發(fā)布時間：2018-01-06 00:34

  本文關(guān)鍵詞：基于哈希的多目標跟蹤算法的研究　出處：《安徽大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 多目標跟蹤 哈希算法 卷積神經(jīng)網(wǎng)絡(luò) 行人檢測

【摘要】：隨著圖像處理領(lǐng)域的蓬勃發(fā)展,多目標跟蹤作為圖像處理的重要研究方向也取得了巨大的進展,使得多目標跟蹤技術(shù)可以成功應(yīng)用到各種實時視頻場景分析中,比如無人駕駛、無人機等。但是目前多目標跟蹤算法中仍然存在著遮擋、目標數(shù)量不確定、數(shù)據(jù)關(guān)聯(lián)、實時性要求等難題。為了解決目標數(shù)量不確定的問題,需要用一個性能優(yōu)秀的目標檢測器對視頻序列進行檢測,以獲得每幀圖片出現(xiàn)的目標位置以及數(shù)量。因此本文首先采用卷積神經(jīng)網(wǎng)絡(luò)結(jié)合選擇性搜索算法對視頻序列進行行人檢測。傳統(tǒng)的目標檢測算法一般首先提取目標的人工特征,然后使用該特征訓(xùn)練得到一個分類器,最后使用滑動窗口得到候選區(qū)域并對其分類。但是傳統(tǒng)的目標檢測算法具有以下缺陷:其一人工特征提取方法復(fù)雜,并且需要設(shè)計者具備一定的先驗知識,才能得到對目標描述較好的特征。其二傳統(tǒng)的目標檢測算法將特征提取過程與分類過程獨立開,如果提取的特征的描述性不夠充分,那么分類算法也無法取得較好的效果。與傳統(tǒng)的目標檢測算法相比,卷積神經(jīng)網(wǎng)絡(luò)不需要輸入復(fù)雜的人工特征,可以直接輸入樣本圖片,通過卷積運算自主學(xué)習(xí)得到更自然、更通用的樣本特征,而且得到的特征對于形變具有一定的不變性,因此使得卷積神經(jīng)網(wǎng)絡(luò)廣泛的應(yīng)用于目標檢測中。本文在經(jīng)典的卷積神經(jīng)網(wǎng)絡(luò)模型LeNet-5上進行改進并借助于Caffe框架搭建卷積神經(jīng)網(wǎng)絡(luò),然后通過在常用的行人檢測數(shù)據(jù)集中選取樣本構(gòu)成數(shù)據(jù)集,并在此數(shù)據(jù)集上進行對比實驗,通過實驗表明,將卷積神經(jīng)網(wǎng)絡(luò)應(yīng)用到行人檢測中能取得很好的效果。為了解決目標被遮擋的問題,本文將跟蹤目標從出現(xiàn)到離開攝像頭拍攝范圍的過程分為初始、跟蹤、丟失、結(jié)束四種狀態(tài),然后對處于不同狀態(tài)的目標進行不同的處理以解決遮擋問題。為了解決數(shù)據(jù)關(guān)聯(lián)、實時性要求等難題,本文使用哈希算法對檢測對象的圖像特征進行編碼,得到檢測對象的哈希碼,然后使用哈希碼內(nèi)積衡量當前幀檢測對象與前一時刻跟蹤目標之間的相似度,選取相似度最大的組合完成目標關(guān)聯(lián)。簡化了算法的復(fù)雜度的同時能夠完成它們之間的關(guān)聯(lián)。為了提高目標關(guān)聯(lián)的準確性,基于跟蹤目標就后幀必然在空間上存在連續(xù)這一先驗知識,本文將當前幀檢測對象與前一幀跟蹤目標之間的質(zhì)心距離也作為相似度的衡量標準。最后本文在MOT Benchmark數(shù)據(jù)集上進行實驗,與其他多目標跟蹤算法進行對比,對算法的有效性進行驗證。最后對本文的研究內(nèi)容進行總結(jié),并且根據(jù)實驗結(jié)果對本文提出的基于哈希算法的多目標跟蹤算法的不足之處提出下一步的改進方法。
[Abstract]:With the rapid development in the field of image processing, target tracking as an important research direction of image processing has made tremendous progress, the multi-target tracking technology can be successfully applied to a variety of real-time video scene analysis, such as unmanned drones, etc. but the multi-target tracking algorithm still exist in the shelter, the target number uncertain data association, the requirements of the real-time problem. In order to solve the problem of determining the number of goals, it is necessary to detect the video sequence with an excellent target detector to obtain each frame picture the target location and quantity. So this paper adopts convolution neural network combined with selective search algorithm for pedestrian detection video sequence. Artificial target detection algorithm of traditional feature extraction of target first, then use this feature to train a classifier, the most After the sliding window is used to get the candidate region and its classification. But the traditional target detection algorithm has the following defects: the artificial feature extraction method is complicated, and designers need to have certain prior knowledge, in order to get better describe the characteristics of the target. The target detection algorithm the traditional feature extraction process and classification process independently. If the extracted feature description is not sufficient, then the classification algorithm can achieve better results. Compared with the traditional detection algorithm, convolutional neural network does not need to manually input features of complex, you can directly enter the sample images, through the convolution of autonomous learning is more natural, more general and sample characteristics, has the characteristics of the invariance for the deformation, so that the application of convolutional neural networks in a wide range of target detection. Based on the classic volume To improve and use the Caffe framework to build product convolutional neural network LeNet-5 neural network model, and then through the common data set pedestrian detection sample data sets, and compared the experimental data set, experiments show that the convolution neural network is applied to pedestrian detection can achieve good results. In order to solve the target is blocked, the target tracking from appear to leave the camera shooting range, the process is divided into initial, tracking, lost, the end of the four states, and in different states of different target to solve the occlusion problem. In order to solve the data association, the requirements of the real-time problem, the image feature detection the object of encoding using a hashing algorithm to get the hash code of the detection object, and then use the hash code of the current frame detection object and measure the inner product of a moment ago with The similarity between the target tracking, select combination of maximum similarity target association. To simplify the complexity of the algorithm can be finished at the same time the association between them. In order to improve the accuracy of target tracking target is related, after this frame continuous prior knowledge in space based on the inevitable, the current frame with the previous object detection frame tracking between the target centroid distance as similarity measure. Finally, this paper makes experiments on MOT Benchmark data sets, and other multi target tracking algorithm are compared, verified the effectiveness of the algorithm. Finally, the research contents of this paper are summarized, put forward the improvement method of the next step and according to the experimental results of this paper the proposed multi target tracking algorithm based on hash algorithm's shortcomings.

【學(xué)位授予單位】：安徽大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前2條

1 羅寰;于雷;廖俊;穆中林;;復(fù)雜背景下紅外弱小多目標跟蹤系統(tǒng)[J];光學(xué)學(xué)報;2009年06期

2 常發(fā)亮;馬麗;喬誼正;;視頻序列中面向人的多目標跟蹤算法[J];控制與決策;2007年04期

，

本文編號：1385574