计算机工程与设计
計算機工程與設計
계산궤공정여설계
COMPUTER ENGINEERING AND DESIGN
2014年
7期
2536-2540
,共5页
杨国亮%漆娟娟%高萌
楊國亮%漆娟娟%高萌
양국량%칠연연%고맹
步态识别%步态光流图%HS算法%组稀疏约束%局部平滑稀疏约束
步態識彆%步態光流圖%HS算法%組稀疏約束%跼部平滑稀疏約束
보태식별%보태광류도%HS산법%조희소약속%국부평활희소약속
gait recognition%gait optical flow image%HS algorithm%group sparsity constraint representation%local smooth sparsity constraint
提出一种局部约束组稀疏表示的步态识别方法。通过预处理提取人体二值化侧影图，计算步态周期并利用HS （Horn-Schunck）算法生成步态光流图，经降维后利用局部约束组稀疏表示的方法进行分类识别。在标准稀疏表示分类方法的基础上，引入了组稀疏约束和局部平滑稀疏约束，使其最小重构误差的非零重构系数分散在与测试样本相邻的同一训练类别组内。在CASIA Dataset B数据库上的实验结果表明，该方法有较高的识别率。
提齣一種跼部約束組稀疏錶示的步態識彆方法。通過預處理提取人體二值化側影圖，計算步態週期併利用HS （Horn-Schunck）算法生成步態光流圖，經降維後利用跼部約束組稀疏錶示的方法進行分類識彆。在標準稀疏錶示分類方法的基礎上，引入瞭組稀疏約束和跼部平滑稀疏約束，使其最小重構誤差的非零重構繫數分散在與測試樣本相鄰的同一訓練類彆組內。在CASIA Dataset B數據庫上的實驗結果錶明，該方法有較高的識彆率。
제출일충국부약속조희소표시적보태식별방법。통과예처리제취인체이치화측영도，계산보태주기병이용HS （Horn-Schunck）산법생성보태광류도，경강유후이용국부약속조희소표시적방법진행분류식별。재표준희소표시분류방법적기출상，인입료조희소약속화국부평활희소약속，사기최소중구오차적비령중구계수분산재여측시양본상린적동일훈련유별조내。재CASIA Dataset B수거고상적실험결과표명，해방법유교고적식별솔。
A locality constrained group sparse representation for human gait recognition was presented.First a preprocess tech-nique was used to segment the human silhouette from the walking videos,then gait period was calculated and gait optical flow image was generated by HS algorithm,after dimension reduction,the GFI was classified using locality constrained group sparse representation.The method introduced group sparsity constraint and local smooth sparsity constraint based on standard sparse representation classification algorithm.Experiments with CASIA Dataset B showed that the method outperformed several other gait recognition methods.
