《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 一種基于實(shí)例分割和點(diǎn)云配準(zhǔn)的六維位姿估計(jì)方法
一種基于實(shí)例分割和點(diǎn)云配準(zhǔn)的六維位姿估計(jì)方法
信息技術(shù)與網(wǎng)絡(luò)安全
侯大偉
(中國(guó)科學(xué)技術(shù)大學(xué) 信息科學(xué)技術(shù)學(xué)院,,安徽 合肥230026)
摘要: 本文提出一種基于Mask R-CNN實(shí)例分割網(wǎng)絡(luò)和Super4PCS點(diǎn)云配準(zhǔn)算法來(lái)估計(jì)物體六維姿態(tài)的方法,。通過(guò)目標(biāo)點(diǎn)云與已知位姿的參考點(diǎn)云進(jìn)行配準(zhǔn),,可以獲取目標(biāo)的六維姿態(tài),。但實(shí)際中往往采用三維設(shè)備掃描目標(biāo)的整體環(huán)境,生成的點(diǎn)云數(shù)量龐大,,直接作為源點(diǎn)云與參考點(diǎn)云配準(zhǔn)時(shí),,會(huì)由于候選集較多從而導(dǎo)致運(yùn)算時(shí)間太長(zhǎng),因此本文先對(duì)目標(biāo)實(shí)例分割處理后再配準(zhǔn):首先,,利用深度相機(jī)獲取整體環(huán)境的RGB-D圖,,其次利用Mask R-CNN模型將把目標(biāo)分割出來(lái),并將分割的目標(biāo)RGB-D圖轉(zhuǎn)化為點(diǎn)云圖,,利用Super4PCS點(diǎn)云配準(zhǔn)算法與參考點(diǎn)云進(jìn)行配準(zhǔn),,最終得到目標(biāo)的六維位姿。在自制作的數(shù)據(jù)集上進(jìn)行了驗(yàn)證,,對(duì)比分割前后的四組實(shí)驗(yàn),,時(shí)間降低率約為60%-80%,有效證明了本方法的可行性,。
中圖分類號(hào): TP391
文獻(xiàn)標(biāo)識(shí)碼: A
DOI: 10.19358/j.issn.2096-5133.2021.06.010
引用格式: 侯大偉. 一種基于實(shí)例分割和點(diǎn)云配準(zhǔn)的六維位姿估計(jì)方法[J].信息技術(shù)與網(wǎng)絡(luò)安全,,2021,40(6):56-61.
6D pose estimation based on instance segmentation and point cloud registration
Hou Dawei
(School of Information Science and Technology,,University of Science and Technology of China,,Hefei 230026,China)
Abstract: This paper proposes a method to estimate the six-dimensional pose of an object based on the Mask R-CNN instance segmentation network and the Super4PCS point cloud registration algorithm. The six-dimensional pose of the target can be generally estimated by registering the point cloud of the environment and the target. The number of point clouds generated by the scanning the overall environment with 3D equipment is huge, the calculation time will be too long when directly using the source point cloud to register the reference point cloud. Therefore, this article will divide the target before registration. Firstly, we obtain the RGB-D map of the overall environment by the depth-sensing camera. Secondly, we use the Mask-R CNN model to segment the target, after that we convert the RGB-D map of the segmented target into a point cloud image and complete the point cloud registration of the reference and the segmented target through Super4PCS algorithm. We finally obtain the six-dimensional pose of the target and compare the four sets of experiments based on our dataset. The results show that the time reduction rate is about 60%-80%, which effectively illustrates the feasibility of our method.
Key words : 6D pose estimation,;Mask R-CNN instance segmentation;Super4PCS point cloud registration

0 引言

點(diǎn)云配準(zhǔn)是三維重建,、工業(yè)測(cè)量,、機(jī)器人抓取等方面的一種常見方法,目標(biāo)是將不同視角下點(diǎn)云拼接成一塊完整的點(diǎn)云數(shù)據(jù),。隨著深度相機(jī)的廣泛應(yīng)用,,研究人員可以便捷地獲取三維空間的點(diǎn)云數(shù)據(jù),用以估計(jì)物體的六維位姿,。圖1(a)和圖1(b)是在不同視角下的存在交集的兩片點(diǎn)云,,不斷地調(diào)整交集部分的點(diǎn)云直到基本重疊,,最終兩片點(diǎn)云拼接為一個(gè)整體(圖1(c))。

以上兩片點(diǎn)云配準(zhǔn)的過(guò)程,,本質(zhì)上得到的是兩片點(diǎn)云之間相對(duì)位姿的變換矩陣,。假設(shè)其中一片點(diǎn)云參考目標(biāo),即相對(duì)世界坐標(biāo)系的位姿參數(shù)均已知,,便可推理得到另一片點(diǎn)云的位姿,,從而實(shí)現(xiàn)目標(biāo)點(diǎn)云的位姿估計(jì)。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000003601




作者信息:

侯大偉

(中國(guó)科學(xué)技術(shù)大學(xué) 信息科學(xué)技術(shù)學(xué)院,,安徽 合肥230026)


此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。