本文選題：非均勻性校正 + 神經(jīng)網(wǎng)絡(luò)算法��； 參考：《激光與紅外》2016年08期

【摘要】：針對某國產(chǎn)探測器成像特點(diǎn),對傳統(tǒng)兩點(diǎn)校正和神經(jīng)網(wǎng)絡(luò)非均勻性校正算法進(jìn)行了改進(jìn)和定點(diǎn)化處理。對算法實(shí)現(xiàn)時的存儲和數(shù)據(jù)流需求進(jìn)行分析后,利用存儲控制器對DDR2高速讀寫的優(yōu)勢,在以FPGA為核心的紅外成像裝置預(yù)處理平臺上實(shí)現(xiàn)了校正系數(shù)的在線標(biāo)定和自適應(yīng)迭代。在系數(shù)更新時,引入運(yùn)動判斷環(huán)節(jié),以防止神經(jīng)網(wǎng)絡(luò)校正算法帶來的目標(biāo)退化和鬼影現(xiàn)象。成像系統(tǒng)僅采用一片F(xiàn)PGA芯片,使得系統(tǒng)小型化成為可能,充足的資源余量使其具有功能可擴(kuò)充性。實(shí)驗證明該實(shí)現(xiàn)方法明顯改善了紅外成像裝置的非均勻性,在抑制時間漂移上也取得了滿意的效果。
[Abstract]:According to the imaging characteristics of a home-made detector, the traditional two-point correction and neural network nonuniformity correction algorithm are improved and fixed-point processing is carried out. After analyzing the requirement of storage and data flow when the algorithm is implemented, the on-line calibration and adaptive iteration of correction coefficients are realized on the pre-processing platform of infrared imaging device based on FPGA, using the advantage of memory controller to read and write DDR2 at high speed. In order to prevent the target degradation and ghost phenomenon caused by the neural network correction algorithm, the motion judgment is introduced when the coefficients are updated. Only one FPGA chip is used in the imaging system, which makes the system miniaturized and has sufficient resource margin to make it functional and extensible. The experimental results show that the proposed method can improve the nonuniformity of infrared imaging device and achieve satisfactory results in suppressing the time drift.
【作者單位】： 中國空空導(dǎo)彈研究院;
【分類號】：TP391.41;TN219

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 王浩天;單甘霖;段修生;;基于LM-BP神經(jīng)網(wǎng)絡(luò)算法的模擬電路故障診斷[J];計算機(jī)測量與控制;2013年12期

2 邵忠良;黎安軍;曹薇;呂軍;;基于RBF神經(jīng)網(wǎng)絡(luò)算法的被動紅外探測器設(shè)計及單片機(jī)實(shí)現(xiàn)[J];廣東水利電力職業(yè)技術(shù)學(xué)院學(xué)報;2007年03期

3 祁漢逸;;基于神經(jīng)網(wǎng)絡(luò)算法的配電網(wǎng)APF最優(yōu)規(guī)劃[J];科協(xié)論壇(下半月);2010年02期

4 ;[J];;年期

，

本文編號：1937906