本文選題：無人車 + 三維數(shù)據(jù)��； 參考：《浙江大學(xué)》2014年博士論文

【摘要】：無人車對行駛環(huán)境的感知和理解是保證其后續(xù)行為規(guī)劃正確的前提和基礎(chǔ),也是人工智能領(lǐng)域一直以來具有挑戰(zhàn)性的課題之一。通過車載三維傳感器,感知行駛環(huán)境,具有簡便、信息量豐富、探測精度高等優(yōu)點,尤其是64線激光雷達和雙目立體視覺傳感器,被越來越多的無人車三維感知系統(tǒng)所采用。三維信息與環(huán)境相關(guān)性強,具有很大的隨機性。與結(jié)構(gòu)化場景相比,室外非結(jié)構(gòu)化場景中無特定的人工標(biāo)記,物體的三維外形復(fù)雜多變,并且室外顛簸的路況,雜亂的植被也會給場景檢測理解帶來額外的困難。因此,研究無人車對非結(jié)構(gòu)化場景三維信息特征模型的構(gòu)建和處理,對擴展無人車系統(tǒng)的活動范圍、提高它對復(fù)雜和惡劣地形環(huán)境的適應(yīng)能力具有非常重要的意義。本文基于三維傳感器,研究了面向無人車的典型非結(jié)構(gòu)化場景理解問題,主要內(nèi)容及貢獻如下： 提出了64線激光雷達內(nèi)參標(biāo)定的方法以及外參自標(biāo)定的方法。通過分析激光發(fā)射系統(tǒng)的數(shù)學(xué)模型,放棄64線激光雷達內(nèi)參中距離誤差補償常量的通常做法,實現(xiàn)一個與反射距離成線性關(guān)系的變量的更為精密的補償。以不同距離的墻面為目標(biāo)物,對64線激光雷達內(nèi)參進行非線性優(yōu)化。對于64線激光雷達外參,將傳統(tǒng)實施復(fù)雜的一次性標(biāo)定過程分解為兩部分,實現(xiàn)了操作更為簡單的自標(biāo)定算法。第一步通過雷達坐標(biāo)系中的地面與實際地平面比對,求解出激光雷達相對于車體的俯仰角和側(cè)滾角；第二步讓無人車在具有柱狀物體(路燈桿等)的城市道路中行駛,匹配前后幀中柱狀物體在雷達坐標(biāo)系中航向角的以及平移的變化,與GPS記錄的車體航向角及平移變化做比對,求解出激光雷達相對于車體坐標(biāo)系的航向角以及平移。合并兩步驟求得的參數(shù)就能獲得準(zhǔn)確的激光雷達外參。 針對鄉(xiāng)村環(huán)境的感知理解。提出了基于馬爾科夫隨機場的路面分割算法。相比于柵格模式的道路分割,基于圖的道路分割檢測距離更遠、精度更高、更節(jié)省內(nèi)存資源；而傳統(tǒng)的基于圖的道路分割算法,僅利用單個三維點的特征,極易受到噪聲干擾,只能適用于平坦的城市道路而非顛簸起伏的鄉(xiāng)村環(huán)境道路。算法利用激光雷達掃描線在xoy平面上的幾何特性以及激光雷達原始數(shù)據(jù)結(jié)構(gòu)的特點,將掃描線分割為線段,通過分析線段的多個特征,構(gòu)建線段屬性的概率函數(shù),并且通過馬爾可夫隨機場和圖割的方式優(yōu)化最終分割的結(jié)果。通過實際數(shù)據(jù)序列實驗結(jié)果與現(xiàn)有算法結(jié)果的量化比較,表明本算法在鄉(xiāng)村環(huán)境道路情況下不僅道路分割精度高,而且穩(wěn)定性好。經(jīng)測試,本算法能夠在無人車平臺上實時運行。 針對植被散布環(huán)境,提出了基于多傳感器融合的的障礙物分類方法。首先將三維激光雷達數(shù)據(jù)、二維彩色相機數(shù)據(jù)融合,進行稀疏深度指導(dǎo)的超像素分割以及深度恢復(fù)算法,在迭代過程中,讓二維圖像分割的結(jié)果和三維深度數(shù)據(jù)相互指導(dǎo),提高算法的性能。然后提取局部的區(qū)域特征,包括三維點云局部統(tǒng)計特征、激光雷達強度特征,利用近紅外相機與彩色相機融合的歸一化差分植被指數(shù)等特征,組成多維的特征向量,采用有監(jiān)督的學(xué)習(xí)方式訓(xùn)練SVM分類器。在現(xiàn)實環(huán)境中的測試表明,多傳感器融合的分類方法提高了分類的準(zhǔn)確性,增加了遠距離物體分類的魯棒性。 針對未知復(fù)雜地形的感知理解,提出了一個從三維點云輸入到柵格通行性輸出的運算框架。在該框架下可以完成點云數(shù)據(jù)的濾波、多幀拼接、幀間匹配、點云恢復(fù)、點云數(shù)據(jù)柵格化、通行性分析以及障礙物聚類。首先針對無人車立體視覺系統(tǒng)三維重建后產(chǎn)生的噪聲,分別采用基于點云局部密度的算法去除外點,采用雙邊帶濾波器減小點云中的隨機噪聲。其次針對數(shù)據(jù)幀間匹配,采用經(jīng)KD-Tree的數(shù)據(jù)結(jié)構(gòu)加速計算的ICP進行點云匹配。針對點云恢復(fù),采用較為簡單的反距離平方和插值算法。在通行性分析中,以無人車車體大小為窗口,計算中心點的屬性：若窗口內(nèi)有任意兩柵格不僅階躍值大于閾值,而且柵格間梯度也大于坡度閾值,則標(biāo)記狀況中心柵格屬性為階躍障礙；將窗口內(nèi)所有柵格值用于擬合平面,計算坡度和粗糙度,根據(jù)通行性式計算通行代價。
[Abstract]:The perception and understanding of the driving environment by unmanned vehicles is the premise and foundation to ensure the correct follow-up behavior planning. It is also one of the challenging topics in the field of artificial intelligence. It is simple, rich in information and high detection precision through the three-dimensional sensor in vehicle, which has the advantages of simple, convenient, abundant information and high detection precision, especially 64 line laser radar and double. The stereoscopic vision sensor has been adopted by more and more unmanned vehicle 3D sensing systems. The three-dimensional information is strongly correlated with the environment and has great randomness. Compared with the structured scene, there are no specific artificial markers in the outdoor unstructured scene, the three-dimensional shape of the object is complicated and more complex, and the outdoors turbulence and the chaotic vegetation will also be found. It brings additional difficulties to the detection and understanding of the scene. Therefore, it is very important to study the construction and processing of the unstructured 3D information feature model for unstructured scenes, to extend the range of the unmanned vehicle system and to improve its adaptability to the complex and abominable terrain environment. The main contents and contributions of the typical unstructured scene understanding of human cars are as follows:
The calibration method of 64 line laser radar and the method of self calibration are proposed. By analyzing the mathematical model of the laser emission system and giving up the usual practice of compensating the constant of the distance error in the internal reference of the 64 line laser radar, a more precise compensation is realized for a variable with the linear relation of the reflection distance. The target, nonlinear optimization of the 64 line laser radar internal parameter. For the 64 line laser radar external parameter, the traditional implementation of the complicated one-time calibration process is decomposed into two parts, and a more simple self calibration algorithm is realized. The first step is to solve the laser radar relative to the vehicle by comparing the ground surface to the actual surface surface in the radar coordinate system. The pitch angle and the side roll angle of the body; the second step makes the unmanned vehicle run in the city road with a columnar object (the street lamp pole, etc.), matches the change of the navigation angle and the shift of the column shaped objects in the radar coordinate system before and after the frame, and compares the direction angle and the shift change of the car body recorded by the GPS, and solves the relative system of the laser radar relative to the car body coordinate system. The parameters obtained by merging the two steps can get accurate laser radar extrinsic parameters.
In view of the perception and understanding of the rural environment, a road segmentation algorithm based on Markov random field is proposed. Compared with the grid mode, the road segmentation based on the graph is far farther, more accurate, and more memory saving, while the traditional road segmentation algorithm based on graph only uses the characteristics of a single three-dimensional point, and is very easy to be subjected to. Noise interference can only be applied to a flat urban road rather than a bumpy country road. The algorithm uses the geometric characteristics of the laser radar scanning line on the xoy plane and the characteristics of the original data structure of the laser radar. The scanning line is divided into line segments, and the probability function of the line segment attribute is constructed by analyzing the multiple features of the line segment. The results of the final segmentation are optimized by Markov random field and graph cut. The results of the actual data sequence experiment and the existing algorithm results show that the algorithm not only has high road segmentation precision, but also has good stability. The algorithm can run on the unmanned vehicle platform in real time after testing.
An obstacle classification method based on multi-sensor fusion is proposed for the vegetation distribution environment. Firstly, the 3D laser radar data and two-dimensional color camera data are fused to carry out the super pixel segmentation and depth recovery algorithm guided by the sparse depth. In the iterative process, the results of the two dimensional image segmentation and the three-dimensional depth data are interacted with each other. To improve the performance of the algorithm, the local regional features are extracted, including the local statistical features of the three dimensional point cloud, the intensity feature of the laser radar, the feature vectors of the normalized difference vegetation index, such as the fusion of the near infrared camera and the color camera, and the multi-dimensional feature vectors, and the supervised learning method is used to train the SVM classifier. The test shows that the classification method of multi-sensor fusion improves the accuracy of classification and increases the robustness of remote object classification.
In view of the perception and understanding of unknown complex terrain, a framework of input from three dimensional point cloud to grid pass is proposed. Under this framework, the filtering of point cloud data, multi frame splicing, inter frame matching, point cloud recovery, point cloud data grid, traffic analysis and obstacle clustering can be completed. The noise generated by the three dimensional reconstruction is used to remove the external points based on the local density based algorithm of point cloud, and the random noise of Dian Yunzhong is reduced by a bilateral band filter. Secondly, the point cloud is matched by the KD-Tree data structure accelerated ICP for the matching of data frames. In the traffic analysis, the attribute of the center point is calculated with the size of the car body of unmanned vehicle as the window. If there is any two grid in the window not only the step value is greater than the threshold value, but also the gradient of the grid is greater than the gradient threshold, then the grid attribute of the mark state center is a step obstacle, and all the grid values within the window are used to fit the plane. Calculate the slope and roughness and calculate the passage cost according to the traffic pattern.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：U495;TP242

【參考文獻】

相關(guān)期刊論文 前6條

1 王宏,艾海舟,何克忠,張鈸;移動機器人體系結(jié)構(gòu)與系統(tǒng)設(shè)計[J];機器人;1993年01期

2 歐青立,何克忠;室外智能移動機器人的發(fā)展及其關(guān)鍵技術(shù)研究[J];機器人;2000年06期

3 孫振平,安向京,賀漢根;CITAVT-IV——視覺導(dǎo)航的自主車[J];機器人;2002年02期

4 于春和;劉濟林;;越野環(huán)境的三維地圖重建[J];南京理工大學(xué)學(xué)報(自然科學(xué)版);2007年02期

5 王春瑤;陳俊周;李煒;;超像素分割算法研究綜述[J];計算機應(yīng)用研究;2014年01期

6 楊飛;朱株;龔小謹;劉濟林;;基于三維激光雷達的動態(tài)障礙實時檢測與跟蹤[J];浙江大學(xué)學(xué)報(工學(xué)版);2012年09期

，

本文編號：2097407