基于機器視覺的室內(nèi)人物檢測與場景識別
發(fā)布時間：2019-01-10 09:53
【摘要】：室內(nèi)環(huán)境下的場景理解是室內(nèi)移動機器人必須具備的能力之一,隨著全球服務(wù)機器人行業(yè)的興起,半結(jié)構(gòu)化環(huán)境下的室內(nèi)場景理解成為計算機視覺領(lǐng)域的研究熱點,也是一個難點,其主要體現(xiàn)在室內(nèi)環(huán)境的復(fù)雜性,識別算法的魯棒性以及實時性上。室內(nèi)場景理解包括室內(nèi)環(huán)境下的目標物體檢測,機器人所處環(huán)境估計,室內(nèi)障礙物規(guī)避,人的檢測和身份識別等。圍繞上文所提出的問題,本文以室內(nèi)行人和物體檢測為研究內(nèi)容,主要的研究和工作內(nèi)容如下:1)本文詳細分析了卷積神經(jīng)網(wǎng)絡(luò)的特征提取和分類方法,并將該方法進行物體識別效果與SIFT特征提取加FLANN匹配方法的物體識別效果作對比,得出在目標物體的不同觀察角度與目標物體發(fā)生形變的情況下,卷積神經(jīng)網(wǎng)絡(luò)物體識別效果明顯優(yōu)于SIFT特征提取加FLANN匹配方法識別效果的結(jié)論。2)針對傳統(tǒng)場景識別底層特征語義信息表達能力的不足,結(jié)合卷積神經(jīng)網(wǎng)絡(luò),本文提出一種基于物體檢測的室內(nèi)場景識別方法。該方法首先采用卷積神經(jīng)網(wǎng)絡(luò)對場景中的目標進行特征提取和分類,然后基于概率模型以檢測到的目標作為中間橋梁去推斷當前所處的場景。與基于計算機視覺底層特征的場景識別方法相比,該方法更接近于人類對場景的認知思維。本文運用該方法對場景的五種室內(nèi)場景進行場景識別分類,取得不錯效果。3)為了測試機器人在室內(nèi)環(huán)境下對行人檢測效果和響應(yīng),本文在PR2機器人平臺下基于ROS系統(tǒng)(Robot Operating System),采用Haar-Like特征與Ada Boost分類器實現(xiàn)人臉檢測,并用EigenFace進行身份識別,同時用HOG(Histogram of Oriented Gradient)特征與SVM(Support Vector Machine)分類器進行人體檢測,并實現(xiàn)機器人對行人的自主跟隨。
[Abstract]:Scene understanding in indoor environment is one of the necessary capabilities of indoor mobile robot. With the rise of global service robot industry, indoor scene understanding in semi-structured environment has become a research hotspot in the field of computer vision. It is also a difficult point, which is mainly reflected in the complexity of indoor environment, the robustness of recognition algorithm and the real-time performance. Indoor scene understanding includes object detection in indoor environment, robot environment estimation, indoor obstacle avoidance, human detection and identity recognition. The main contents of this paper are as follows: 1) the feature extraction and classification methods of convolution neural network are analyzed in detail. The object recognition effect of this method is compared with that of SIFT feature extraction and FLANN matching method. The result of object recognition based on convolution neural network is obviously better than that of SIFT feature extraction and FLANN matching. 2) aiming at the deficiency of semantic information expression of traditional scene recognition underlying features, we combine convolutional neural network with convolution neural network. This paper presents a method of indoor scene recognition based on object detection. Firstly, the convolution neural network is used to extract and classify the features of the targets in the scene, and then based on the probabilistic model, the detected target is used as the intermediate bridge to infer the current scene. Compared with the scene recognition method based on the underlying features of computer vision, this method is more similar to the cognitive thinking of the scene. In this paper, we use this method to classify the scene of five indoor scenes, and get good results. 3) in order to test the robot in the indoor environment to detect the effect and response to pedestrian, In this paper, based on ROS system (Robot Operating System), Haar-Like feature and Ada Boost classifier are used to realize face detection based on PR2 robot platform, and EigenFace is used to identify human face. At the same time, the HOG (Histogram of Oriented Gradient) feature and SVM (Support Vector Machine) classifier are used to detect the human body, and the robot can follow the pedestrian autonomously.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP242
本文編號：2406198
[Abstract]:Scene understanding in indoor environment is one of the necessary capabilities of indoor mobile robot. With the rise of global service robot industry, indoor scene understanding in semi-structured environment has become a research hotspot in the field of computer vision. It is also a difficult point, which is mainly reflected in the complexity of indoor environment, the robustness of recognition algorithm and the real-time performance. Indoor scene understanding includes object detection in indoor environment, robot environment estimation, indoor obstacle avoidance, human detection and identity recognition. The main contents of this paper are as follows: 1) the feature extraction and classification methods of convolution neural network are analyzed in detail. The object recognition effect of this method is compared with that of SIFT feature extraction and FLANN matching method. The result of object recognition based on convolution neural network is obviously better than that of SIFT feature extraction and FLANN matching. 2) aiming at the deficiency of semantic information expression of traditional scene recognition underlying features, we combine convolutional neural network with convolution neural network. This paper presents a method of indoor scene recognition based on object detection. Firstly, the convolution neural network is used to extract and classify the features of the targets in the scene, and then based on the probabilistic model, the detected target is used as the intermediate bridge to infer the current scene. Compared with the scene recognition method based on the underlying features of computer vision, this method is more similar to the cognitive thinking of the scene. In this paper, we use this method to classify the scene of five indoor scenes, and get good results. 3) in order to test the robot in the indoor environment to detect the effect and response to pedestrian, In this paper, based on ROS system (Robot Operating System), Haar-Like feature and Ada Boost classifier are used to realize face detection based on PR2 robot platform, and EigenFace is used to identify human face. At the same time, the HOG (Histogram of Oriented Gradient) feature and SVM (Support Vector Machine) classifier are used to detect the human body, and the robot can follow the pedestrian autonomously.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP242
【參考文獻】
相關(guān)期刊論文 前1條
1 鄧中亮;余彥培;袁協(xié);萬能;楊磊;;室內(nèi)定位現(xiàn)狀與發(fā)展趨勢研究(英文)[J];中國通信;2013年03期
，本文編號：2406198
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2406198.html
最近更新
教材專著
