- 6
- 0
- 约4.01千字
- 约 15页
- 2017-01-10 发布于湖南
- 举报
(c) 2000, 2001 SNU CSE Biointelligence Lab Chapter 6.Robot Vision Introduction Computer vision Endowing machines with the means to “see” Create an image of a scene and extract features Very difficult problem for machines Several different scenes can produce identical images. Images can be noisy . Cannot directly ‘invert’ the image to reconstruct the scene. Steering an Automobile ALVINN system [Pomerleau 1991,1993] Uses Artificial Neural Network Used 30*32 TV image as input (960 input node) 5 Hidden node 30 output node Training regime: modified “on-the-fly” A human driver drives the car
您可能关注的文档
- ppt课件-月亮-国家光学天文学天文台 (n o o)( the moon- national optical astronomy observatory( n o a o)).ppt
- ppt课件-月球与潮汐( moon& tides).ppt
- ppt课件-阅读 maps(time zones)-大学( reading maps(time zones)- universityof).ppt
- ppt课件-阅读地图 san joaquin 三角洲大学( reading maps- san joaquin delta college).ppt
- ppt课件-阅读地图-教育家页( reading maps- educator pages).ppt
- ppt课件-阅读地图居学区( reading maps- kyrene school district).ppt
- ppt课件-阅读地图-夏普学校( reading maps- sharp school).ppt
- ppt课件-阅读千分尺 glenrose f f a( reading a micrometer- glenrose f f a).ppt
- ppt课件-运动和结构战后图像序列理论( motionand structure recoveryfrom image sequences theory).ppt
- ppt课件-运行-对句子-自由大学( run- on sentences- liberty university).ppt
原创力文档

文档评论(0)