光电工程
光電工程
광전공정
Opto-Electronic Engineering
2015年
9期
21-27
,共7页
目标识别%深度学习%无监督学习%非线性处理%稀疏编码
目標識彆%深度學習%無鑑督學習%非線性處理%稀疏編碼
목표식별%심도학습%무감독학습%비선성처리%희소편마
object recognition%deep learning%unsupervised learning%nonlinear processing%sparse coding
针对行人分类中常见的光照条件、形体变化以及遮挡等多种因素,对特征提取过程造成了很大的阻碍.本文提出一种基于稀疏编码的分层特征提取方法.该方法采用前向预测函数训练最优的稀疏编码,在深度卷积网络模型的框架下以卷积预测稀疏分解算法(CPSD)分别对两层模型进行无监督学习,将两层的特征融合起来,最后采用支持向量机算法实现行人分类.实验结果表明,该文特征学习方法对行人分类的有效性,对比同类方法性能有明显提升.
針對行人分類中常見的光照條件、形體變化以及遮擋等多種因素,對特徵提取過程造成瞭很大的阻礙.本文提齣一種基于稀疏編碼的分層特徵提取方法.該方法採用前嚮預測函數訓練最優的稀疏編碼,在深度捲積網絡模型的框架下以捲積預測稀疏分解算法(CPSD)分彆對兩層模型進行無鑑督學習,將兩層的特徵融閤起來,最後採用支持嚮量機算法實現行人分類.實驗結果錶明,該文特徵學習方法對行人分類的有效性,對比同類方法性能有明顯提升.
침대행인분류중상견적광조조건、형체변화이급차당등다충인소,대특정제취과정조성료흔대적조애.본문제출일충기우희소편마적분층특정제취방법.해방법채용전향예측함수훈련최우적희소편마,재심도권적망락모형적광가하이권적예측희소분해산법(CPSD)분별대량층모형진행무감독학습,장량층적특정융합기래,최후채용지지향량궤산법실현행인분류.실험결과표명,해문특정학습방법대행인분류적유효성,대비동류방법성능유명현제승.
In pedestrian classification, there are many factors, such as light changes, posture changes and occlusion problems etc, which brings many difficulties for feature extraction process. A hierarchical feature method is put forward based on sparse coding. The method trains optimal sparse coding with forward prediction function, and then learns the two levels networks one by one in unsupervised manner with Convolution Predictive Sparse Decomposition algorithm (CPSD) under framework of the deep convolution network model. Then we make the feature fusion. Finally, we implement classification with SVM algorithm. Experimental results demonstrate the effectiveness of our method for pedestrian classification, which has significant performance improvement compared with similar methods.