Collective motion pattern inference via Locally Consistent Latent Dirichlet Allocation

详细信息    查看全文

• 作者：Jialing Zou^aAuthor Vitae ; Qixiang Ye^aAuthor Vitae ; Yanting Cui^aAuthor Vitae ; Fang Wan^aAuthor Vitae ; Kun Fu^bAuthor Vitae ; Jianbin Jiao^a ; ^{jiaojb@ucas.ac.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Collective motion ; Local motion pattern ; Topic model ; Trajectory clustering
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：5 April 2016
• 年：2016
• 卷：184
• 期：Complete
• 页码：221-231
• 全文大小：14969 K

文摘

Extracting motion descriptors in crowd videos is highly challenging due to scene clutter and serious occlusions. In this paper, Locally Consistent Latent Dirichlet Allocation (LC-LDA) model is proposed to learn collective motion patterns using tracklets and bag-of-words as low level features. The LC-LDA model implements a graph Laplacian operator to impose neighboring constraints to tracklets on a local manifold, which enforces the spatial–temporal coherence of tracklets in a high dimensional bag-of-word feature space. With initialization of clustering on a manifold, LC-LDA model improves the unsupervised inference capability and compactness of learned collective motion patterns. Experimental results on three public datasets indicate that LC-LDA based motion patterns can improve the trajectory clustering performance effectively.