Admissibility of linear predictor in the general gauss - markov model under matrix loss 模型線性預(yù)測的可容許性
A one step adaptive linear predictor is used to predict the coming video traffic from users , and then the predicted results are used to help dba accurately distribute bandwidth to satisfy users ' needs 該算法利用自適應(yīng)線性單步預(yù)測器對(duì)未來到達(dá)的平均視頻流量進(jìn)行預(yù)測,實(shí)時(shí)預(yù)測結(jié)果用于對(duì)下一個(gè)發(fā)送時(shí)隙的計(jì)算,使得帶寬分配算法能夠充分滿足實(shí)時(shí)視頻流量需求。
What ’ s more , we design a 3d prediction compression scheme . the scheme is based on our optimal linear predictor and we use jpeg - ls lossless compression algorithm to compress the residual images . the scheme costs less time in computing , but works much better than jpeg - ls algorithm and software winrar 此外,用基于jpeg - ls的無損壓縮算法對(duì)運(yùn)用我們設(shè)計(jì)出的最佳線性預(yù)測器預(yù)測得到的殘差圖像進(jìn)行壓縮,運(yùn)算速度很快,壓縮比也大大優(yōu)于jpeg - ls算法和winrar壓縮軟件,具有很強(qiáng)的實(shí)用性。
Each band of hyperspectral image has the same physical structure , so we classification the first band , and design an optimal linear predictor for each class to make the mean prediction square error minimal , and then we use jpeg - ls algorithm to remove the spatial redundancy 由于高光譜圖像每個(gè)波段都具有相同的物理結(jié)構(gòu),先對(duì)首幅圖像進(jìn)行分類,在每個(gè)子類中分別使用各自的最佳線性預(yù)測器,將該類中的相鄰譜段進(jìn)行預(yù)測并將預(yù)測殘差均方降為最小,然后用jpeg - ls算法去除殘差圖像的相關(guān)性。
Secondly , hyperspectral images are hard to compress because of their abundant details , complicated texture and insignificant special correlation . making use of the significant spectral correlation within the hyperspectral images , we propose an optimal linear predictor which makes the square error minimal 針對(duì)高光譜遙感圖像細(xì)節(jié)豐富紋理復(fù)雜,空間相關(guān)性弱,難于壓縮的特點(diǎn),本文充分利用了高光譜遙感圖像的譜間相關(guān)性,設(shè)計(jì)出對(duì)相鄰譜段進(jìn)行預(yù)測并將預(yù)測殘差均方降為最小的一種最佳線性預(yù)測器。