改進(jìn)的單目視覺實(shí)時(shí)定位與測(cè)圖方法
發(fā)布時(shí)間：2018-10-15 13:06
【摘要】：針對(duì)經(jīng)典單目實(shí)時(shí)定位與測(cè)圖(SLAM)采用卡爾曼濾波(EKF)濾波和FAST特征角點(diǎn)所存在的非線性誤差和魯棒性較差的問題,提出了一種改進(jìn)的單目視覺實(shí)時(shí)定位與測(cè)圖方法。該方法采用相機(jī)中心的迭代EKF(IEKF)濾波方法,將特征點(diǎn)在當(dāng)前相機(jī)坐標(biāo)系下表達(dá),并在線性化展開點(diǎn)附近迭代更新,不斷逼近最優(yōu)位置,從而最小化線性化誤差;針對(duì)特征點(diǎn)跟蹤的魯棒性、高效性及分布不均的問題,選用具有尺度和旋轉(zhuǎn)不變性,且探測(cè)和匹配效率更高的ORB特征作為特征角點(diǎn),并采用一種由探測(cè)到篩選階段的整體網(wǎng)格化處理方法;另外,采用特征點(diǎn)逆深度參數(shù)化方法,避免了因深度信息未知而導(dǎo)致的局部地圖初始化錯(cuò)誤問題,并采用1點(diǎn)隨機(jī)抽樣一致方法(RANSAC)濾波更新方法剔除錯(cuò)誤的特征匹配,保證濾波估計(jì)的準(zhǔn)確與穩(wěn)定。實(shí)驗(yàn)采用外符合精度對(duì)算法進(jìn)行評(píng)價(jià),結(jié)果表明:新方法具有更強(qiáng)的魯棒性,絕對(duì)定位精度提升至2.24 m,誤差軌跡比提升至1.3%,且滿足實(shí)時(shí)性要求,是一種實(shí)用性較強(qiáng)的單目視覺實(shí)時(shí)定位與測(cè)圖方法。
[Abstract]:Aiming at the problem of poor nonlinear error and robustness of classical monocular real-time location and mapping (SLAM) using Kalman filter (EKF) filter and FAST feature corner, an improved monocular vision real-time location and mapping method is proposed. The method uses the camera center iterative EKF (IEKF) filtering method to express the feature points in the current camera coordinate system, and iteratively updates near the linearization expansion point to continuously approximate the optimal position, thus minimizing the linearization error. Aiming at the problem of robustness, high efficiency and uneven distribution of feature point tracking, ORB features with scale and rotation invariance and higher detection and matching efficiency are selected as feature corners. In addition, the method of inverse depth parameterization of feature points is used to avoid the problem of local map initialization error caused by unknown depth information. The one-point random sampling consistent method (RANSAC) filter updating method is used to eliminate the wrong feature matching to ensure the accuracy and stability of the filter estimation. The experimental results show that the new method is more robust, the absolute positioning accuracy is increased to 2.24 m, the error locus ratio is increased to 1.3%, and the real-time requirement is satisfied. It is a practical and practical method for real-time positioning and mapping of monocular vision.
【作者單位】： 信息工程大學(xué)導(dǎo)航與空天目標(biāo)工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(41274014,41501491)項(xiàng)目資助
【分類號(hào)】：TN713;TP391.41
，
本文編號(hào)：2272644
[Abstract]:Aiming at the problem of poor nonlinear error and robustness of classical monocular real-time location and mapping (SLAM) using Kalman filter (EKF) filter and FAST feature corner, an improved monocular vision real-time location and mapping method is proposed. The method uses the camera center iterative EKF (IEKF) filtering method to express the feature points in the current camera coordinate system, and iteratively updates near the linearization expansion point to continuously approximate the optimal position, thus minimizing the linearization error. Aiming at the problem of robustness, high efficiency and uneven distribution of feature point tracking, ORB features with scale and rotation invariance and higher detection and matching efficiency are selected as feature corners. In addition, the method of inverse depth parameterization of feature points is used to avoid the problem of local map initialization error caused by unknown depth information. The one-point random sampling consistent method (RANSAC) filter updating method is used to eliminate the wrong feature matching to ensure the accuracy and stability of the filter estimation. The experimental results show that the new method is more robust, the absolute positioning accuracy is increased to 2.24 m, the error locus ratio is increased to 1.3%, and the real-time requirement is satisfied. It is a practical and practical method for real-time positioning and mapping of monocular vision.
【作者單位】： 信息工程大學(xué)導(dǎo)航與空天目標(biāo)工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(41274014,41501491)項(xiàng)目資助
【分類號(hào)】：TN713;TP391.41
，
本文編號(hào)：2272644
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2272644.html
最近更新
教材專著
