本文選題：行人檢測 + 區(qū)域建議網(wǎng)絡(luò)　； 參考：《浙江大學(xué)》2017年碩士論文

【摘要】：近年來,隨著人工智能和機器學(xué)習(xí)的快速發(fā)展,計算機視覺也進入了發(fā)展的黃金時期,吸引了眾多學(xué)者以及企業(yè)的目光。行人檢測是計算機視覺中的重要課題之一,在智能視頻監(jiān)控和無人駕駛汽車等應(yīng)用領(lǐng)域都有著舉足輕重的地位。本文便著眼于行人檢測這一重要且極具挑戰(zhàn)的課題,行人檢測本質(zhì)上是個二分類問題,性能優(yōu)異的行人檢測算法既要有良好的分類算法也要有優(yōu)秀的特征。本文的主要工作歸納如下:在行人檢測領(lǐng)域中,已經(jīng)被經(jīng)常使用的分類算法有AdaBoost、支持向量機以及卷積神經(jīng)網(wǎng)絡(luò)中的Softmax分類函數(shù)等。梯度提升決策樹(GBDT)是數(shù)據(jù)挖掘領(lǐng)域中性能非常出眾的分類算法,在個性化推薦、金融預(yù)測等方面都有著成功的應(yīng)用案例。然而,它目前還沒有被應(yīng)用于行人檢測的算法中,因此本文的第一個創(chuàng)新點是把梯度提升決策樹算法應(yīng)用于行人檢測中。本文設(shè)計了ACF/LDCF+GBDT算法,并在Inria、Caltech、Kitti幾個主流的數(shù)據(jù)集上進行實驗,實驗結(jié)果證實了梯度提升決策樹算法可以較好地適用于行人檢測的研究中。卷積神經(jīng)網(wǎng)絡(luò)所得到的特征是對輸入圖像更抽象、更高層次的表達,高層次表達可以提升輸入數(shù)據(jù)的區(qū)分度,我們采用一種優(yōu)秀的卷積神經(jīng)網(wǎng)絡(luò)特征來進行行人檢測算法的設(shè)計。FasterR-CNN中的區(qū)域建議網(wǎng)絡(luò)(RPN)本身可以做為一個性能較好的行人檢測器,但后面的分類器降低了其應(yīng)有的性能�；诖吮疚奶岢隽说诙䝼�創(chuàng)新點,先使用區(qū)域建議網(wǎng)絡(luò)進行候選框的建議以及特征的提取,隨后使用Bootstrapping策略分多個階段采用梯度提升決策樹算法進行模型的訓(xùn)練,充分挖掘疑似行人的負樣本,并把這些樣本加入訓(xùn)練集中的負樣本里,從而逐步提升檢測器的性能。此外,為了加快訓(xùn)練速度及有效地避免過擬合現(xiàn)象,我們采用了隨機梯度提升的策略:每個階段隨機選取部分樣本、隨機選取部分特征用于決策樹的訓(xùn)練,即訓(xùn)練過程中我們采用了隨機梯度提升決策樹算法。最終,本文設(shè)計了基于隨機梯度提升決策樹與區(qū)域建議網(wǎng)絡(luò)的行人檢測算法,并在當(dāng)前流行的Caltech數(shù)據(jù)集上進行了實驗。實驗結(jié)果表明,經(jīng)過以上改進后我們可得到一個性能非常優(yōu)秀的行人檢測器。
[Abstract]:In recent years, with the rapid development of artificial intelligence and machine learning, computer vision has entered a golden period of development, attracting the attention of many scholars and enterprises. Pedestrian detection is one of the most important subjects in computer vision. It plays an important role in intelligent video surveillance and driverless vehicle applications. This paper focuses on pedestrian detection, which is an important and challenging subject. Pedestrian detection is essentially a two-classification problem. The excellent pedestrian detection algorithm should have good classification algorithm as well as excellent characteristics. The main work of this paper is summarized as follows: in the field of pedestrian detection, the commonly used classification algorithms are Ada boost, support vector machine and Softmax classification function in convolution neural network. Gradient elevation decision Tree (GBDT) is a very outstanding classification algorithm in the field of data mining. It has been successfully applied in personalized recommendation and financial forecasting. However, it has not been applied to pedestrian detection, so the first innovation of this paper is to apply gradient lifting decision tree algorithm to pedestrian detection. In this paper, ACFR / LDCF GBDT algorithm is designed and tested on several main data sets of Inria Caltech Kitti. The experimental results show that the gradient lifting decision tree algorithm is suitable for pedestrian detection. The feature of convolution neural network is that the input image is more abstract and expressed at a higher level, which can improve the differentiation of input data. We use an excellent convolution neural network feature to design a pedestrian detection algorithm. The area recommendation Network (RPN) in FasterR-CNN can be used as a pedestrian detector with better performance, but the latter classifier reduces its performance. Based on this, a second innovation is proposed. Firstly, the proposed candidate and feature are extracted by using the regional suggestion network, and then the model is trained by gradient lifting decision tree algorithm in several stages using bootstrapping strategy. The negative samples of suspected pedestrians are fully mined and added to the negative samples in the training set to improve the performance of the detector step by step. In addition, in order to accelerate the training speed and avoid overfitting effectively, we adopt the strategy of random gradient lifting: random selection of parts of samples, random selection of some features for the training of decision trees in each stage. In the process of training, we adopt the stochastic gradient lifting decision tree algorithm. Finally, a pedestrian detection algorithm based on stochastic gradient lifting decision tree and regional recommendation network is designed and tested on the current popular Caltech data set. The experimental results show that after the above improvements, we can get a very good performance pedestrian detector.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP183

【相似文獻】

相關(guān)期刊論文 前6條

1 丁鋒;汪菲菲;汪學(xué)海;;多元偽線性回歸系統(tǒng)部分耦合多新息隨機梯度類辨識方法[J];南京信息工程大學(xué)學(xué)報(自然科學(xué)版);2014年02期

2 丁潔;謝莉;丁鋒;;非均勻采樣系統(tǒng)多新息隨機梯度辨識性能分析[J];控制與決策;2011年09期

3 丁鋒,楊家本;隨機梯度算法的收斂性分析[J];清華大學(xué)學(xué)報(自然科學(xué)版);1999年01期

4 袁平;丁峰;;多變量系統(tǒng)隨機梯度辨識方法比較研究[J];科學(xué)技術(shù)與工程;2008年03期

5 劉景t，

本文編號：2076695