【摘 要】
:
The current mainstream methods of loop closure detection in visual simultaneous localization and mapping (SLAM) are based on bag-of-words (BoW). However, traditional BoW-based approaches are strongly affected by changes in the appearance of the scene, whi
【机 构】
:
KeyLaboratoryofOptoelectronicInformationSensingandTechnology,SchoolofOpticalEngineering,ChongqingUni
【出 处】
:
OptoelectronicsLetters
论文部分内容阅读
The current mainstream methods of loop closure detection in visual simultaneous localization and mapping (SLAM) are based on bag-of-words (BoW). However, traditional BoW-based approaches are strongly affected by changes in the appearance of the scene, which leads to poor robustness and low precision. In order to improve the precision and robustness of loop closure detection, a novel approach based on stacked assorted auto-encoder (SAAE) is proposed. The traditional stacked auto-encoder is made up of multiple layers of the same autoencoder. Compared with the visual BoW model, although it can better extract the features of the scene image, the output feature dimension is high. The proposed SAAE is composed of multiple layers of denoising auto-encoder, convolutional auto-encoder and sparse auto- encoder, it uses denoising auto-encoder to improve the robustness of image features, convolutional auto-encoder to preserve the spatial information of the image, and sparse auto-encoder to reduce the dimensionality of image features. It is capable of extracting low to high dimensional features of the scene image and preserving the spatial local characteristics of the image, which makes the output features more robust. The performance of SAAE is evaluated by a comparison study using data from new college dataset and city centre dataset. The methodology proposed in this paper can effectively improve the precision and robustness of loop closure detection in visual SLAM.
其他文献
将半导体可饱和吸收体(SESAM)锁模技术与腔倒空技术结合,采用半导体端面抽运方式实现了具有高重复频率、大单脉冲能量的皮秒激光器的运转。从理论上分析了腔倒空锁模输出的机理,建立起腔倒空锁模激光器运行的物理图像,并对影响激光器倒空率的一些因素进行了研究。实验上,实现端面抽运NdYVO4晶体的SESAM连续锁模后,在锁模腔内插入BBO电光调制晶体,获得10 kHz腔倒空皮秒锁模脉冲输出。当抽运光功率为14.1 W时,输出锁模脉冲的单脉冲能量为6.5 μJ,脉冲宽度为10.4 ps。
We report a line-narrowed electro-optic periodically-poled-lithium-niobate (PPLN) Q-switched laser with intra-cavity optical parametric oscillation using a grazing-incidence grating, producing 8-ns, 5-\mu J pulses at 10-kHz repetition rate when pumped wi
咖啡是世界三大饮料之一,严格把控咖啡品质具有重大意义。以三个不同品种的咖啡豆为对象,利用太赫兹时域光谱技术结合化学计量学实现咖啡豆品种的快速鉴别。采用多种预处理方法减小实验误差,利用主成分分析(PCA)对光谱矩阵进行降维。建立偏最小二乘判别分析(PLS-DA)二分类模型和支持向量机(SVM)、反向传播神经网络(BPNN)、随机森林(RF)多分类判别模型。PLS-DA二分类模型的定性判别效果较为理想,总正确率可达98%;在多分类模型中,基于基线校正建立的SVM模型的效果最佳,总正确率达到98%。本研究表明利
本文对适用于对撞脉冲锁模的环型谐振腔进行了普遍地、严格地讨论.第一次给出了严格的解析解.
Traditional speckle fringe patterns by electronic speckle pattern interferometry (ESPI) are inherently noisy and of limited visibility, so denoising is the key problem in ESPI. We present the variational denoising method for ESPI. This method transforms t
A single-mode polymer optical fiber (POF) with highly photosensitive core doped with benzil dimethyl ketal (BDK) is fabricated and used for writing Bragg grating through the two-beam interference method. The Bragg wavelength of the grating is about 1570 n
本文提出一种基于氧化石墨烯(Graphene Oxide,GO)微腔的光纤多频法布里-珀罗(Fabry-Perot,FP)声振动传感器。该传感器使用单模光纤端面和GO薄膜构成微米级尺度的FP干涉微腔结构,采用液相法制备GO薄膜并将其作为声振动信号的敏感材料,实现对外界声振动信号的探测。通过控制和优化FP微腔长度可以获得消光比最大的干涉光谱,并对该传感器施加不同频率的单频、双频和三频声振动信号以测试其对多频信号的响应能力。实验结果表明,该传感器具有较高的信噪比(Signal to Noise Ratio,S
针对GaAs基和InP基材料的波长可调谐垂直腔面发射激光器(VCSEL)中微机电系统(MEMS)应力集中引起结构损坏的问题开展研究。设计了蝴蝶结状MEMS悬臂结构, 在保证最大位移不变的情况下, 降低了悬臂固定端所受的米塞斯应力, 提高了器件的可靠性。采用COMSOL软件对蝴蝶结状悬臂结构的各项参数对力学特性的影响进行了优化与分析。结果表明: 优化后的蝴蝶结状MEMS悬臂结构固定端的最大米塞斯应力相比于等截面状悬臂结构最大降低了64%, 对于GaAs基材料的蝴蝶结状MEMS波长可调谐VCSEL自由光谱范围
为确定边缘扩散函数(ESF)最优提取方法,对基于三次样条插值与SG滤波的四种提取方法进行分析比较,包括Spline、Spline SG、MSG及SASG方法。分别通过仿真图像实验与实际遥感图像实验,分析了图像仅存在加性噪声以及图像中同时存在加性噪声与白噪声时,四种方法的有效性。实验结果表明,Spline与Spline SG方法的效果几乎完全一致,仿真实验中,二者线扩散函数(LSF)和调制传递函数(