Current Issue : July - September Volume : 2012 Issue Number : 3 Articles : 5 Articles
For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs\r\nto be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such\r\nconditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each\r\nblock location a representative set is maintained which contains distinct blocks obtained along its temporal line. The background\r\nestimation is carried out in a Markov Random Field framework, where the optimal labelling solution is computed using iterated\r\nconditional modes. The clique potentials are computed based on the combined frequency response of the candidate block and its\r\nneighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial\r\ncontinuity of structures within a scene. Experiments on real-life surveillance videos demonstrate that the proposedmethod obtains\r\nconsiderably better background estimates (both qualitatively and quantitatively) than median filtering and the recently proposed\r\nââ?¬Å?intervals of stable intensityââ?¬Â method. Further experiments on theWallflower dataset suggest that the combination of the proposed\r\nmethod with a foreground segmentation algorithm results in improved foreground segmentation....
A packet-layer video quality assessment (VQA) model is a lightweight model that predicts the video quality\r\nimpacted by network conditions and coding configuration for application scenarios such as video system planning\r\nand in-service video quality monitoring. It is under standardization in ITU-T Study Group (SG) 12. In this article, we\r\nfirst differentiate the requirements for VQA model from the two application scenarios, and state the argument that\r\nthe dataset for evaluating the quality monitoring model should be more challenging than that for system planning\r\nmodel. Correspondingly, different criteria and approaches are used for constructing the test datasets, for system\r\nplanning (dataset-1) and for video quality monitoring (dataset-2), respectively. Further, we propose a novel video\r\nquality monitoring model by estimating the spatiotemporal complexity of video content. The model takes into\r\naccount the interactions among content features, the error concealment effectiveness, and error propagation\r\neffects. Experiment results demonstrate that the proposed model achieves robust performance improvement\r\ncompared with the existing peer VQA metrics on both dataset-1 and dataset-2. It is noted that on the more\r\nchallenging dataset-2 for video quality monitoring, we obtain a large increase in Pearson correlation from 0.75 to\r\n0.92 and a decrease in the modified RMSE from 0.41 to 0.19....
Although automatic faces recognition has shown success for high-quality images under controlled conditions, for video-based\r\nrecognition it is hard to attain similar levels of performance.We describe in this paper recent advances in a project being undertaken\r\nto trial and develop advanced surveillance systems for public safety. In this paper, we propose a local facial feature based framework\r\nfor both still image and video-based face recognition. The evaluation is performed on a still image dataset LFW and a video\r\nsequence dataset MOBIO to compare 4 methods for operation on feature: feature averaging (Avg-Feature), Mutual Subspace\r\nMethod (MSM), Manifold to Manifold Distance (MMS), and Affine Hull Method (AHM), and 4 methods for operation on\r\ndistance on 3 different features. The experimental results show thatMulti-region Histogram (MRH) feature ismore discriminative\r\nfor face recognition compared to Local Binary Patterns (LBP) and raw pixel intensity. Under the limitation on a small number of\r\nimages available per person, feature averaging ismore reliable thanMSM,MMD, andAHM and ismuch faster. Thus, our proposed\r\nframeworkââ?¬â?averaging MRH feature is more suitable for CCTV surveillance systems with constraints on the number of images\r\nand the speed of processing....
This paper proposes a scheme for error-resilient transmission of videos which jointly uses intra macroblock\r\nrefreshment and redundant motion vector. The selection of using intra refreshment or redundant motion vector is\r\ndetermined by the rate-distortion optimization procedure. The end-to-end distortion is used for the rate-distortion\r\noptimization, which can be easily calculated with the recursive optimal per-pixel estimate (ROPE) method.\r\nSimulation results show that the proposed method outperforms both the intra refreshment approach and\r\nredundant motion vector approach significantly, when the two approaches are deployed separately. Specifically, for\r\nthe Foreman sequence, the average PSNR of the proposed approach can be 1.12 dB higher than that of the intra\r\nrefreshment approach and 5 dB higher than that of the redundant motion vector approach....
There is a growing need in computer vision applications for stereopsis, requiring not only accurate distance but\r\nalso fast and compact physical implementation. Global energy minimization techniques provide remarkably precise\r\nresults. But they suffer from huge computational complexity. One of the main challenges is to parallelize the\r\niterative computation, solving the memory access problem between the big external memory and the massive\r\nprocessors. Remarkable memory saving can be obtained with our memory reduction scheme, and our new\r\narchitecture is a systolic array. If we expand it into N�s multiple chips in a cascaded manner, we can cope with\r\nvarious ranges of image resolutions. We have realized it using the FPGA technology. Our architecture records 19\r\ntimes smaller memory than the global minimization technique, which is a principal step toward real-time chip\r\nimplementation of the various iterative image processing algorithms with tiny and distributed memory resources\r\nlike optical flow, image restoration, etc....
Loading....