In this paper,we propose a novel approach to recognise human activities from a different view.Although appearance-based recognition methods have been shown to be unsuitable for action recognition for varying views,the...In this paper,we propose a novel approach to recognise human activities from a different view.Although appearance-based recognition methods have been shown to be unsuitable for action recognition for varying views,there must be some regularity among the same action sequences of different views.Selfsimilarity matrices appear to be relative stable across views.However,the ability to effectively realise this stability is a problem.In this paper,we extract the shape-flow descriptor as the low-level feature and then choose the same number of key frames from the action sequences.Self-similarity matrices are obtained by computing the similarity between any pair of the key frames.The diagonal features of the similarity matrices are extracted as the highlevel feature representation of the action sequence and Support Vector Machines(SVM) is employed for classification.We test our approach on the IXMAS multi-view data set.The proposed approach is simple but effective when compared with other algorithms.展开更多
The laser beam divergence angle is one of the important parameters to evaluate the quality of the laser beam.It can not only accurately indicate the nature of the beam divergence when the laser beam is transmitted ove...The laser beam divergence angle is one of the important parameters to evaluate the quality of the laser beam.It can not only accurately indicate the nature of the beam divergence when the laser beam is transmitted over a long distance,but also objectively evaluate the performance of the laser system.At present,lidar has received a lot of attention as a core component of environment awareness technology.Micro-electromechanical system(MEMS)micromirror has become the first choice for three-dimensional imaging lidar because of its small size and fast scanning speed.However,due to the small size of the MEMS micromirror,the lidar scanning system has a small field of view(FOV).In order to achieve a wide range of scanning imaging,collimating optical system and wide-angle optical system are generally added to the system.However,due to the inherent properties of the optical lens,it is impossible to perfect the imaging,so the effects of collimating and expanding the beam will be different at different angles.This article aims to propose a measurement system that dynamically measures the divergence angles of MEMS scanning lidar beams in different fields of view to objectively evaluate the performances of scanning lidar systems.展开更多
基金supported by a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(Information and Communication Engineering)the Natural Science Foundation of Jiangsu Province under Grant No.BK2010523+2 种基金the National Natural Science Foundation of China under Grants No.61172118,No.61001152the University Natural Science Research Project of Jiangsu Province under Grant No.11KJB510012the Scientific Research Foundation of Nanjing University of Posts and Telecommunications under Grant No.NY210073
文摘In this paper,we propose a novel approach to recognise human activities from a different view.Although appearance-based recognition methods have been shown to be unsuitable for action recognition for varying views,there must be some regularity among the same action sequences of different views.Selfsimilarity matrices appear to be relative stable across views.However,the ability to effectively realise this stability is a problem.In this paper,we extract the shape-flow descriptor as the low-level feature and then choose the same number of key frames from the action sequences.Self-similarity matrices are obtained by computing the similarity between any pair of the key frames.The diagonal features of the similarity matrices are extracted as the highlevel feature representation of the action sequence and Support Vector Machines(SVM) is employed for classification.We test our approach on the IXMAS multi-view data set.The proposed approach is simple but effective when compared with other algorithms.
基金Project supported by the National Key Scientific Instrument and Equipment Development Projects of China(Grant No.62027823)the Shenzhen Fundamental Research Program(Grant No.JCYJ2020109150808037)the National Natural Science Foundation of China(Grant No.61775048)。
文摘The laser beam divergence angle is one of the important parameters to evaluate the quality of the laser beam.It can not only accurately indicate the nature of the beam divergence when the laser beam is transmitted over a long distance,but also objectively evaluate the performance of the laser system.At present,lidar has received a lot of attention as a core component of environment awareness technology.Micro-electromechanical system(MEMS)micromirror has become the first choice for three-dimensional imaging lidar because of its small size and fast scanning speed.However,due to the small size of the MEMS micromirror,the lidar scanning system has a small field of view(FOV).In order to achieve a wide range of scanning imaging,collimating optical system and wide-angle optical system are generally added to the system.However,due to the inherent properties of the optical lens,it is impossible to perfect the imaging,so the effects of collimating and expanding the beam will be different at different angles.This article aims to propose a measurement system that dynamically measures the divergence angles of MEMS scanning lidar beams in different fields of view to objectively evaluate the performances of scanning lidar systems.
