, laboratory or factory environment as in Ref. 1) and towards a known, predetermined target. The AVS must extract salient characteristics concerning the 3-D structure of the scene as well as accurate relative depth information concerning its surfaces and edges in order to enable successful robot navigation, stationary obstacle avoidance, and target finding.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using geometrical information for accurate scene understanding in an artificial vision system

Tambouratzis¹

1996

Int J of Intelligent Sys

View full text Add to dashboard Cite

Section: Lower Level-operatorsmentioning

confidence: 99%

Section: Higher Level-the Decision Treementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using geometrical information for accurate scene understanding in an artificial vision system

Tambouratzis¹

1996

Int J of Intelligent Sys

View full text Add to dashboard Cite

“…Tsukiyama and Huang (1987) reported a scene interpretation approach for navigation of autonomous vehicles. They extracted the edge lines from images based on brightness variation of pixels and these edge lines were classified into three categories: oblique, horizontal and vertical.…”

Section: Introductionmentioning

confidence: 99%

Camera calibration using a genetic algorithm

Hui¹,

Pratihar²

2008

Engineering Optimization

View full text Add to dashboard Cite

An autonomous robot will have to detect moving obstacles online before it can plan its collision-free path, while navigating in a dynamic environment. The robot collects information about the environment with the help of a camera and determines the inputs for its motion planner through image analysis. The present article deals with issues related to camera calibration and online image processing. The problem of camera calibration is treated as an optimization problem and solved using a genetic algorithm so as to achieve minimum distorted image plane error. The calibrated vision system is then utilized for the detection and identification of the objects by analysing the images collected at regular intervals. For image processing, five different operations, such as median filtering, thresholding, perimeter estimation, labelling and size filtering, have been carried out. To show the effectiveness of the developed camera-based vision system, inputs of the motion planner of a navigating robot are calculated for two different cases. It is observed that online detection of the shapes and configurations of the obstacles is possible by using the vision system developed.

show abstract

“…The problem of recovering the structure of an unknown environment has received a great deal of attention by researchers [2,3,4,5,7,8,10,13,14,15,19,20,21]. Conventional vision-based approaches to the depth recovery problem have followed the approach described by Barnard and Fischler [1]: Image Acquisition, Camera Modeling, Feature Extraction, Image Matching, and Depth Determination.…”

Section: Introductionmentioning

confidence: 99%

A New Paradigm for Computational Stereo

Skifstad

Jain

1992

Active Perception and Robot Vision

View full text Add to dashboard Cite

Most research in computational stereo has followed the approach described in Barnard and Fischler's "Computational Stereo" (in Computing Surveys, vol. 14, no. 4, 1982). This approach, although conceptually appealing and theoretically elegant, suffers from several limitations. Among these are the difficulties in the matching process, problems with feature localization, restrictive camera geometries, and, perhaps most importantly, the extensive computational effort required to produce depth estimates. By approaching the problem from more of an engineering perspective, a new paradigm for computational stereo had been developed that avoids the problems inherent in the conventional "extract and match" paradigm. The Intensity Gradient Analysis (IGA) technique determines depth values by analyzing temporal intensity gradients arising from the optic flow field induced by known camera motion. IGA assumes nothing about the nature of the environment and places no restrictions on camera orientation (IGA is applicable to sequences obtained using arbitrary translational motion). A. K. Sood et al. (eds.), Active Perception and Robot Vision © Springer-Verlag Berlin Heidelberg 1992 I have. Now, how can I solve the problem?"

show abstract

Motion stereo for navigation of autonomous vehicles in man-made environments

Cited by 19 publications

References 4 publications

Using geometrical information for accurate scene understanding in an artificial vision system

Using geometrical information for accurate scene understanding in an artificial vision system

Camera calibration using a genetic algorithm

A New Paradigm for Computational Stereo

Contact Info

Product

Resources

About