A technique for getting Euclidean reconstruction from two images of the same scene taken by a single moving camera, which undergoes a pure translation, is presented. Euclidean reconstruction of the scene up to three s...A technique for getting Euclidean reconstruction from two images of the same scene taken by a single moving camera, which undergoes a pure translation, is presented. Euclidean reconstruction of the scene up to three scale factors can be obtained by using this special but still realistic motion when the skew factor of the cam- era is zero; otherwise Euclidean reconstruction of the depth up to one scale factor can be achieved. The only assumption is that the camera intrinsic parameters are constant. Using this special but still realistic motion to do the reconstruction has the advantage that no projective reconstruction is needed and the Euclidean reconstruction is computed directly from the point correspondences in the two images.展开更多
A key problem that plagues camera self-calibration, namely that the classical self-calibration algorithms are very sensitive to the initial values of the camera intrinsic parameters, is analyzed and a practical soluti...A key problem that plagues camera self-calibration, namely that the classical self-calibration algorithms are very sensitive to the initial values of the camera intrinsic parameters, is analyzed and a practical solution is provided. The effect of the camera intrinsic parameters, mainly the principal point and the skew factor is first discussed. Then a practical method via a controlled motion of the camera is introduced so as to obtain an accurate estimation of these parameters. Feasibility of this approach is illustrated by carrying out comprehensive experiments using synthetic data as well as real image sequences. Unreasonable initial values can often make self-calibration impossible, yet a precise initialization guarantees a better and successful reconstruction. Trying to obtain a more reasonable initialization is worthwhile the effort in camera self-calibration.展开更多
The ability to recognise video events has become increasingly more popular owing to its extensive practical applications.Most events will occur in certain scene with certain people,and the scene context and group cont...The ability to recognise video events has become increasingly more popular owing to its extensive practical applications.Most events will occur in certain scene with certain people,and the scene context and group context provide important information for event recognition.In this paper,we present an algorithm to recognise video events in different scenes in which there are multiple agents.First,we recognise events for each agent based on Stochastic Context Sensitive Grammar(SCSG).Then we propose the model of a scene in order to infer the scene in which the events occur,and we use a co-occurrence matrix of events to represent the group context.Finally,the scene and group context are exploited to distinguish events having similar structures.Experimental results show that by adding the scene and group context,the performance of events recognition can be significantly improved.展开更多
Video events recognition is a challenging task for high-level understanding of video se- quence. At present, there are two major limitations in existing methods for events recognition. One is that no algorithms are av...Video events recognition is a challenging task for high-level understanding of video se- quence. At present, there are two major limitations in existing methods for events recognition. One is that no algorithms are available to recognize events which happen alternately. The other is that the temporal relationship between atomic actions is not fully utilized. Aiming at these problems, an algo- rithm based on an extended stochastic context-free grammar （SCFG） representation is proposed for events recognition. Events are modeled by a series of atomic actions and represented by an extended SCFG. The extended SCFG can express the hierarchical structure of the events and the temporal re- lationship between the atomic actions. In comparison with previous work, the main contributions of this paper are as follows： ① Events （include alternating events） can be recognized by an improved stochastic parsing and shortest path finding algorithm. ② The algorithm can disambiguate the detec- tion results of atomic actions by event context. Experimental results show that the proposed algo- rithm can recognize events accurately and most atomic action detection errors can be corrected sim- ultaneously.展开更多
文摘A technique for getting Euclidean reconstruction from two images of the same scene taken by a single moving camera, which undergoes a pure translation, is presented. Euclidean reconstruction of the scene up to three scale factors can be obtained by using this special but still realistic motion when the skew factor of the cam- era is zero; otherwise Euclidean reconstruction of the depth up to one scale factor can be achieved. The only assumption is that the camera intrinsic parameters are constant. Using this special but still realistic motion to do the reconstruction has the advantage that no projective reconstruction is needed and the Euclidean reconstruction is computed directly from the point correspondences in the two images.
文摘A key problem that plagues camera self-calibration, namely that the classical self-calibration algorithms are very sensitive to the initial values of the camera intrinsic parameters, is analyzed and a practical solution is provided. The effect of the camera intrinsic parameters, mainly the principal point and the skew factor is first discussed. Then a practical method via a controlled motion of the camera is introduced so as to obtain an accurate estimation of these parameters. Feasibility of this approach is illustrated by carrying out comprehensive experiments using synthetic data as well as real image sequences. Unreasonable initial values can often make self-calibration impossible, yet a precise initialization guarantees a better and successful reconstruction. Trying to obtain a more reasonable initialization is worthwhile the effort in camera self-calibration.
基金partially supported by the National Natural Science Foundation of China under Grant No.61203291the Specialised Research Fund for the Doctoral Program under Grant No.20121101110035
文摘The ability to recognise video events has become increasingly more popular owing to its extensive practical applications.Most events will occur in certain scene with certain people,and the scene context and group context provide important information for event recognition.In this paper,we present an algorithm to recognise video events in different scenes in which there are multiple agents.First,we recognise events for each agent based on Stochastic Context Sensitive Grammar(SCSG).Then we propose the model of a scene in order to infer the scene in which the events occur,and we use a co-occurrence matrix of events to represent the group context.Finally,the scene and group context are exploited to distinguish events having similar structures.Experimental results show that by adding the scene and group context,the performance of events recognition can be significantly improved.
基金Supported by the National Natural Science Foundation of China(60805028,60903146)Natural Science Foundation of Shandong Province of China (ZR2010FM027)+1 种基金SDUST Research Fund(2010KYTD101)China Postdoctoral Science Foundation(2012M521336)
文摘Video events recognition is a challenging task for high-level understanding of video se- quence. At present, there are two major limitations in existing methods for events recognition. One is that no algorithms are available to recognize events which happen alternately. The other is that the temporal relationship between atomic actions is not fully utilized. Aiming at these problems, an algo- rithm based on an extended stochastic context-free grammar （SCFG） representation is proposed for events recognition. Events are modeled by a series of atomic actions and represented by an extended SCFG. The extended SCFG can express the hierarchical structure of the events and the temporal re- lationship between the atomic actions. In comparison with previous work, the main contributions of this paper are as follows： ① Events （include alternating events） can be recognized by an improved stochastic parsing and shortest path finding algorithm. ② The algorithm can disambiguate the detec- tion results of atomic actions by event context. Experimental results show that the proposed algo- rithm can recognize events accurately and most atomic action detection errors can be corrected sim- ultaneously.
