Local invariant algorithm applied in downward-looking image registration,usually computes the camera's pose relative to visual landmarks.Generally,there are three requirements in the process of image registration ...Local invariant algorithm applied in downward-looking image registration,usually computes the camera's pose relative to visual landmarks.Generally,there are three requirements in the process of image registration when using these approaches.First,the algorithm is apt to be influenced by illumination.Second,algorithm should have less computational complexity.Third,the depth information of images needs to be estimated without other sensors.This paper investigates a famous local invariant feature named speeded up robust feature(SURF),and proposes a highspeed and robust image registration and localization algorithm based on it.With supports from feature tracking and pose estimation methods,the proposed algorithm can compute camera poses under different conditions of scale,viewpoint and rotation so as to precisely localize object's position.At last,the study makes registration experiment by scale invariant feature transform(SIFT),SURF and the proposed algorithm,and designs a method to evaluate their performances.Furthermore,this study makes object retrieval test on remote sensing video.For there is big deformation on remote sensing frames,the registration algorithm absorbs the Kanade-Lucas-Tomasi(KLT)3-D coplanar calibration feature tracker methods,which can localize interesting targets precisely and efficiently.The experimental results prove that the proposed method has a higher localization speed and lower localization error rate than traditional visual simultaneous localization and mapping(vSLAM)in a period of time.展开更多
车载语音交互小词汇量语音识别常用动态时间规整(Dynamic Time Warping,DTW)算法,但该算法参数固定,难以应对语速变化与噪声干扰。文章提出自适应DTW(A-DTW)框架,经变速、多噪声孤立词语库试验验证,其复杂场景识别率较传统DTW及其主流...车载语音交互小词汇量语音识别常用动态时间规整(Dynamic Time Warping,DTW)算法,但该算法参数固定,难以应对语速变化与噪声干扰。文章提出自适应DTW(A-DTW)框架,经变速、多噪声孤立词语库试验验证,其复杂场景识别率较传统DTW及其主流改进算法提升3.5~8.7个百分点,且计算开销可控,为资源受限环境的稳定语音识别提供有效方案。展开更多
针对传统图像匹配算法计算量大、耗时长等缺陷,提出一种基于SURF(speeded up robust features)的图像特征点快速匹配算法.首先对图像采用SURF算法提取特征点;然后通过Haar小波变换确定特征点的主方向和特征点描述子,使用优化的最近邻搜...针对传统图像匹配算法计算量大、耗时长等缺陷,提出一种基于SURF(speeded up robust features)的图像特征点快速匹配算法.首先对图像采用SURF算法提取特征点;然后通过Haar小波变换确定特征点的主方向和特征点描述子,使用优化的最近邻搜索算法(best bin first,BBF)进行特征点匹配;最后根据实际需要选取相似度最高的前n对匹配点进行对比实验.实验结果表明:该算法鲁棒性强,速度快,匹配准确性高,具有较大的应用价值.展开更多
现有的多数人脸识别系统都要依赖于面部特征(比如眼睛中心位置)的严格配准来归一化人脸以便提取人脸描述特征,但面部特征配准的准确度如何影响人脸识别算法的性能却没有得到足够的重视.该文作者首次针对这一问题进行了系统的研究,并提...现有的多数人脸识别系统都要依赖于面部特征(比如眼睛中心位置)的严格配准来归一化人脸以便提取人脸描述特征,但面部特征配准的准确度如何影响人脸识别算法的性能却没有得到足够的重视.该文作者首次针对这一问题进行了系统的研究,并提出了一种基于误配准学习的解决方案.为了揭示现有典型识别算法的识别性能对特征配准准确度的敏感程度,通过对眼睛位置人为加扰,作者对Fisherface算法的识别性能随平移、旋转和尺度改变而变化的情况进行了实验评估.结果表明Fisherface的识别性能随着误配准的增大而急剧下降——称这一现象为“误配准灾难”问题.针对此问题,作者提出了一种基于扰动学习的“误配准灾难”解决方案,该方法通过在模型训练阶段加入扰动配准偏差来提高判别分析方法对误配准的鲁棒性.在FERET人脸图像数据库和CAS PEAL R1人脸库上的实验表明该方法可以有效地提高识别算法对误配准的鲁棒性.展开更多
针对传统车辆检索方法中存在准确性和区分度较低的问题,提出了一个基于改进SURF(speeded up robust features)算法的视频车辆检索方法。在车辆视频关键帧提取的基础上,根据改进SURF算法完成车辆图像的特征提取及匹配,其中包含改进FAST(f...针对传统车辆检索方法中存在准确性和区分度较低的问题,提出了一个基于改进SURF(speeded up robust features)算法的视频车辆检索方法。在车辆视频关键帧提取的基础上,根据改进SURF算法完成车辆图像的特征提取及匹配,其中包含改进FAST(features from accelerated segment test)特征点检测、SURF特征向量提取以及最近邻查询方法来进行特征点的匹配;通过计算比较待检索车辆图像与数据库车辆图像的相似度,算法完成图像筛选并反馈检索结果。实验结果表明:针对交通监控视频中待检索车辆,该方法能够较为准确地进行检索并反馈结果。展开更多
为从不同角度识别目标物体以及解决左右两幅图像中目标轮廓中心不匹配的问题,将SURF(Speeded Up Robust Features)算法与Grab Cut算法相结合,离线采集目标物体不同角度的图像,生成目标模板图片库。利用SURF算法完成目标物体的识别;利用S...为从不同角度识别目标物体以及解决左右两幅图像中目标轮廓中心不匹配的问题,将SURF(Speeded Up Robust Features)算法与Grab Cut算法相结合,离线采集目标物体不同角度的图像,生成目标模板图片库。利用SURF算法完成目标物体的识别;利用SURF算法自动初始化Grab Cut算法,实现目标轮廓的提取;利用基于灰度相关的区域匹配算法完成目标轮廓中心点的匹配,结合三维重建原理实现目标定位。实验结果表明,该方法可以成功识别目标物体并对目标物体进行准确定位。展开更多
基金supported by the National Natural Science Foundation of China(60802043)the National Basic Research Program of China(973 Program)(2010CB327900)
文摘Local invariant algorithm applied in downward-looking image registration,usually computes the camera's pose relative to visual landmarks.Generally,there are three requirements in the process of image registration when using these approaches.First,the algorithm is apt to be influenced by illumination.Second,algorithm should have less computational complexity.Third,the depth information of images needs to be estimated without other sensors.This paper investigates a famous local invariant feature named speeded up robust feature(SURF),and proposes a highspeed and robust image registration and localization algorithm based on it.With supports from feature tracking and pose estimation methods,the proposed algorithm can compute camera poses under different conditions of scale,viewpoint and rotation so as to precisely localize object's position.At last,the study makes registration experiment by scale invariant feature transform(SIFT),SURF and the proposed algorithm,and designs a method to evaluate their performances.Furthermore,this study makes object retrieval test on remote sensing video.For there is big deformation on remote sensing frames,the registration algorithm absorbs the Kanade-Lucas-Tomasi(KLT)3-D coplanar calibration feature tracker methods,which can localize interesting targets precisely and efficiently.The experimental results prove that the proposed method has a higher localization speed and lower localization error rate than traditional visual simultaneous localization and mapping(vSLAM)in a period of time.
文摘车载语音交互小词汇量语音识别常用动态时间规整(Dynamic Time Warping,DTW)算法,但该算法参数固定,难以应对语速变化与噪声干扰。文章提出自适应DTW(A-DTW)框架,经变速、多噪声孤立词语库试验验证,其复杂场景识别率较传统DTW及其主流改进算法提升3.5~8.7个百分点,且计算开销可控,为资源受限环境的稳定语音识别提供有效方案。
文摘针对传统图像匹配算法计算量大、耗时长等缺陷,提出一种基于SURF(speeded up robust features)的图像特征点快速匹配算法.首先对图像采用SURF算法提取特征点;然后通过Haar小波变换确定特征点的主方向和特征点描述子,使用优化的最近邻搜索算法(best bin first,BBF)进行特征点匹配;最后根据实际需要选取相似度最高的前n对匹配点进行对比实验.实验结果表明:该算法鲁棒性强,速度快,匹配准确性高,具有较大的应用价值.
文摘现有的多数人脸识别系统都要依赖于面部特征(比如眼睛中心位置)的严格配准来归一化人脸以便提取人脸描述特征,但面部特征配准的准确度如何影响人脸识别算法的性能却没有得到足够的重视.该文作者首次针对这一问题进行了系统的研究,并提出了一种基于误配准学习的解决方案.为了揭示现有典型识别算法的识别性能对特征配准准确度的敏感程度,通过对眼睛位置人为加扰,作者对Fisherface算法的识别性能随平移、旋转和尺度改变而变化的情况进行了实验评估.结果表明Fisherface的识别性能随着误配准的增大而急剧下降——称这一现象为“误配准灾难”问题.针对此问题,作者提出了一种基于扰动学习的“误配准灾难”解决方案,该方法通过在模型训练阶段加入扰动配准偏差来提高判别分析方法对误配准的鲁棒性.在FERET人脸图像数据库和CAS PEAL R1人脸库上的实验表明该方法可以有效地提高识别算法对误配准的鲁棒性.
文摘针对传统车辆检索方法中存在准确性和区分度较低的问题,提出了一个基于改进SURF(speeded up robust features)算法的视频车辆检索方法。在车辆视频关键帧提取的基础上,根据改进SURF算法完成车辆图像的特征提取及匹配,其中包含改进FAST(features from accelerated segment test)特征点检测、SURF特征向量提取以及最近邻查询方法来进行特征点的匹配;通过计算比较待检索车辆图像与数据库车辆图像的相似度,算法完成图像筛选并反馈检索结果。实验结果表明:针对交通监控视频中待检索车辆,该方法能够较为准确地进行检索并反馈结果。
