音频感知哈希闭环检测的无人机仿生声呐SLAM算法研究
|
摘要
针对基于SLAM技术无人机在特定高度下构建二维经历图的优化问题,在RatSLAM的基础上,采用仿生声呐系统代替视觉传感器的BatSLAM模型和音频感知哈希闭环检测,实现在暗光条件下的二维经历图优化。BatSLAM模型通过绝对差值和(SAD)图像处理方法来进行仿生声纳模板的更新,此方法仅仅判断二幅耳蜗图外观是否一致,不存在几何处理和特征提取。由于耳蜗图在获取和传输过程中会产生各类噪音,相同位置获得的耳蜗图具有一定的差异,会导致构建的经历图失真。本文在BatSLAM的基础上,使用音频感知哈希算法对耳蜗图进行特征提取,并进行闭环检测。改进后的算法不仅考虑到外观,而且考虑到相邻频带间的能量差异,通过提高闭环检测准确率,来改善经历图的失真问题。仿真实验表明:采用基于音频感知哈希闭环检测的BatSLAM模型,不仅实现了无人机特定高度和暗光条件下二维经历图的构建,而且提高了闭环检测准确率,从而改善经历图的失真问题,实现经历图的优化。
Aiming at the problem of constructing two-dimensional empirical graph based on SLAM technology at certain heights,on the basis of RatSLAM, using the bionic sonar system to replace the visual sensor's BatSLAM mode and audio perceptual hash closed-loop detection, realizing two-dimentional empirical graph optimization under dark conditions. The BatSLAM model uses Sum of Absolute Difference(SAD) image processing methods to update the bionic sonar template. This method only judges whether the appearance of the two cochlear images is consistent, and does not have geometric processing and feature extraction. Because the cochlear images produce various noises during the acquisition and transmission, There are some differences in cochlear maps obtained at the same position. which can lead to the distortion of the constructed empirical map. This article is based on BatSLAM, The audio perceptual hash algorithm is used to extract features of cochlea,and according to closed-loop detection. The improved algorithm not only considers the appearance, but also considers the energy difference between adjacent bands. By improving the accuracy of closed-loop detection, to improve the experience map of the distortion problem. Simulation experiment shows,the BatSLAM model based on audio perceptual hash closed-loop detection is adopted, it not only realizes the construction of two-dimensional experience map under certain height and dark conditions of UAV, but also improves the accuracy of the closed-loop detection, improving the experience map of the distortion problem and implementing the optimization of experience graph.
Aiming at the problem of constructing two-dimensional empirical graph based on SLAM technology at certain heights,on the basis of RatSLAM, using the bionic sonar system to replace the visual sensor's BatSLAM mode and audio perceptual hash closed-loop detection, realizing two-dimentional empirical graph optimization under dark conditions. The BatSLAM model uses Sum of Absolute Difference(SAD) image processing methods to update the bionic sonar template. This method only judges whether the appearance of the two cochlear images is consistent, and does not have geometric processing and feature extraction. Because the cochlear images produce various noises during the acquisition and transmission, There are some differences in cochlear maps obtained at the same position. which can lead to the distortion of the constructed empirical map. This article is based on BatSLAM, The audio perceptual hash algorithm is used to extract features of cochlea,and according to closed-loop detection. The improved algorithm not only considers the appearance, but also considers the energy difference between adjacent bands. By improving the accuracy of closed-loop detection, to improve the experience map of the distortion problem. Simulation experiment shows,the BatSLAM model based on audio perceptual hash closed-loop detection is adopted, it not only realizes the construction of two-dimensional experience map under certain height and dark conditions of UAV, but also improves the accuracy of the closed-loop detection, improving the experience map of the distortion problem and implementing the optimization of experience graph.
引文
[1]MUR-ARTAL R, MONTIEL J M M, TARDóS J D. ORBSLAM:a versatile and accurate monocular SLAM system[J]. IEEE transactions on robotics, 2015, 31(5):1147–1163.
[2]HUANG G P, MOURIKIS A I, ROUMELIOTIS S I. A quadratic-complexity observability-constrained unscented Kalman filter for SLAM[J]. IEEE transactions on robotics,2013, 29(5):1226–1243.
[3]张凤,黄陆君,袁帅,等. NLOS环境下基于EKF的移动机器人定位研究[J].控制工程, 2015, 22(1):14–19.ZHANG Feng, HUANG Lujun, YUAN Shuai, et al. Reach on robot localization based on EKF in NLOS environment[J]. Control engineering of China, 2015, 22(1):14–19.
[4]刘卫华,王希彬,周强.基于容积粒子滤波的无人机FastSLAM算法研究[J].系统仿真技术, 2014, 10(3):234–238.LIU Weihua, WANG Xibin, ZHOU Qiang. FastSLAM algorithm based on cubature particle filtering algorithm for UAV[J]. System simulation technology, 2014, 10(3):234–238.
[5]丛楚滢,王从庆,丁臻极,等.一种小型无人机的FastSLAM算法[J].华中科技大学学报(自然科学版), 2015,43(S1):420–423.CONG Chuying, WANG Congqing, DING Zhenji, et al. A FastSLAM algorithm for small unmanned aerial vehicle[J].Journal of Huazhong university of science and technology(nature science edition), 2015, 43(S1):420–423.
[6]吕品,赖际舟,杨天雨,等.基于气动模型辅助的四旋翼飞行器室内自主导航方法[J].航空学报, 2015, 36(4):1275–1284.LYU Pin, LAI Jizhou, YANG Tianyu, et al. Autonomous navigation method aided by aerodynamics model for an indoor quadrotor[J]. Acta aeronautica et astronautica sinica,2015, 36(4):1275–1284.
[7]蒙山,唐文名.单目SLAM直线匹配增强平面发现方法[J].北京航空航天大学学报, 2017, 43(4):660–666.MENG Shan, TANG Wenming. Monocular SLAM plane discovery method enhanced by line segments matching[J].Journal of Beijing university of aeronautics and astronsutics, 2017, 43(4):660–666.
[8]余小欢,韩波,张宇,等.基于双目视觉的微型无人机室内三维地图构建[J].信息与控制, 2014, 43(4):392–397.YU Xiaohuan, HAN Bo, ZHANG Yu, et al. Binocular stereo vision based 3D mapping for micro aerial vehicles in an indoor environment[J]. Information and control, 2014,43(4):392–397.
[9]吕科,施泽南,李一鹏.微型无人机视觉定位与环境建模研究[J].电子科技大学学报, 2017, 46(3):543–548.LüKe, SHI Zenan, LI Yipeng. Visual localization and environment mapping for micro aerial vehicles[J]. Journal of university of electronic science and technology of China,2017, 46(3):543–548.
[10]王国胜,郭峰,刘峰.无人飞行器视觉SLAM特征检测和匹配算法研究[J].计算机测量与控制, 2015, 23(7):2453–2455.WANG Guosheng, GUO Feng, LIU Feng. Research on feature detection and matching algorithm of unmanned aerial vehicles visual SLAM[J]. Computer measurement&control, 2015, 23(7):2453–2455.
[11]王闯,卢健,黄杰. AUV同时定位与跟踪算法研究[J].西安工程大学学报, 2014, 28(5):556–562.WANG Chuang, LU Jian, HUANG Jie. Algorithms research of simultaneous localization and tracking for AUVs[J]. Journal of Xi’an polytechnic university, 2014,28(5):556–562.
[12]STECKEL J, PEREMANS H. Spatial sampling strategy for a 3D sonar sensor supporting BatSLAM[C]//Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Hamburg, Germany, 2015:723–728.
[13]TUBMAN R, POTGIETER J, ARIF K M. Efficient robotic SLAM by fusion of RatSLAM and RGBD-SLAM[C]//Proceedings of the 201623rd International Conference on Mechatronics and Machine Vision in Practice. Nanjing,China, 2016:1–6.
[14]STECKEL J, PEREMANS H. BatSLAM:simultaneous localization and mapping using biomimetic sonar[J].PLoS One, 2013, 8(1):e54076.
[15]YU Hongshan, ZHANG Yuan, WANG Yaonan, et al.Fast and robust frontier line segment extracting method based on FCM for robot exploration[C]//Proceedings of2013 Chinese Automation Congress. Changsha, China,2013:685–690.
[16]王伟,陈志高,孟宪凯,等.基于熵的音频指纹检索技术研究与实现[J].计算机科学, 2017, 44(S1):551–556.WANG Wei, CHEN Zhigao, MENG Xiankai, et al. Research and implementation of identifying music through performances using entropy based audio-fingerprint[J].Computer science, 2017, 44(S1):551–556.
[2]HUANG G P, MOURIKIS A I, ROUMELIOTIS S I. A quadratic-complexity observability-constrained unscented Kalman filter for SLAM[J]. IEEE transactions on robotics,2013, 29(5):1226–1243.
[3]张凤,黄陆君,袁帅,等. NLOS环境下基于EKF的移动机器人定位研究[J].控制工程, 2015, 22(1):14–19.ZHANG Feng, HUANG Lujun, YUAN Shuai, et al. Reach on robot localization based on EKF in NLOS environment[J]. Control engineering of China, 2015, 22(1):14–19.
[4]刘卫华,王希彬,周强.基于容积粒子滤波的无人机FastSLAM算法研究[J].系统仿真技术, 2014, 10(3):234–238.LIU Weihua, WANG Xibin, ZHOU Qiang. FastSLAM algorithm based on cubature particle filtering algorithm for UAV[J]. System simulation technology, 2014, 10(3):234–238.
[5]丛楚滢,王从庆,丁臻极,等.一种小型无人机的FastSLAM算法[J].华中科技大学学报(自然科学版), 2015,43(S1):420–423.CONG Chuying, WANG Congqing, DING Zhenji, et al. A FastSLAM algorithm for small unmanned aerial vehicle[J].Journal of Huazhong university of science and technology(nature science edition), 2015, 43(S1):420–423.
[6]吕品,赖际舟,杨天雨,等.基于气动模型辅助的四旋翼飞行器室内自主导航方法[J].航空学报, 2015, 36(4):1275–1284.LYU Pin, LAI Jizhou, YANG Tianyu, et al. Autonomous navigation method aided by aerodynamics model for an indoor quadrotor[J]. Acta aeronautica et astronautica sinica,2015, 36(4):1275–1284.
[7]蒙山,唐文名.单目SLAM直线匹配增强平面发现方法[J].北京航空航天大学学报, 2017, 43(4):660–666.MENG Shan, TANG Wenming. Monocular SLAM plane discovery method enhanced by line segments matching[J].Journal of Beijing university of aeronautics and astronsutics, 2017, 43(4):660–666.
[8]余小欢,韩波,张宇,等.基于双目视觉的微型无人机室内三维地图构建[J].信息与控制, 2014, 43(4):392–397.YU Xiaohuan, HAN Bo, ZHANG Yu, et al. Binocular stereo vision based 3D mapping for micro aerial vehicles in an indoor environment[J]. Information and control, 2014,43(4):392–397.
[9]吕科,施泽南,李一鹏.微型无人机视觉定位与环境建模研究[J].电子科技大学学报, 2017, 46(3):543–548.LüKe, SHI Zenan, LI Yipeng. Visual localization and environment mapping for micro aerial vehicles[J]. Journal of university of electronic science and technology of China,2017, 46(3):543–548.
[10]王国胜,郭峰,刘峰.无人飞行器视觉SLAM特征检测和匹配算法研究[J].计算机测量与控制, 2015, 23(7):2453–2455.WANG Guosheng, GUO Feng, LIU Feng. Research on feature detection and matching algorithm of unmanned aerial vehicles visual SLAM[J]. Computer measurement&control, 2015, 23(7):2453–2455.
[11]王闯,卢健,黄杰. AUV同时定位与跟踪算法研究[J].西安工程大学学报, 2014, 28(5):556–562.WANG Chuang, LU Jian, HUANG Jie. Algorithms research of simultaneous localization and tracking for AUVs[J]. Journal of Xi’an polytechnic university, 2014,28(5):556–562.
[12]STECKEL J, PEREMANS H. Spatial sampling strategy for a 3D sonar sensor supporting BatSLAM[C]//Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Hamburg, Germany, 2015:723–728.
[13]TUBMAN R, POTGIETER J, ARIF K M. Efficient robotic SLAM by fusion of RatSLAM and RGBD-SLAM[C]//Proceedings of the 201623rd International Conference on Mechatronics and Machine Vision in Practice. Nanjing,China, 2016:1–6.
[14]STECKEL J, PEREMANS H. BatSLAM:simultaneous localization and mapping using biomimetic sonar[J].PLoS One, 2013, 8(1):e54076.
[15]YU Hongshan, ZHANG Yuan, WANG Yaonan, et al.Fast and robust frontier line segment extracting method based on FCM for robot exploration[C]//Proceedings of2013 Chinese Automation Congress. Changsha, China,2013:685–690.
[16]王伟,陈志高,孟宪凯,等.基于熵的音频指纹检索技术研究与实现[J].计算机科学, 2017, 44(S1):551–556.WANG Wei, CHEN Zhigao, MENG Xiankai, et al. Research and implementation of identifying music through performances using entropy based audio-fingerprint[J].Computer science, 2017, 44(S1):551–556.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |