An Object Detection Algorithm based on Deformable Part Models with Bing Features

To solve the problem that the positioning strategy with sliding window approaches requires exhaustive search in feature pyramids, the paper proposes an object detection algorithm based on deformable part models with Bing features to help object detection. First of all, input images are preprocessed with the objectness detection algorithm with Bing features and a set of potential windows that may contain target objects are obtained, and then the deformable part model is regarded as the class-specific detector to match potential windows, at last Non-Maximum Suppression is used to merge and reduce window areas of results to obtain final detection results. The experimental results on Pascal VOC 2007 dataset show that the algorithm in the paper outperforms the original DPM in 19 out of 20 classes, achieving an improvement of 2.7% mAP.

[1]  Pietro Perona,et al.  Strong supervision from weak annotation: Interactive training of deformable part models , 2011, 2011 International Conference on Computer Vision.

[2]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[3]  Ivan Laptev,et al.  Object Detection Using Strongly-Supervised Deformable Part Models , 2012, ECCV.

[4]  Peter V. Gehler,et al.  Multi-View and 3D Deformable Part Models , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Iasonas Kokkinos,et al.  Deformable Part Models with CNN Features , 2014, ECCV 2014.

[6]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Deva Ramanan,et al.  Histograms of Sparse Codes for Object Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Philip H. S. Torr,et al.  BING: Binarized normed gradients for objectness estimation at 300fps , 2019, Computational Visual Media.

[10]  Iasonas Kokkinos,et al.  Segmentation-Aware Deformable Part Models , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.