A neural network based method to determine initial object positions for segmentation

This paper presents a new neural network based method for the segmentation of sky from video data collected from a vehicle with a fixed camera position. Using a combination of spatial information, a neural network and thresholding, a high degree of success has been achieved with the images tested. Having the approximate location of the sky allows for an initial starting point for segmentation to be determined. By training a neural network on various sky pixel data, it is possible to find starting locations for thresholding despite the effects of different lighting conditions which significantly affect the colour of the sky in an image. Using this information, thresholds based on colour difference can be employed to discover sky connected pixels. Due to the similar colour of poles to sky, these must then be subtracted from the discovered sky pixels using an edge detection algorithm. The results have been compared with both an SVM and exclusive thresholding technique and comparative analysis is presented in this paper.

[1]  Jun-Seok Oh,et al.  Road sign detection and shape recognition invariant to sign defects , 2012, 2012 IEEE International Conference on Electro/Information Technology.

[2]  H.P. Ng,et al.  Medical Image Segmentation Using K-Means Clustering and Improved Watershed Algorithm , 2006, 2006 IEEE Southwest Symposium on Image Analysis and Interpretation.

[3]  H. Fleyeh,et al.  Color detection and segmentation for road and traffic signs , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[4]  Chung-Hao Chen,et al.  Outdoor Scene Image Segmentation Based on Background Recognition and Perceptual Organization , 2012, IEEE Transactions on Image Processing.

[5]  Jian Li,et al.  Automatic detection of road traffic signs from natural scene images based on pixel vector and central projected shape feature , 2012 .

[6]  Christian Koch,et al.  Pothole detection in asphalt pavement images , 2011, Adv. Eng. Informatics.

[7]  Lipo Wang,et al.  Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[8]  Babette Dellen,et al.  Real-Time Segmentation of Stereo Videos on a Portable System With a Mobile GPU , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Shishir Shah,et al.  Performance Modeling and Algorithm Characterization for Robust Image Segmentation , 2008, International Journal of Computer Vision.

[10]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[11]  Eran A. Edirisinghe,et al.  Road Sign Segmentation based on Colour Spaces: A Comparative Study , 2010 .

[12]  Yok-Yen Nguwi,et al.  Detection and classification of road signs in natural environments , 2008, Neural Computing and Applications.

[13]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[14]  Ashfaqur Rahman,et al.  An hierarchical approach towards road image segmentation , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[15]  Xue Li,et al.  A Neural Network based Technique for Automatic Classification of Road Cracks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[16]  Antonio Criminisi,et al.  TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context , 2007, International Journal of Computer Vision.

[17]  M. Benallal,et al.  Real-time color segmentation of road signs , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[18]  Ouahiba Azouaoui,et al.  Road intersection detection and classification using hierarchical SVM classifier , 2014, Adv. Robotics.