IPDDF: an improved precision dense descriptor based flow estimation

CAAI Transactions on Intelligence Technology

article

Weiyong Eng¹  Voonchet Koo¹  Tiensze Lim¹ 

[1] Faculty of Engineering and Technology, Multimedia University

关键词: optimisation;    filtering theory;    image sequences;    feature extraction;    estimation theory;    image matching;    image segmentation;    object tracking;    pixel-based cost;    light-weight pre-computation;    dense descriptor matching framework;    Daisy Filter Flow work;    filter-based efficient flow inference technique;    novel matching cost formulation;    dense correspondence field estimation;    flow estimation accuracy;    edge-aware flow field;    IPDDF;    improved precision dense descriptor based flow estimation;    displacement optical flow algorithms;    descriptor-based approaches;    inherent localisation precision limitation;    precision dense descriptor flow;    additional pixel-based;    existing dense Daisy descriptor framework;    flow estimation precision;    pixel-based features;    pixel colour;    original descriptor;    authors;    B0240Z Other topics in statistics;    B0260 Optimisation techniques;    B6135 Optical;    image and video signal processing;    B6135E Image recognition;    B6140B Filtering methods in signal processing;    C1140Z Other topics in statistics;    C1180 Optimisation techniques;    C4130 Interpolation and function approximation (numerical analysis);    C5260B Computer vision and image processing techniques;   

DOI  :  10.1049/trit.2019.0052

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

Large displacement optical flow algorithms are generally categorised into descriptor-based matching and pixel-based matching. Descriptor-based approaches are robust to geometric variation, however they have inherent localisation precision limitation due to histogram nature. This work presents a novel method called improved precision dense descriptor flow (IPDDF). The authors introduce an additional pixel-based matching cost within an existing dense Daisy descriptor framework to improve the flow estimation precision. Pixel-based features such as pixel colour and gradient are computed on top of the original descriptor in the authors' matching cost formulation. The pixel-based cost only requires a light-weight pre-computation and can be adapted seamlessly into the matching cost formulation. The framework is built based on the Daisy Filter Flow work. In the framework, Daisy descriptor and a filter-based efficient flow inference technique, as well as a randomised fast patch match search algorithm, are adopted. Given the novel matching cost formulation, the framework enables efficiently solving dense correspondence field estimation in a high-dimensional search space, which includes scale and orientation. Experiments on various challenging image pairs demonstrate the proposed algorithm enhances flow estimation accuracy as well as generate a spatially coherent yet edge-aware flow field result efficiently.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND