Jamzad, M., Sadjad, B.S., Mirrokni, V.S., Kazemi, M., Chitsaz, H., Heydarnoori, A., Hajiaghai, M.T., Chiniforooshan, E.: A fast vision system for middle size robots in robocup. In: RoboCup Symposium. (2001)  Home/Search   Document Not in Database   Summary   Related Articles   Check

....necessary to perform any kind of pre run calibration. Although it is not necessary to use the full resolution of images to detect objects, it helps in determining their sizes and positions precisely. A very fast method for object finding which uses the concept of perspective view is suggested in [5]. Several additional methods restricting the number of pixels being processed during object finding are presented in this paper. 2 Image Processing The key ideas of the image processing method presented in this paper are that speed can be achieved by avoiding to process all pixels of an image, ....

M. Jamzad, B. Sadjad, V. Mirrokni, M. Kazemi, H. Chitsaz, A. Heydarnoori, M. Hajiaghai, and E. Chiniforooshan. A fast vision system for middle size robots in RoboCup. In RoboCup 2001 Robot Soccer World Cup V, A. Birk, S. Coradeschi, S. Tadokoro (Eds.), number 2377 in Lecture Notes in Artificial Intelligence, pages 71--80, 2002.

....because lines are often partially hidden either by other robots or due to the limited opening angle of the camera. To find pixels on edges, in the image vertical lines having a distance of five pixels to one another are scanned from top to bottom following the method described in [4] (cf. Fig. 3b) In contrast to this method no color classification is applied. As the green of the field is very dark, all edges are characterized by a big difference of the Y channel of adjacent pixels. An increase in the Y channel followed by a decrease is an indication for an edge. If the ....

M. Jamzad, B. Sadjad, V. Mirrokni, M. Kazemi, H. Chitsaz, A. Heydarnoori, M. Hajiaghai, and E. Chiniforooshan, "A fast vision system for middle size robots in robocup," in 5th International Workshop on RoboCup 2001.

....illumination is constant and roughly homogeneous. Due to these restrictions, classes of objects (e.g. robots, ball, lines, color markers, goals) can roughly be identified by color classification. To the best of our knowledge, all robot soccer teams participating in RoboCup use color classification [30, 33, 14, 16, 6, 3]. However, color classification is usually not feasible in a natural scene. In this paper we consider a natural scene to be a scene where the colors of objects and the illumination are not restricted and where texture, clutter, shading, and specularity complicate image interpretation. Especially ....

M. Jamzad, B. Sadjad, V. Mirrokni, M. Kazemi, H. Chitsaz, A. Heydarnoori, M. Hajiaghai, and E. Chiniforooshan. A fast vision system for middle size robots in robocup. In 5th International Workshop on RoboCup (Robot World Cup Soccer Games and Conferences), Lecture Notes in Computer Science. Springer-Verlag, 2001.

....is constant and roughly homogeneous. Due to this restrictions classes of objects (e.g. robots, ball, lines, color markers, goals) can roughly be identified by their color. To the best of our knowledge, all robot soccer teams using cameras apply a color labeling step to the sensed image data, e.g. [29, 32, 15, 17, 6, 3]. In this label ing or classification step the color value of a pixel is mapped to one of the distinct colors. Labeling provides the advantage of a fast and substantial reduction of the image data while maintaining the major part of the relevant information. However even in the restricted RoboCup ....

....with an enlarged area of convergence. Furthermore, high frequency information of the image data is not lost. Several segmentation methods integrate different image cues such as texture and color or brightness [4, 22, 23, 30] To the best of our knowledge all RoboCup teams use color labeling [29, 32, 15, 17, 6, 3] which belongs to the category of region based methods. Used color spaces are for example YUV [32, 17, 6, 3] and ISY [15] The boundaries between the classes are usually defined as rectangles, boxes, or pizza slices . Simon et al. 29] propose spatially adapted thresholds. In order to infer the ....

[Article contains additional citation context not shown here]

JAMZAD, M., SADJAD, B., MIRROKNI, V., KAZEMI, M., CHITSAZ, H., HEYDARNOORI, A., HAJIAGHAI, M., AND CHINIFOROOSHAN, E. A fast vision system for middle size robots in RoboCup. In 5th International Workshop on RoboCup (Robot World Cup Soccer Games and Conferences) (2001), Lecture Notes in Computer Science, Springer-Verlag.

No context found.

M. Jamzad, et al, a fast vision system for middle size robots in RoboCup, submitted to RobCup Symposium, Seattle-2001.

....for mobile robots. A robot can not plan to dribble other robots which are too far from it. However, a robot should be able to dribble other robots which are within a close distance to it. In our dribbling procedure, we assume a bounding box around the opponent robot that should be dribbled [2]. 4 As it is seen in figure 2, ff and fi are the left and right angles of our robot with respect to the left and right side of the opponent robot. The dribbling procedure is described as follows: while (distance(o) neardistance) nearrobotdistance means the close distance within which we ....

M. Jamzad, et al, a fast vision system for middle size robots in RoboCup, submitted to RobCup Symposium, Seattle-2001.

No context found.

Jamzad, M., Sadjad, B.S., Mirrokni, V.S., Kazemi, M., Chitsaz, H., Heydarnoori, A., Hajiaghai, M.T., Chiniforooshan, E.: A fast vision system for middle size robots in robocup. In: RoboCup Symposium. (2001)

No context found.

M. Jamzad, B. Sadjad, V. Mirrokni, M. Kazemi, H. Chitsaz, A. Heydarnoori, M. Hajiaghai, and E. Chiniforooshan. A fast vision system for middle size robots in robocup. In 5th International Workshop on RoboCup 2001 (Robot World Cup Soccer Games and Conferences), number 2377 in Lecture Notes in Computer Science, pages 71--80. Springer, 2002.

No context found.

M. Jamzad, B. Sadjad, V. Mirrokni, M. Kazemi, H. Chitsaz, A. Heydarnoori, M. Hajiaghai, and E. Chiniforooshan. A fast vision system for middle size robots in robocup. In 5th International Workshop on RoboCup 2001 (Robot World Cup Soccer Games and Conferences), number 2377 in Lecture Notes in Computer Science, pages 71--80. Springer, 2002.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC