本文選題：模糊視覺 + 大型車輛�。� 參考：《計算機測量與控制》2014年09期

【摘要】：當前的車輛監(jiān)測系統(tǒng)進行大型車輛監(jiān)控的過程中,容易受到環(huán)境不可控因素的影響,造成監(jiān)控過程形式單一,對車輛細節(jié)識別準確度較低;提出基于模糊視覺技術的大型車輛監(jiān)控系統(tǒng)設計方法;系統(tǒng)由硬件和軟件這兩部分構成;硬件部分以FPGA為控制核心進行了設計,重點對交通圖像的采集模塊、緩存模塊、攝像機方案、監(jiān)視器方案和嵌入式處理器方案進行闡述;軟件部分首先對圖像進行預處理消除圖像中的噪聲.引入車輛細節(jié)模糊視覺特征識別模型表示外界隨機因素的干擾,根據(jù)模型的輸出結果計算車輛細節(jié)特征的像素密度,能夠?qū)囕v的細節(jié)狀態(tài)進行準確識別;實驗結果表明,利用設計的監(jiān)控系統(tǒng)對大型車輛進行監(jiān)控,能夠有效提高監(jiān)控的準確率,具有較強的穩(wěn)定性。
[Abstract]:The current vehicle monitoring system is easy to be affected by uncontrollable environmental factors in the process of large-scale vehicle monitoring, resulting in a single form of monitoring process and low accuracy of vehicle detail recognition. The design method of large vehicle monitoring system based on fuzzy vision technology is put forward. The system is composed of hardware and software. The hardware part is designed with FPGA as the control core, especially the traffic image acquisition module and buffer module. The camera scheme, monitor scheme and embedded processor scheme are described. Firstly, the image is preprocessed to eliminate the noise in the image. The fuzzy visual feature recognition model of vehicle details is introduced to represent the interference of external random factors. The pixel density of vehicle detail features can be calculated according to the output results of the model, which can accurately identify the details of vehicles. The experimental results show that, Using the designed monitoring system to monitor large vehicles can effectively improve the accuracy of monitoring and has strong stability.
【作者單位】： 青島酒店管理職業(yè)技術學院;
【分類號】：TP391.41;U495

【參考文獻】

相關期刊論文 前7條

1 覃永新;陳文輝;章帆;;實時視頻數(shù)據(jù)采集的FPGA實現(xiàn)[J];電子技術應用;2009年09期

2 朱立新;王平安;夏德深;;基于梯度場均衡化的圖像對比度增強[J];計算機輔助設計與圖形學學報;2007年12期

3 王瑩;南敬昌;郭凌云;;基于視頻圖像的車牌定位預處理算法[J];計算機測量與控制;2011年10期

4 潘兵,謝惠民,續(xù)伯欽,戴福隆;數(shù)字圖像相關中的亞像素位移定位算法進展[J];力學進展;2005年03期

5 李U，

本文編號：1974720