基于三維激光雷達(dá)的動(dòng)態(tài)車輛檢測(cè)與跟蹤
發(fā)布時(shí)間：2019-06-13 14:28
【摘要】：物體檢測(cè)與跟蹤是移動(dòng)機(jī)器人領(lǐng)域中的核心問題之一。作為物體檢測(cè)與跟蹤的重要組成部分,動(dòng)態(tài)車輛檢測(cè)與跟蹤對(duì)自主車環(huán)境感知能力的提高有重要作用。本文以自主車在城市環(huán)境中自主導(dǎo)航為背景,重點(diǎn)研究了基于三維激光雷達(dá)的動(dòng)態(tài)車輛檢測(cè)與跟蹤問題。論文的主要成果和創(chuàng)新點(diǎn)如下:(1)提出了兩種新的地面分割算法對(duì)各種地形的三維激光雷達(dá)數(shù)據(jù)進(jìn)行分割,分別是:基于區(qū)域高斯過程回歸的地面分割算法和基于分塊遞歸高斯過程回歸的實(shí)時(shí)地面分割算法�；趨^(qū)域高斯過程回歸的地面分割算法主要應(yīng)用于三維笛卡爾坐標(biāo)柵格地圖,該算法使用帶有稀疏協(xié)方差函數(shù)的二維高斯過程回歸直接對(duì)所有柵格單元中高度最低的三維點(diǎn)進(jìn)行地面建模。在公開的波士頓數(shù)據(jù)庫上,該算法地面分割的準(zhǔn)確率達(dá)到97.90%。基于分塊遞歸高斯過程回歸的實(shí)時(shí)地面分割算法將在三維笛卡爾坐標(biāo)柵格地圖中復(fù)雜的、大尺度的二維地面分割問題分解為極坐標(biāo)柵格地圖中的多個(gè)低復(fù)雜度的一維回歸問題,對(duì)于極坐標(biāo)柵格地圖的每個(gè)扇形塊,分別采用帶有非靜態(tài)協(xié)方差函數(shù)的一維遞歸高斯過程回歸算法對(duì)相應(yīng)區(qū)域內(nèi)的局部地面進(jìn)行建模。在同樣的數(shù)據(jù)庫上該算法的準(zhǔn)確率為97.67%,同時(shí)還能夠滿足自主車所必須的實(shí)時(shí)性要求。(2)提出了一種基于迭代高斯過程回歸的道路邊界檢測(cè)算法來獲取自主車的感興趣區(qū)域。該算法以三維激光雷達(dá)的每一條掃描線為處理單元提取其中的特征點(diǎn),然后采用迭代高斯過程回歸算法根據(jù)提取的特征點(diǎn)自動(dòng)對(duì)直線或曲線道路邊界進(jìn)行建模。本文提出的道路邊界檢測(cè)算法在滿足檢測(cè)精度的情況下能夠檢測(cè)到離自主車50米遠(yuǎn)的道路邊界。為了定量地驗(yàn)證該道路邊界檢測(cè)算法的性能,本文手工標(biāo)記了一個(gè)基于三維激光雷達(dá)的道路邊界數(shù)據(jù)庫。在該數(shù)據(jù)庫上使用本文提出的基于迭代高斯過程回歸的道路邊界檢測(cè)算法,左右道路邊界的正檢率分別達(dá)到 78.74%和 81.96%。(3)提出了一種新的全局柱坐標(biāo)直方圖特征用于在城市環(huán)境進(jìn)行車輛識(shí)別。該特征以感興趣區(qū)域內(nèi)每個(gè)物體的中心為原點(diǎn),通過引入全局坐標(biāo)系來克服物體繞z軸旋轉(zhuǎn)的不變性,并將柱形支持域內(nèi)的所有三維點(diǎn)按其柱坐標(biāo)進(jìn)行劃分,構(gòu)建三維直方圖。在悉尼城市物體數(shù)據(jù)庫和我們整理、標(biāo)記的數(shù)據(jù)集上進(jìn)行車輛識(shí)別的ROC曲線驗(yàn)證了新的全局柱坐標(biāo)直方圖特征在車輛識(shí)別上的優(yōu)異性能。(4)提出了一種新的基于似然場(chǎng)模型的動(dòng)態(tài)車輛檢測(cè)與跟蹤算法。該算法首先使用我們提出的基于似然場(chǎng)的車輛觀測(cè)模型結(jié)合改進(jìn)的Scaling Series算法來估計(jì)感興趣區(qū)域內(nèi)各個(gè)車輛的初始姿態(tài)。在動(dòng)態(tài)車輛檢測(cè)階段,本文改進(jìn)了一種基于二維虛擬幀的三維激光雷達(dá)數(shù)據(jù)表示方式,采用該表示方式的動(dòng)態(tài)車輛檢測(cè)算法能夠檢測(cè)到感興趣區(qū)域內(nèi)在xy平面完全被其它物體遮擋,但仍能夠被三維激光雷達(dá)感知到的動(dòng)態(tài)車輛;在跟蹤階段,本文提出了一種新的基于貝葉斯濾波器的變尺寸車輛跟蹤算法,由于引入了不動(dòng)點(diǎn),該跟蹤算法不僅能在動(dòng)態(tài)背景場(chǎng)景中更新目標(biāo)車輛的姿態(tài)和速度,而且能夠在跟蹤過程中根據(jù)所關(guān)聯(lián)的觀測(cè)數(shù)據(jù)自動(dòng)更新目標(biāo)車輛的尺寸。在公開的KITTI數(shù)據(jù)庫和在城市、高速公路環(huán)境采集的激光雷達(dá)數(shù)據(jù)上的定量和定性實(shí)驗(yàn)都驗(yàn)證了本文提出的動(dòng)態(tài)車輛檢測(cè)與跟蹤算法的性能。以上研究成果已經(jīng)成功應(yīng)用于本實(shí)驗(yàn)室的自主車"開路雄師",該自主車在2015年第七屆中國(guó)智能車"未來挑戰(zhàn)賽"中獲得了第三名。
[Abstract]:Object detection and tracking is one of the core problems in the field of mobile robots. As an important part of object detection and tracking, dynamic vehicle detection and tracking plays an important role in improving the environment-sensing ability of autonomous vehicle. This paper focuses on the dynamic vehicle detection and tracking problem based on three-dimensional lidar in the background of autonomous navigation in the urban environment. The main achievements and innovation points of the paper are as follows: (1) Two new ground segmentation algorithms are proposed to divide the three-dimensional lidar data of various terrain, respectively: A ground segmentation algorithm based on regional Gaussian process regression and a real-time ground segmentation algorithm based on block recursive Gaussian process regression. The terrain segmentation algorithm based on the regional Gaussian process regression is mainly applied to a three-dimensional Cartesian coordinate grid map, which uses a two-dimensional Gaussian process regression with a sparse covariance function to directly model the three-dimensional points with the lowest height in all the grid cells. The accuracy of the algorithm is 97.90% on the open Boston database. The real-time ground segmentation algorithm based on the block recursive Gaussian process regression is used for decomposing a complex and large-scale two-dimensional ground segmentation problem in a three-dimensional Cartesian coordinate grid map into a plurality of low-complexity one-dimensional regression problems in a polar coordinate grid map, For each sector of the polar coordinate grid map, a one-dimensional recursive Gaussian process regression algorithm with a non-static covariance function is used to model the local ground in the corresponding region. The accuracy of the algorithm is 97.67% on the same database, and the real-time requirement of the autonomous vehicle can be met. (2) A road boundary detection algorithm based on the iterative Gaussian process regression is proposed to obtain the region of interest of the autonomous vehicle. The method uses each scanning line of the three-dimensional laser radar as the processing unit to extract the characteristic points, and then uses the iterative Gaussian process regression algorithm to automatically model the straight line or the curve road boundary according to the extracted feature points. The road boundary detection algorithm proposed in this paper can detect the road boundary which is 50 meters away from the autonomous vehicle when the detection accuracy is satisfied. In order to quantitatively verify the performance of the road boundary detection algorithm, a road boundary database based on a three-dimensional laser radar is manually marked. The road boundary detection algorithm based on the iterative Gaussian process regression is used in the database, and the positive rate of the left and right road boundary is 78.74% and 81.96%, respectively. (3) A new global column coordinate histogram is proposed for vehicle identification in urban environment. The characteristic takes the center of each object in the region of interest as the origin, overcomes the invariance of the rotation of the object around the z-axis by introducing a global coordinate system, and divides all three-dimensional points in the cylindrical support domain according to the column coordinates to construct a three-dimensional histogram. The ROC curve of vehicle identification on the database of the city object in Sydney and the data set that we have sorted and marked verifies the excellent performance of the new global column coordinate histogram feature on vehicle identification. (4) A new dynamic vehicle detection and tracking algorithm based on the likelihood field model is proposed. The algorithm first uses the likelihood-based vehicle observation model proposed by us to combine the improved scaling series algorithm to estimate the initial attitude of each vehicle in the region of interest. in that dynamic vehicle detection stage, the invention improve a three-dimensional laser radar data representation mode based on a two-dimensional virtual frame, but still can be perceived by the three-dimensional laser radar; in the tracking phase, a novel variable-size vehicle tracking algorithm based on a Bayesian filter is proposed, The tracking algorithm can not only update the attitude and speed of the target vehicle in the dynamic background scene, but also can automatically update the size of the target vehicle according to the associated observation data during the tracking process. The performance of the dynamic vehicle detection and tracking algorithm presented in this paper is verified by the quantitative and qualitative experiments on the open KITTI database and the lidar data collected in the city and the highway environment. The above research results have been successfully applied to the autonomous vehicle "open-circuit male" of the laboratory, and the independent vehicle has obtained the third place in the first "future competition" of the 7th China Intelligent Vehicle in 2015.
【學(xué)位授予單位】：國(guó)防科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：U495;TN958.98
，
本文編號(hào)：2498583
[Abstract]:Object detection and tracking is one of the core problems in the field of mobile robots. As an important part of object detection and tracking, dynamic vehicle detection and tracking plays an important role in improving the environment-sensing ability of autonomous vehicle. This paper focuses on the dynamic vehicle detection and tracking problem based on three-dimensional lidar in the background of autonomous navigation in the urban environment. The main achievements and innovation points of the paper are as follows: (1) Two new ground segmentation algorithms are proposed to divide the three-dimensional lidar data of various terrain, respectively: A ground segmentation algorithm based on regional Gaussian process regression and a real-time ground segmentation algorithm based on block recursive Gaussian process regression. The terrain segmentation algorithm based on the regional Gaussian process regression is mainly applied to a three-dimensional Cartesian coordinate grid map, which uses a two-dimensional Gaussian process regression with a sparse covariance function to directly model the three-dimensional points with the lowest height in all the grid cells. The accuracy of the algorithm is 97.90% on the open Boston database. The real-time ground segmentation algorithm based on the block recursive Gaussian process regression is used for decomposing a complex and large-scale two-dimensional ground segmentation problem in a three-dimensional Cartesian coordinate grid map into a plurality of low-complexity one-dimensional regression problems in a polar coordinate grid map, For each sector of the polar coordinate grid map, a one-dimensional recursive Gaussian process regression algorithm with a non-static covariance function is used to model the local ground in the corresponding region. The accuracy of the algorithm is 97.67% on the same database, and the real-time requirement of the autonomous vehicle can be met. (2) A road boundary detection algorithm based on the iterative Gaussian process regression is proposed to obtain the region of interest of the autonomous vehicle. The method uses each scanning line of the three-dimensional laser radar as the processing unit to extract the characteristic points, and then uses the iterative Gaussian process regression algorithm to automatically model the straight line or the curve road boundary according to the extracted feature points. The road boundary detection algorithm proposed in this paper can detect the road boundary which is 50 meters away from the autonomous vehicle when the detection accuracy is satisfied. In order to quantitatively verify the performance of the road boundary detection algorithm, a road boundary database based on a three-dimensional laser radar is manually marked. The road boundary detection algorithm based on the iterative Gaussian process regression is used in the database, and the positive rate of the left and right road boundary is 78.74% and 81.96%, respectively. (3) A new global column coordinate histogram is proposed for vehicle identification in urban environment. The characteristic takes the center of each object in the region of interest as the origin, overcomes the invariance of the rotation of the object around the z-axis by introducing a global coordinate system, and divides all three-dimensional points in the cylindrical support domain according to the column coordinates to construct a three-dimensional histogram. The ROC curve of vehicle identification on the database of the city object in Sydney and the data set that we have sorted and marked verifies the excellent performance of the new global column coordinate histogram feature on vehicle identification. (4) A new dynamic vehicle detection and tracking algorithm based on the likelihood field model is proposed. The algorithm first uses the likelihood-based vehicle observation model proposed by us to combine the improved scaling series algorithm to estimate the initial attitude of each vehicle in the region of interest. in that dynamic vehicle detection stage, the invention improve a three-dimensional laser radar data representation mode based on a two-dimensional virtual frame, but still can be perceived by the three-dimensional laser radar; in the tracking phase, a novel variable-size vehicle tracking algorithm based on a Bayesian filter is proposed, The tracking algorithm can not only update the attitude and speed of the target vehicle in the dynamic background scene, but also can automatically update the size of the target vehicle according to the associated observation data during the tracking process. The performance of the dynamic vehicle detection and tracking algorithm presented in this paper is verified by the quantitative and qualitative experiments on the open KITTI database and the lidar data collected in the city and the highway environment. The above research results have been successfully applied to the autonomous vehicle "open-circuit male" of the laboratory, and the independent vehicle has obtained the third place in the first "future competition" of the 7th China Intelligent Vehicle in 2015.
【學(xué)位授予單位】：國(guó)防科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：U495;TN958.98
，
本文編號(hào)：2498583
本文鏈接：http://sikaile.net/shoufeilunwen/xxkjbs/2498583.html
最近更新
教材專著
