The identification of the overlapped objects is a great challenge in object tracking and video data indexing. For this purpose, a backtrack-chain-updation split algorithm is proposed to assist an unsupervised video se...
详细信息
The identification of the overlapped objects is a great challenge in object tracking and video data indexing. For this purpose, a backtrack-chain-updation split algorithm is proposed to assist an unsupervised video segmentation method called the "simultaneous partition and class parameter estimation" (SPCPE) algorithm to identify the overlapped objects in the video sequence. The backtrack-chain-updation split algorithm can identify the split segment (object) and use the information in the current frame to update the previous frames in a backtrack-chain manner. The splitalgorithm provides more accurate temporal and spatial information of the semantic objects so that the semantic objects can be indexed and modeled by multimedia input strings and the multimedia augmented transition network (MATN) model. The MATN model is based on the ATN model that has been used in artificial intelligence (AI) areas for natural language understanding systems, and its inputs are modeled by the multimedia input strings. In this paper, we will show that the SPCPE algorithm together with the backtrack-chain-updation split algorithm can significantly enhance the efficiency of spatio-temporal video indexing by improving the accuracy of multimedia database queries related to semantic objects.
In our previous work, a multimedia augmented transition network (ATN) model together with its multimedia input strings were proposed to model and structure video data. The multimedia ATN model is based on the ATN mode...
详细信息
ISBN:
(纸本)076950910X
In our previous work, a multimedia augmented transition network (ATN) model together with its multimedia input strings were proposed to model and structure video data. The multimedia ATN model is based on the ATN model that has been used in the artificial intelligence (AI) areas for natural language understanding systems and its inputs are modeled by the multimedia input strings. The temporal and spatial relations of semantic objects are captured by an unsupervised video segmentation method called simultaneous partition and class parameter estimation (SPCPE) algorithm and are modeled by the multimedia input strings. However, the segmentation method used is not able to identify the objects that are overlapped together within video frames. The identification of the overlapped objects is a great challenge. For this purpose, a backtrack-chain-updation split algorithm that identifies the split segment (object) and uses the information in the current frame to update the previous frames in a backtrack-chain manner is developed in this paper. The proposed splitalgorithm provides more accurate temporal and spatial information of the semantic objects for video indexing.
暂无评论