Evolution-based virtual content insertion Chiang, Ming-Che; Chang, Chia-Hu; Wu, Ja-Ling
Proceedings of the 17th ACM international conference on Multimedia,
10/2009
Conference Proceeding
This demonstration presents an innovative framework for virtual content insertion in an interactive way. The virtual content is inserted into video with evolved animations according to predefined ...behaviors, and generates interactions with video contents. In order to reduce the intrusiveness and improve the impression for viewers, the evolution process is divided into distinct yet dependent phases, in which the virtual content evolves its appearances and behaviors according to the incremental interactions. Therefore, the augmented videos generated by the proposed system establish visually relevant connection between the inserted virtual content and the source videos, and increase the acceptability and the attractiveness at the same time. Moreover, the proposed system enables video owners to create entertaining personalized videos effectively, and engages viewers with the storyline.
The scalable video coding (SVC) extension of H.264/AVC was designed to support bandwidth efficient and loss resilient video streaming. Its multilayer predictive encoding enables user devices to adapt ...their video reception by extracting and decoding selected code layers according to device display capability and network throughput. However, this desirable feature is much harder to realize in practice as the reduction of coding efficiency causes inflation of SVC bitstreams. Consequently, an SVC multicast session among clusters of heterogeneous devices may consume more bandwidth than an AVC simulcasting session. In this paper, we propose a bandwidth efficient scheme for conducting heterogeneous SVC multicasting. The proposed scheme employs a combination of three transport techniques: (1) broadcasting of SVC layers in local service subnets, (2) multipath transport of SVC layers over long- haul networks and (3) aggregation of data flows along transport paths. This scheme is particularly suited for delivering SVC bitstreams to different user devices scattered over geographically dispersed local subnets. Preliminary simulation experiments performed over lossless networks showed that the scheme can introduce from 2:1 to 6:1 reduction of up-stream bandwidth for SVC layer transport. It can also maintain 85% transport efficiency while minimizes PSNR loss of most user devices even under heavy traffic. We expect the proposed scheme will achieve better rate- distortion performance than AVC simulcasting over lossy networks if unequal erasure protection (UEP) will be applied to the lower SVC layers. Further investigation of its potential is currently underway.
We proposed an image retrieval algorithm that deals with multi-instance query with heterogeneous features. For the pre-processing, we utilized the gray-level morphological operations by ...reconstruction to effectively identify the foreground objects in images. This method can be processed by the pipeline architecture which is suitable for dealing with volume images. The retrieval process is carried out in intra and inter feature domains: (1) the intra retrieval utilizes the profession of multi-instance query with one feature and; (2) the inter retrieval coordinates the individual intra retrieval results to boost salient common features among query samples. To represent feature saliency, the averaged normalized correlation coefficient is computed in the intra domain and is normalized in the inter domain. The most distinguished point of this algorithm is that it coordinates heterogeneous features for multi-instance retrieval. Up to five different image types could be integrated for retrieval. Simulations demonstrate satisfactory subjective and objective retrieval performances