發(fā)布時間：2018-04-02 09:36

  本文選題：運動目標(biāo)跟蹤　切入點：并行計算　出處：《哈爾濱工程大學(xué)》2016年碩士論文

【摘要】：計算機視覺技術(shù)作為自動控制系統(tǒng)的信息獲取方式是當(dāng)前自動化技術(shù)領(lǐng)域的一個熱點,其主要原因是視覺可以承載更多的信息。但是,視覺信息復(fù)雜、數(shù)據(jù)量大、有效特征提取困難,這給計算機視覺技術(shù)的研究帶來極大困難,成為目前計算機視覺研究的一個難點。目前,在PC機上實現(xiàn)基于視覺的跟蹤技術(shù)已經(jīng)很成熟,但是,由PC機或工作站等實現(xiàn)的視覺系統(tǒng)體積比較大,難以滿足靈活性要求。而基于嵌入式的視覺系統(tǒng)可以彌補以上不足,因此越來越受歡迎�；趩我惶幚砥鲗崿F(xiàn)的嵌入式算法比較多,而多處理器算法的大部分實現(xiàn)是利用協(xié)處理器架構(gòu)。本文以DSP (數(shù)字信號處理器)與FPGA (現(xiàn)場可編程門陣列)相互協(xié)同為基礎(chǔ),搭建了一個自動跟蹤系統(tǒng),實現(xiàn)攝像頭對運動目標(biāo)的隨動跟蹤。一方面,鑒于視頻處理中實時跟蹤涉及大量的并行運算,適合用FPGA來實現(xiàn)圖像的實時濾波、平滑等操作,同時在視頻流的采集和處理過程中,存儲圖像到SDRAM時運用FPGA操作存儲器速度更快。另一方面,目標(biāo)跟蹤涉及到大量的復(fù)雜運算和迭代算法,在DSP上實現(xiàn)更為容易。本文結(jié)合二者的優(yōu)點,設(shè)計用不同的處理器分別處理不同的操作,并行運行相互通信。在FPGA上實現(xiàn)顏色空間的轉(zhuǎn)換、混合高斯模型、形態(tài)學(xué)二值開運算、中值濾波和線性濾波等圖像處理算法和ⅡC時序、UART通訊接口、MCBSP、SDRAM控制器、BT656視頻解碼等接口;在DSP上實現(xiàn)雙分辨率的MeanShift算法用于運動目標(biāo)的跟蹤,并與FPGA進行通信。為了實現(xiàn)攝像頭對運動目標(biāo)的實時瞄準(zhǔn),在ATmega16單片機上實現(xiàn)了 PID算法以控制電機的運動。為了加快系統(tǒng)開發(fā)速度,本文首先在PC上論證并設(shè)計適合在FPGA與DSP上運行的算法結(jié)構(gòu),然后將算法映射到本文選定的硬件結(jié)構(gòu)上并通過與PC機通信以調(diào)試系統(tǒng)。實驗結(jié)果表明,本系統(tǒng)對運動目標(biāo)的隨動跟蹤具有快速和準(zhǔn)確的特點。
[Abstract]:Computer vision technology is a hot spot in the field of automation technology as the information acquisition method of automatic control system. The main reason is that vision can carry more information, but the visual information is complex and the amount of data is large. Effective feature extraction is difficult, which brings great difficulty to the research of computer vision technology, and becomes a difficulty in computer vision research. At present, it is very mature to realize the tracking technology based on vision on PC, but, The visual system realized by PC or workstation is large in volume and difficult to meet the requirement of flexibility. However, the vision system based on embedded system can make up for the above deficiency. So it's getting more and more popular. There are more embedded algorithms based on a single processor. Based on the cooperation between DSP (Digital signal processor) and FPGA (Field Programmable Gate Array), an automatic tracking system is built. On the one hand, because the real-time tracking of video processing involves a large number of parallel operations, it is suitable to use FPGA to realize real-time image filtering, smoothing and other operations. At the same time, in the process of video stream acquisition and processing, it is faster to use FPGA to store images to SDRAM. On the other hand, target tracking involves a large number of complex operations and iterative algorithms. It is easier to implement on DSP. In this paper, different processors are designed to deal with different operations with different processors, running parallel communication with each other. Color space conversion, mixed Gao Si model, morphological binary open operation are realized on FPGA. The image processing algorithms such as median filter and linear filter, and the interface of 鈪，

本文編號：1699787