东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

Effectively Lossless Subspace Appearance Model Compression Using Prior Information

时间：0
分类：TP391.41[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术] TS441[农业科学—烟草工业]
作者机构：[1]Department of Electronic Engineering, Tsinghua University,Beijing 100084, China
相关基金：supported by the National key Basic Research and Development (973) Program of China (No. 2013CB329006);the National Natural Science Foundation of China (Nos. 61471220 and 61021001);Tsinghua University Initiative Scientific Research Program, and Tsinghua-Qualcomm Joint Research Program

关键词：外观变化, 先验信息, y压缩, 子空间, 模型, 无损, 计算机视觉, 量化步长, data compression, principal component analysis, appearance modeling

中文摘要：

Subspace appearance models are widely used in computer vision and image processing tasks to compactly represent the appearance variations of target objects. In order to ensure algorithm performance, they are typically stored in high-precision formats; this results in a large storage footprint, rendering redistribution costly and difficult. Since for most image and vision applications, pixel values are quantized to 8 bits by the acquisition apparatuses, we show that it is possible to construct a fixed-width, effectively lossless representation of the bases vectors, in the sense that reconstructions from the original bases and from the quantized bases never deviate by more than half of the quantization step-size. In addition to directly applying this result to losslessly compress individual models, we also propose an algorithm to compress appearance models by utilizing prior information on the modeled objects in the form of prior appearance subspaces. Experiments conducted on the compression of person-specific face appearance models demonstrate the effectiveness of the proposed algorithms.

英文摘要：

Subspace appearance models are widely used in computer vision and image processing tasks to compactly represent the appearance variations of target objects. In order to ensure algorithm performance, they are typically stored in high-precision formats; this results in a large storage footprint, rendering redistribution costly and difficult. Since for most image and vision applications, pixel values are quantized to 8 bits by the acquisition apparatuses, we show that it is possible to construct a fixed-width, effectively Iossless representation of the bases vectors, in the sense that reconstructions from the original bases and from the quantized bases never deviate by more than half of the quantization step-size. In addition to directly applying this result to Iosslessly compress individual models, we also propose an algorithm to compress appearance models by utilizing prior information on the modeled objects in the form of prior appearance subspaces. Experiments conducted on the compression of person-specific face appearance models demonstrate the effectiveness of the proposed algorithms.