復(fù)雜環(huán)境下智能車輛動(dòng)態(tài)目標(biāo)三維感知方法研究
[Abstract]:Drivers' processing of traffic environment information includes three stages: sensation, perception and cognition. Similarly, intelligent vehicle "driving brain" can only achieve real "intelligent" driving if it is sublimated to environmental perception like human beings. As an important means for intelligent vehicle to improve the depth of environmental perception, the research of dynamic target perception based on 3D lidar has been paid great attention to and many achievements have been made. However, the following problems still exist: first, the environment of perception is simple, that is, the simple traffic scene is usually focused on a single perceptual object, sparse target distribution, and less research on the complex scene where the target is mixed and densely distributed; The second is that most of them are in the stage of low-level perception, that is to say, the focus of the research is on the detection and recognition of dynamic targets, and less on the intrinsic behavior of cognitive targets. In view of the above problems, this paper studies the dynamic target perception method based on 3D lidar in complex environment, focusing on the perception, perception and cognitive mechanism of dynamic target, taking its state, category and behavior perception as the specific research object. The performance of the system is verified by the data collected in the natural environment. Firstly, based on the two scientific problems of intelligent vehicle environment perception, the research object and scope of dynamic target perception are clarified, and the research ideas from dynamic target state, category to behavior from low-level to advanced perception are put forward. On this basis, the overall research scheme and architecture are constructed. Aiming at the contradiction between accuracy and real-time of target detection under the condition of massive point cloud, the segmentation of point cloud is transformed into image domain and processed by mature methods in image science. Then, in order to overcome the difference of point cloud density at different distances in target recognition, a point cloud density enhancement method is proposed to generate a new target point cloud that meets the requirements of target density. In order to improve the applicability of point cloud features and model classification ability. On this basis, the key state parameters of vehicle target are modeled, and the parameters are optimized by using the tracking method of decision tree-tracking gate and joint probabilistic data association Kalman filter. Finally, a vehicle behavior recognition model based on natural speech recognition is proposed, which is based on the analysis and modeling of vehicle moving behavior. In order to verify the effectiveness of the method, the data collected under the natural traffic environment were tested. The results show that the 3D sensing system can quickly and accurately calculate the state and class parameters of dynamic targets in complex traffic environment. At the same time, the behavior recognition model based on natural speech recognition method can not only help to establish a general framework and system of vehicle behavior recognition, but also can accurately and hierarchically reflect the degree of behavior and improve the depth of perception.
【學(xué)位授予單位】:清華大學(xué)
【學(xué)位級(jí)別】:博士
【學(xué)位授予年份】:2016
【分類號(hào)】:U463.6;TN958.98
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 李國(guó)棟,劉春陽(yáng),柳長(zhǎng)安;一種基于特征的動(dòng)態(tài)目標(biāo)檢測(cè)與跟蹤算法[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2005年07期
2 劉語(yǔ)平;雙向制約與激勵(lì)[J];中國(guó)三峽建設(shè);2002年07期
3 周蘆蘆;曹凱;;基于動(dòng)態(tài)目標(biāo)位置的車輛彎道保持控制仿真[J];山東理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年02期
4 陳景濤;楊志剛;程力;王華磊;;運(yùn)動(dòng)車輛的視頻動(dòng)態(tài)目標(biāo)檢測(cè)[J];汽車工程學(xué)報(bào);2014年01期
5 龍真真;張策;王維平;張正文;;一種基于數(shù)據(jù)流聚類的動(dòng)態(tài)目標(biāo)分群框架[J];上海交通大學(xué)學(xué)報(bào);2010年07期
6 劉永東,王佳,梁晉文;動(dòng)態(tài)目標(biāo)全姿態(tài)激光跟蹤測(cè)量[J];激光與紅外;1999年03期
7 李莉,段錦,顧玲嘉;一種動(dòng)態(tài)目標(biāo)檢測(cè)與跟蹤的方法研究[J];長(zhǎng)春理工大學(xué)學(xué)報(bào);2005年03期
8 王偉;李崗;侯亞麗;焦景欣;;動(dòng)態(tài)目標(biāo)熱紅外涂層隱身效能測(cè)試評(píng)價(jià)系統(tǒng)[J];探測(cè)與控制學(xué)報(bào);2012年06期
9 楊洪芹;利用DDE協(xié)議獲取動(dòng)態(tài)目標(biāo)跟蹤數(shù)據(jù)[J];大連海事大學(xué)學(xué)報(bào);1996年04期
10 野舟;米曼;;聯(lián)合防區(qū)外武器C-1打擊靜態(tài)及動(dòng)態(tài)目標(biāo)的演示試驗(yàn)獲得成功[J];飛航導(dǎo)彈;2013年04期
相關(guān)會(huì)議論文 前6條
1 王坤;王磊;游安清;;基于形殊點(diǎn)的動(dòng)態(tài)目標(biāo)“定位”方法研究[A];第九屆全國(guó)光電技術(shù)學(xué)術(shù)交流會(huì)論文集(下冊(cè))[C];2010年
2 王坤;游安清;賀喜;王磊;;基于動(dòng)態(tài)目標(biāo)結(jié)構(gòu)特征的姿態(tài)實(shí)時(shí)定位方法[A];第十屆全國(guó)光電技術(shù)學(xué)術(shù)交流會(huì)論文集[C];2012年
3 李剛偉;邱宗明;盧剛;;動(dòng)態(tài)目標(biāo)三維激光跟蹤測(cè)量?jī)x[A];制造技術(shù)自動(dòng)化學(xué)術(shù)會(huì)議論文集[C];2002年
4 宋丹;趙保軍;;一種基于SIFT算子的動(dòng)態(tài)目標(biāo)跟蹤的改進(jìn)方法[A];全國(guó)第4屆信號(hào)和智能信息處理與應(yīng)用學(xué)術(shù)會(huì)議論文集[C];2010年
5 肖作江;安志勇;石麗霞;;基于LabVIEW動(dòng)態(tài)目標(biāo)發(fā)生器穩(wěn)定性光電檢測(cè)技術(shù)研究[A];2008中國(guó)儀器儀表與測(cè)控技術(shù)進(jìn)展大會(huì)論文集(Ⅰ)[C];2008年
6 韓冰;;小尺寸、新型動(dòng)態(tài)MTF測(cè)試設(shè)備的研制[A];第十四屆全國(guó)光學(xué)測(cè)試學(xué)術(shù)討論會(huì)論文(摘要集)[C];2012年
相關(guān)重要報(bào)紙文章 前2條
1 通訊員 周實(shí)辦;我州全面推行全流程動(dòng)態(tài)目標(biāo)管理[N];紅河日?qǐng)?bào);2009年
2 通訊員 光興;成都實(shí)行動(dòng)態(tài)目標(biāo)管理[N];中國(guó)房地產(chǎn)報(bào);2003年
相關(guān)博士學(xué)位論文 前3條
1 趙謙;煤礦井下動(dòng)態(tài)目標(biāo)視頻監(jiān)測(cè)圖像處理研究[D];西安科技大學(xué);2014年
2 王肖;復(fù)雜環(huán)境下智能車輛動(dòng)態(tài)目標(biāo)三維感知方法研究[D];清華大學(xué);2016年
3 程龍;面向移動(dòng)設(shè)備的動(dòng)態(tài)目標(biāo)的光場(chǎng)渲染技術(shù)研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2009年
相關(guān)碩士學(xué)位論文 前10條
1 王偉;復(fù)雜環(huán)境下移動(dòng)機(jī)器人的動(dòng)態(tài)目標(biāo)檢測(cè)與跟蹤控制研究[D];西安建筑科技大學(xué);2015年
2 洪怡琳;多旋翼飛行器基于單目視覺(jué)的動(dòng)態(tài)目標(biāo)跟蹤[D];大連理工大學(xué);2015年
3 趙振杰;視頻序列中動(dòng)態(tài)目標(biāo)的檢測(cè)、定位與跟蹤技術(shù)研究[D];南開(kāi)大學(xué);2015年
4 郭春鳳;視頻圖像序列的動(dòng)態(tài)目標(biāo)檢測(cè)新算法研究[D];福州大學(xué);2013年
5 馬世強(qiáng);卡爾曼與均值漂移在動(dòng)態(tài)目標(biāo)跟蹤中的應(yīng)用研究[D];內(nèi)蒙古大學(xué);2016年
6 王光彪;基于雙目機(jī)器人的動(dòng)態(tài)目標(biāo)檢測(cè)與跟蹤方法研究[D];天津理工大學(xué);2013年
7 葉瑞;基于云臺(tái)控制的無(wú)人車動(dòng)態(tài)目標(biāo)跟蹤[D];西安工業(yè)大學(xué);2013年
8 王春輝;跟蹤轉(zhuǎn)臺(tái)檢測(cè)用動(dòng)態(tài)目標(biāo)生成技術(shù)[D];長(zhǎng)春理工大學(xué);2014年
9 閆光;基于多傳感器信息融合的動(dòng)態(tài)目標(biāo)檢測(cè)與識(shí)別[D];北京理工大學(xué);2015年
10 韓雷;基于無(wú)線傳感器網(wǎng)絡(luò)的動(dòng)態(tài)目標(biāo)三維跟蹤[D];南京大學(xué);2015年
,本文編號(hào):2412965
本文鏈接:http://sikaile.net/shoufeilunwen/xxkjbs/2412965.html