Efficient object detection using convolutional neural network-based hierarchical feature modeling. Issue 8 (November 2016)

• Record Type: Journal Article
• Authors: Lee, Byungjae; Erdenee, Enkhbayar; Jin, Songguo; Rhee, Phill
• Is Part Of: Signal, image and video processing. Volume 10:Issue 8(2016)
• Page Start: 1503
• Page End: 1510
• Publication Date: 2016-11
• Subjects: Object detection -- Deep learning -- Convolutional neural network -- Hierarchical feature modeling; Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-016-0962-x
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract A hierarchical data-driven object detection framework is addressed considering a deep feature hierarchy of object appearances. The performance of many object detectors is degraded due to ambiguities in inter-class appearances and variations in intra-class appearances, but deep features extracted from visual objects show a strong hierarchical clustering property. Deep features were partitioned into unsupervised super-categories at the inter-class level, and augmented categories at the object level, to discover deep feature-driven information. A hierarchical feature model is built using a latent topic model algorithm, assembling a one-versus-all support vector machine at each node to constitute a hierarchical classification ensemble. Extensive experiments show that the proposed method is superior to state-of-the-art techniques using the PASCAL VOC 2007 and VOC 2012 datasets.