提出一种保留局部结构的像素差哈希框架，提升动态纹理识别精度。
LP$^{2}$DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition
- 联合编码时空邻域像素差，生成紧凑二值码
- 在三个基准上均超现有方法，最高达99.80%准确率
- 适合需要高效高精度动态纹理识别的场景
时空局部二值模式（STLBP）是常用的动态纹理描述子，但存在维度极高的问题。传统方法在三个正交平面上提取特征，牺牲了平面间相关性。本文提出一种保局像素差哈希框架（LP²DH），联合编码完整时空邻域的像素差。该方法将像素差向量（PDVs）转换为具有最大判别力的紧凑二值码，并引入保局嵌入以维持哈希前后局部结构。通过在Stiefel流形上梯度下降联合优化哈希矩阵与二值码，采用曲线搜索策略。哈希后使用字典学习将二值向量编码为词袋，生成最终特征表示。在三个主流动态纹理识别数据集上表现领先：在UCLA达到99.80%（优于DT-GoogleNet的98.93%），在DynTex++达到98.52%（优于HoGF³D的97.63%），在YUPENN达到96.19%（优于STS的95.00%）。源代码已公开于https://github.com/drx770/LP2DH。
原文摘要 · Abstract (English)
Spatiotemporal Local Binary Pattern (STLBP) is a widely used dynamic texture descriptor, but it suffers from extremely high dimensionality. To tackle this, STLBP features are often extracted on three orthogonal planes, which sacrifice inter-plane correlation. In this work, we propose a Locality-Preserving Pixel-Difference Hashing (LP$^{2}$DH) framework that jointly encodes pixel differences in the full spatiotemporal neighbourhood. LP$^{2}$DH transforms Pixel-Difference Vectors (PDVs) into compact binary codes with maximal discriminative power. Furthermore, we incorporate a locality-preserving embedding to maintain the PDVs' local structure before and after hashing. Then, a curvilinear search strategy is utilized to jointly optimize the hashing matrix and binary codes via gradient descent on the Stiefel manifold. After hashing, dictionary learning is applied to encode the binary vectors into codewords, and the resulting histogram is utilized as the final feature representation. The proposed LP$^{2}$DH achieves state-of-the-art performance on three major dynamic texture recognition benchmarks: 99.80% against DT-GoogleNet's 98.93% on UCLA, 98.52% against HoGF$^{3D}$'s 97.63% on DynTex++, and 96.19% compared to STS's 95.00% on YUPENN. The source code is available at: https://github.com/drx770/LP2DH.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。