本文選題：自主車　切入點(diǎn)：道路理解　出處：《北京理工大學(xué)》2015年博士論文

【摘要】：自主車體現(xiàn)了控制科學(xué)、機(jī)器人學(xué)、認(rèn)知科學(xué)、智能交通等多學(xué)科的交叉,是探索新理論和新技術(shù)的載體,在軍用、民用及大科學(xué)工程中均具有重要應(yīng)用價(jià)值�；谝曈X的道路環(huán)境理解技術(shù)是自主車走向全自主和實(shí)用化的關(guān)鍵,但目前該項(xiàng)技術(shù)尚不成熟,原因在于室外自然環(huán)境下運(yùn)動(dòng)圖像存在大量不確定性擾動(dòng),使得魯棒性、實(shí)時(shí)性及自適應(yīng)性強(qiáng)的道路理解算法開發(fā)起來十分困難。本文以京龍2號(hào)(C30)純電動(dòng)無人車項(xiàng)目為背景,圍繞道路理解中的關(guān)鍵技術(shù)——主導(dǎo)航標(biāo)識(shí)(車道線、虛擬道路中心線)、道路障礙物及輔導(dǎo)航標(biāo)識(shí)(交通標(biāo)志)的檢測(cè)與識(shí)別問題,從機(jī)器視覺的共性技術(shù)即視覺信號(hào)處理、圖像特征提取、圖像模式識(shí)別角度進(jìn)行算法改進(jìn)與算法融合,構(gòu)建出一套快速、魯棒、自適應(yīng)道路環(huán)境理解方法體系。頻率域多尺度特征提取、稀疏表示、基于特征匹配的模式識(shí)別是本文的技術(shù)主線。針對(duì)城區(qū)道路車道線的理解,提出了自校正閉環(huán)車道視覺檢測(cè)器架構(gòu),并基于該架構(gòu)提出了基于小波域多尺度邊緣特征和極角約束改進(jìn)型快速Hough變換的車道線檢測(cè)算法,進(jìn)一步提出了基于尺度自適應(yīng)Kalman濾波的車道線跟蹤方法。針對(duì)有陰影干擾車道的魯棒檢測(cè)難題,提出一種基于二維二進(jìn)小波分析的頻率域陰影干擾去除算法,該算法充分利用車道逆映射變換圖上車道線一般呈現(xiàn)為豎向平行線的圖像特點(diǎn),僅在分解后的多級(jí)垂直子圖上檢測(cè)車道線。針對(duì)虛擬道路中心線提取時(shí)遇到的陰影、裂紋等奇異信號(hào)造成的視覺算法不魯棒問題,以及圖像大數(shù)據(jù)實(shí)時(shí)處理難題,提出了單層小波包近似壓縮感知概念與算法,與自適應(yīng)遺傳算法優(yōu)化的圖像分割法相結(jié)合,構(gòu)建出一種實(shí)時(shí)道路理解算法系統(tǒng)。實(shí)驗(yàn)結(jié)果表明該方法在保持路面分割一致性及語義確定性方面優(yōu)于傳統(tǒng)方法,且實(shí)現(xiàn)了“路-非路”像素的自適應(yīng)二分類。為深層次理解道路,在上述算法基礎(chǔ)上進(jìn)一步提出了基于小波域語義樹Markov模型的道路建模及道路語義理解方法,采用有監(jiān)督RT-MRF模型進(jìn)行道路圖像序列語義分割,將道路圖像分割為具有語義邊界的區(qū)域,自主車通過跟蹤虛擬的道路中心線實(shí)現(xiàn)自主移動(dòng)。該方法解決了道路語義建模問題,填補(bǔ)了當(dāng)前道路視覺感知領(lǐng)域缺乏嚴(yán)謹(jǐn)數(shù)學(xué)模型的空白,使道路理解結(jié)果向更深的語義層次延伸。針對(duì)道路障礙物的檢測(cè)提出兩種方法。方法一采用Contourlet變換進(jìn)行圖像預(yù)處理,通過基于圖割的立體匹配算法獲取視差圖,進(jìn)而提取深度特征,通過自適應(yīng)Sobel算子提取邊緣特征,多特征融合后確定障礙物的尺寸及距離信息。方法二模擬人類視覺特點(diǎn),提出一種采用自適應(yīng)Hessian閾值控制特征稀疏度的顯著性視覺特征提取方法,并利用該特征實(shí)現(xiàn)動(dòng)態(tài)障礙物檢測(cè),算法能夠適用于晴天、陰雨天、傍晚、夜間等多種天氣狀況,魯棒性較強(qiáng)。最后,本文針對(duì)光照度變化、視角變化、遮擋、尺度變化等復(fù)雜條件下的交通標(biāo)志檢測(cè)與識(shí)別問題,提出了基于粗粒度H特征和顏色-形狀組合特征推理模型的由粗到細(xì)二步交通標(biāo)志檢測(cè)法,以及基于SURF特征優(yōu)化匹配的交通標(biāo)志識(shí)別法。
[Abstract]:Independent car embodies the control of science, robotics, cognitive science, multidisciplinary intelligent transportation, is the carrier, to explore new theory and new technology in the military, which has important application value in civil and scientific project. Visual understanding technology is based on the road environment since the main vehicle to full autonomy and practical the key, but the technology is not mature, the reason lies in the motion picture outdoor natural environment there are a lot of uncertainties, the robust, real-time and adaptive way of understanding it is very difficult to develop algorithms. This paper takes Beijing Dragon No. 2 (C30) of pure electric unmanned vehicle project as the background, around the key the main way to understand the navigation identification technology (virtual lane, the central line of the road), and coach road barriers (traffic signs) Airlines logo detection and identification of problems, from the common technology of machine vision or visual signal Image processing, feature extraction algorithm and image fusion algorithm of pattern recognition perspective, constructs a fast, robust, adaptive road environment understanding method system. The multi-scale feature extraction, frequency domain, sparse representation, pattern recognition based on feature matching technology is the main line of this article. According to the urban road lane understanding, put forward self correction loop Lane visual detector architecture and architecture based on the proposed traffic lane detection algorithm in wavelet domain multiscale edge and angle constraints improved fast Hough transform based on the proposed tracking Lane scale based on adaptive Kalman filtering method for robust detection problem of shadow interference lane, put forward a kind of frequency two dimensional wavelet domain shadow removal algorithm based on interference analysis, the algorithm makes full use of lane inverse mapping transformation graph on the line as a present The image characteristics of vertical parallel lines, only lane detection in vertical multistage decomposition of the sub graph. The virtual road centerline extraction algorithm of visual shadow, crack singular signals caused by the robust problem, and real-time image processing of large data problem, proposed single wavelet packet approximation concept and algorithm of compressed sensing. Combined with the image segmentation method of adaptive genetic algorithm optimization, construct a real-time road understanding system. The experimental results show that the method maintains the road segmentation consistency and semantic uncertainty is superior to the traditional method, and the realization of the "non adaptive classification of road - Lu two pixels. For deep understanding on the road, based on the above algorithm is further proposed to understand the method of road modeling and road semantic semantic tree in wavelet domain based on Markov model, using the supervised RT-MRF model road image sequence List of semantic segmentation, the road image segmentation with semantic boundary regions, autonomous vehicles by tracking the road center line of virtual realization of autonomous mobile. This method solves the problem of semantic modeling way to fill the blank of rigorous mathematical model of the road visual field, the road extends to the deeper semantic understanding results. According to the detection the road obstacles put forward two methods using Contourlet transform for image preprocessing, the graph cut stereo matching algorithm to obtain disparity map based on the extracted depth characteristics, through adaptive Sobel operator edge feature extraction, multi feature fusion to determine the size and distance information of obstacles. Two methods of simulating human vision the characteristics, this paper proposes an adaptive threshold control Hessian significant visual features extraction method using sparsity, and making use of the characteristics of dynamic Obstacle detection algorithm can be applied to a sunny day, rainy day, evening, night and other weather conditions, strong robustness. Finally, according to the change of illumination occlusion, viewpoint change, scale change, traffic signs under complicated conditions such as detection and identification of problems, put forward the coarse-grained H feature and color combination based on shape the characteristics of reasoning model from coarse to fine the two step traffic sign detection method, and the optimized SURF features of traffic sign recognition method based on matching.

【學(xué)位授予單位】：北京理工大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41

【共引文獻(xiàn)】

相關(guān)期刊論文 前4條

1 王一丁;徐超;;一種基于改良逆投影變換的道路斑馬線識(shí)別方法[J];北方工業(yè)大學(xué)學(xué)報(bào);2013年03期

2 周桑彥;李東新;;車輛檢測(cè)與跟蹤系統(tǒng)中道路檢測(cè)方法的研究[J];電子設(shè)計(jì)工程;2014年22期

3 魯斌;秦瑞;李慶;陳大鵬;;車載環(huán)視拼接方法的研究[J];計(jì)算機(jī)科學(xué);2013年09期

4 高浦s，

本文編號(hào)：1663488