论文信息 - Vehicle Color Recognition in The Surveillance with DeepConvolutional Neural Networks

Vehicle Color Recognition in The Surveillance with DeepConvolutional Neural Networks

Vehicle information extraction is the key means in Intelligent Transportation System (ITS). Color plays an important role in vehicle recognition. The main challenge of vehicle color recognition is to find the dominant color. In this paper, we propose a color recognition method using convolutional neural network. We train the classifier with the network structure ‘NIN’ to increase the classification accuracy. The experiments are validated on our dataset and extra data, which are collected from city surveillance equipment. The proposed method outperforms other competing color recognition methods.

Jianying Zhou | Jie Shao | Boyang Su | Lin Mei | Xiaoteng Zhang

[1] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2] James Ze Wang,et al. Content-based image retrieval: approaches and trends of the new age , 2005, MIR '05.

[3] Kin-Man Lam,et al. Spectrally Layered Color Indexing , 2002, CIVR.

[4] Wenyu Liu,et al. Vehicle Color Recognition on Urban Road by Feature Context , 2014, IEEE Transactions on Intelligent Transportation Systems.

[5] Andrew Zisserman,et al. Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[6] Cordelia Schmid,et al. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7] Tairui Chen,et al. Going Deeper with Convolutional Neural Network for Intelligent Transportation , 2016 .

[8] Andrew Zisserman,et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[9] Koen E. A. van de Sande,et al. Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10] Wenyu Liu,et al. Feature context for image classification and object detection , 2011, CVPR 2011.

[11] Jitendra Malik,et al. Deformable part models are convolutional neural networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).