Object localization with mid-level part detectors

详细信息    查看全文

• 作者：Xiaoqin KuangAuthor Vitae ; Nong Sang ; ^{nsang@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Changxin GaoAuthor Vitae
• 关键词：Object detection ; Part models ; Cluster ; LDA ; Feature selection
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：5 November 2016
• 年：2016
• 卷：212
• 期：Complete
• 页码：58-64
• 全文大小：2448 K

文摘

We present a method for object detection combining the effectiveness of a set of mid-level parts. These parts are learned weak-supervised from object bounding box annotations. The approach based part models can handle the detection of objects across changes in viewpoint, intraclass variability and object deformation. The objects are localized by the detected parts with learned information of location and scale. We evaluate the detection method on the standard PASCAL VOC 2007 dataset. Our system is competitive with the state of art in localizing the object.