3 . to meet the real - time demand in the robot soccer competition , this thesis proposed a color image segmentation method using improved threshold vector algorithm in yuv color space . the new algorithm can classify 8 colors in one time , so the speed of the algorithm is improved a lot 針對足球機器人系統(tǒng)中對視覺系統(tǒng)實時性方面的具體要求,提出了一種改進了閾值向量彩色圖像分割方法,對于一個未知顏色的像素點,一次計算就能夠判斷其顏色,并將其進行分類。
This dissertation develops research work for some fields in which ground clutter suppression algorithm may be used for airborne phased - array radar , software design of 3dt - - stap algorithm with adaptive space - frequence steer vector algorithm is completed for clutter suppression realtime processing system based on tigersharc ts101 chip 本論文圍繞機載相控陣雷達的空時二維處理技術(shù)展開研究工作,主要任務(wù)是為系統(tǒng)選擇地雜波抑制的算法,并完成以浮點dsp芯片( ts101 )為核心的基于3dt
Secondly , the improved rotation vector algorithms in the pure coning motion are discussed and the computing burden is compared with each other . lastly , computer simulations are executed to test the algorithms " performance . the results show that the rotation vector algorithms can improve the precision of the attitude calculation effectively 分析了高動態(tài)環(huán)境下捷聯(lián)慣導(dǎo)圓錐誤差的產(chǎn)生機理,研究了純錐運動條件下姿態(tài)更新的旋轉(zhuǎn)矢量優(yōu)化算法,對各算法的計算量和精度進行了對比,最后對各算法進行了計算機仿真,仿真結(jié)果表明:旋轉(zhuǎn)矢量算法能有效提高姿態(tài)算法的精度; 2
( 2 ) the influence to classification result is highly effected by using different classifier , for example , the center - vector algorithm obtains better classification results than other two algorithms . with the character feature , the average recall is 80 . 73 % , and the average precision is 82 . 94 % , and with the chinese - word feature , the average recall is 83 . 6 % , and the average precision is 85 . 97 % . different corpuses influence the classification result . for example , the average recall is 89 . 31 % and the average precision is 88 . 33 % , by using the news web pages as corpus from the web site " www . sina . com . cn " , which adopt the center - vector algorithm to structure classifier and select chinese - word as feature 對三種分類器分別以字、詞為特征進行分類測試、分析發(fā)現(xiàn):使用相同的分類算法,用詞作為特征項,比以字作為特征的分類效果好;用不同的算法構(gòu)造分類器對分類效果的影響很大,如中心向量算法在字、詞特征下的分類效果優(yōu)于其他兩算法;在以字為特征的情況下,該算法的平均查全率80 . 73 ,平均查準(zhǔn)率82 . 94 ;在以詞為特征的情況下,該算法的平均查全率83 . 6 ,平均查準(zhǔn)率85 . 97 ;選用語料不同對分類效果也有影響,如用新浪網(wǎng)( www . sina . com . cn )網(wǎng)頁語料進行測試,使用中心向量法分類器和詞作為特征的情況下,平均準(zhǔn)確率為89 . 31 ,平均查全率為88 . 33 。
Based on these descriptions , a nd model called support vector data description ( svdd ) is founded . ( 2 ) a qualitative guide for setting those parameters in oc - svms is investigated . a multi - layer high - speed training strategy was proposed to enable support vector algorithm to handle large training data ( 2 )通過分析支持向量機中模型參數(shù)對檢測結(jié)果的影響,給出了確定這些參數(shù)的一般方法;提出了一種分層式的快速訓(xùn)練方法,克服了樣本個數(shù)和維數(shù)對支持向量算法應(yīng)用的制約,提高了訓(xùn)練效率。