Object Detection based on Convolutional Neural Network

In this paper, we develop a new approach for detecting multiple objects from images based on convolutional neural networks (CNNs). In our model, we first adopt the edge box algorithm to generate region proposals from edge maps for each image, and perform forward passing of all the proposals through a fine-tuned CaffeNet model. Then we get the CNNs score for each proposal by extracting the output of softmax which is the last layer of CNN. Next, the proposals are merged for each class independently by the greedy nonmaximum suppression (NMS) algorithm. At last, we evaluate the mean average precision (mAP) for each class. The mAP of our model on PASCAL 2007 test dataset is 37.38%. We also discuss how to further improve the performance based on our model in this paper.

[1]  Alexei A. Efros,et al.  Ensemble of exemplar-SVMs for object detection and beyond , 2011, 2011 International Conference on Computer Vision.

[2]  Cordelia Schmid,et al.  Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[4]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[5]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[7]  Dumitru Erhan,et al.  Deep Neural Networks for Object Detection , 2013, NIPS.

[8]  장윤희,et al.  Y. , 2003, Industrial and Labor Relations Terms.

[9]  Derek Hoiem,et al.  Diagnosing Error in Object Detectors , 2012, ECCV.

[10]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[11]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

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

[13]  Xiaogang Wang,et al.  DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection , 2014, ArXiv.

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

[15]  Derek Hoiem,et al.  Category Independent Object Proposals , 2010, ECCV.

[16]  Cristian Sminchisescu,et al.  CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.