【摘要】：近年來(lái),在智能交通領(lǐng)域中,基于視頻的車輛檢測(cè)跟蹤已成為一個(gè)重要的研究方向。光流法在視頻運(yùn)動(dòng)分析等領(lǐng)域具有極其重要的基礎(chǔ)地位,能得到目標(biāo)詳細(xì)的二維運(yùn)動(dòng)信息,但光流算法計(jì)算的不適定及不能實(shí)時(shí)運(yùn)算等問(wèn)題限制了其廣泛應(yīng)用,因此研究出一種能實(shí)時(shí)執(zhí)行且精度較高的光流算法對(duì)推廣此算法在實(shí)時(shí)領(lǐng)域的應(yīng)用顯得尤為重要。若能將實(shí)時(shí)光流技術(shù)應(yīng)用于智能交通領(lǐng)域,對(duì)智能交通的發(fā)展也大有裨益。本文詳細(xì)闡述、分析了微分光流法的基本原理,并據(jù)此提出了多幀光流模型和其線性化求解方法,簡(jiǎn)化了光流的求解過(guò)程并提高了其估算精度;選擇GPU平臺(tái)做算法移植,解決光流的實(shí)時(shí)計(jì)算問(wèn)題;根據(jù)所得實(shí)時(shí)稠密光流給出了車輛檢測(cè)跟蹤方案。首先,時(shí)域相關(guān)性在視頻分析中具有重要作用,但在估算光流時(shí)這一特性卻很少被應(yīng)用。針對(duì)這一情況,提出在H-S光流模型基礎(chǔ)上引入前向幀并加入時(shí)域相關(guān)性約束,從而構(gòu)造出多幀光流模型。同時(shí),針對(duì)能量泛函線性化求解過(guò)程異常復(fù)雜的情況,提出運(yùn)用迭代重加權(quán)最小二乘法(IRLS)簡(jiǎn)化這一求解過(guò)程。其次,根據(jù)光流算法在像素間耦合性低這一特點(diǎn),選擇對(duì)其進(jìn)行GPU平臺(tái)移植。在計(jì)算統(tǒng)一設(shè)備(CUDA)架構(gòu)下通過(guò)多線程并行執(zhí)行方式同時(shí)對(duì)多個(gè)像素的光流值進(jìn)行估算。在估算結(jié)果精度相當(dāng)?shù)那闆r下,在GPU上執(zhí)行時(shí)間遠(yuǎn)小于CPU上執(zhí)行時(shí)間。對(duì)于分辨率為640*480的視頻圖像可以達(dá)到實(shí)時(shí)性運(yùn)算,能滿足一般的應(yīng)用要求。最后,給出一種改進(jìn)的車輛檢測(cè)跟蹤方案。一方面,方案使用GPU平臺(tái)計(jì)算所得實(shí)時(shí)稠密光流,相較于特征光流法和區(qū)域稠密光流法,可獲得更加準(zhǔn)確的全局運(yùn)動(dòng)信息,相較于幀差法等運(yùn)動(dòng)檢測(cè)算法,也能獲得更好的運(yùn)動(dòng)目標(biāo)提取效果;另一方面,方案根據(jù)光流場(chǎng)所得到的速度矢量對(duì)車輛幀間的位置進(jìn)行預(yù)測(cè)和匹配,能夠?qū)囕v在跟蹤過(guò)程中常見的狀態(tài)變化進(jìn)行判斷和處理,在實(shí)驗(yàn)中取得了預(yù)期的效果。
[Abstract]:In recent years, video-based vehicle detection and tracking has become an important research direction in the field of intelligent transportation. Optical flow method plays an important role in the field of video motion analysis. It can obtain the detailed two-dimensional motion information of the target. However, the problems such as the ill-posed calculation of optical flow algorithm and the impossibility of real-time operation limit its wide application. Therefore, it is very important to develop a real-time and high-precision optical flow algorithm to extend the application of this algorithm in real-time domain. If the real-time optical flow technology can be applied to the field of intelligent transportation, it will also be of great benefit to the development of intelligent transportation. In this paper, the basic principle of the differential optical flow method is analyzed in detail. Based on this, a multi-frame optical flow model and its linearization method are proposed, which simplifies the process of solving the optical flow and improves its estimation accuracy. The algorithm is transplanted on GPU platform to solve the problem of real-time calculation of optical flow, and the vehicle detection and tracking scheme is given according to the dense real-time optical flow obtained. First, time-domain correlation plays an important role in video analysis, but it is rarely used to estimate optical flow. In order to solve this problem, a multi-frame optical flow model is constructed by introducing forward frame and time-domain correlation constraint on the basis of HES optical flow model. At the same time, the iterative reweighted least square method (IRLS) is proposed to simplify the solution process in view of the complexity of the linearization process of the energy functional. Secondly, according to the low coupling between pixels, the optical flow algorithm is transplanted on GPU platform. The optical flow values of multiple pixels are estimated in parallel multi-thread execution mode under the (CUDA) architecture of computing unified device at the same time. Under the same precision, the execution time on GPU is much shorter than that on CPU. The video image with a resolution of 640 脳 480 can achieve real-time operation and can meet the general application requirements. Finally, an improved vehicle detection and tracking scheme is presented. On the one hand, the scheme uses the GPU platform to calculate the real-time dense optical flow. Compared with the characteristic optical flow method and the region dense optical flow method, the scheme can obtain more accurate global motion information, compared with the frame difference method and other motion detection algorithms. It can also get better effect of moving object extraction. On the other hand, the scheme predicts and matches the vehicle frame position according to the velocity vector obtained from the optical flow field, which can judge and deal with the common state changes in the tracking process of the vehicle, and achieves the expected effect in the experiment.
【學(xué)位授予單位】：江蘇科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 李琦;邵春福;岳昊;;核窗口尺寸和目標(biāo)模型自適應(yīng)的均值漂移跟蹤[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年02期

2 朱安民;陳燕明;;基于特征點(diǎn)一致性約束的實(shí)時(shí)目標(biāo)跟蹤算法[J];深圳大學(xué)學(xué)報(bào)(理工版);2013年03期

相關(guān)碩士學(xué)位論文 前1條

1 張鐘漢;各向異性的微分光流和匹配光流算法[D];西安電子科技大學(xué);2011年

，

本文編號(hào)：2463494