Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier

How to transfer the trained detector into the target scenarios has been an important topic for a long time in the field of computer vision. Unfortunately, most of the existing transfer methods need to keep source samples or label target samples in the detection phase. Therefore, they are difficult to apply to real applications. For this problem, we propose a framework that consists of a controlled convolutional neural network (CCNN) and a modulating neural network (MNN). In a CCNN, the parameters of the last layer, i.e., the classifier, are dynamically adjusted by a MNN. For each target sample, the CCNN adaptively generates a proprietary classifier. Our contributions include (1) the first detector-based unsupervised transfer method that is very suitable for real applications and (2) a new scheme of a dynamically adjusting classifier in which a new object function is invented. Experimental results confirm that our method can achieve state-of-the-art results on two pedestrian datasets.

[1]  Meng Wang,et al.  Scene-Specific Pedestrian Detection for Static Video Surveillance , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Stephen Gould,et al.  Decomposing a scene into geometric and semantically consistent regions , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Rama Chellappa,et al.  Joint Sparse Representation and Robust Feature-Level Fusion for Multi-Cue Visual Tracking , 2015, IEEE Transactions on Image Processing.

[4]  N. Pettersson,et al.  A new pedestrian dataset for supervised learning , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[5]  Shih-Fu Chang,et al.  Cross-domain learning methods for high-level visual concept classification , 2008, 2008 15th IEEE International Conference on Image Processing.

[6]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[7]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[8]  Meng Wang,et al.  Transferring a generic pedestrian detector towards specific scenes , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, CVPR.

[10]  Meng Wang,et al.  Automatic adaptation of a generic pedestrian detector to a specific traffic scene , 2011, CVPR 2011.

[11]  Jian-Huang Lai,et al.  Supervised Spatio-Temporal Neighborhood Topology Learning for Action Recognition , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  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).

[13]  Vinod Nair,et al.  An unsupervised, online learning framework for moving object detection , 2004, CVPR 2004.

[14]  Bernt Schiele,et al.  Pictorial structures revisited: People detection and articulated pose estimation , 2009, CVPR.

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

[16]  Liam Kilmartin,et al.  Performance optimization for pedestrian detection on degraded video using natural scene statistics , 2014, J. Electronic Imaging.

[17]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Ping Li,et al.  Cross-Domain Person Reidentification Using Domain Adaptation Ranking SVMs , 2015, IEEE Transactions on Image Processing.

[19]  Qingming Huang,et al.  Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness , 2011, IEEE Transactions on Image Processing.

[20]  Karl J. Friston,et al.  Structural and Functional Brain Networks: From Connections to Cognition , 2013, Science.

[21]  Pei Xu,et al.  Domain adaption of vehicle detector based on convolutional neural networks , 2015, International Journal of Control, Automation and Systems.

[22]  Matteo Munaro,et al.  Cost-efficient RGB-D smart camera for people detection and tracking , 2016, J. Electronic Imaging.

[23]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.