Shape-based foreign body recognition of train roof using invariant moments

Abstract Foreign body recognition of locomotive roof is an important security link. In this paper, a foreign body recognition method is presented based on shape feature matching. Roof images of the inherent devices (without foreign bodies) and those of the running train are processed respectively with the cubic B-spline wavelet edge detection to get multi-scale edge images and segment objects. And thus the invariant moments of each closed area in the edge images are extracted. Then, after calculating the similarity measure by Euclidean distance, we can judge whether the objects are foreign bodies. Test results show that this method can effectively recognize a foreign body in the size of 33 mm × 33 mm.

[1]  Dinggang Shen,et al.  Discriminative wavelet shape descriptors for recognition of 2-D patterns , 1999, Pattern Recognit..

[2]  Rebecca Forsberg,et al.  Inre säkerheten i tåg eftersatt : fallstudie efter tågkraschen i Kimstad , 2012 .

[3]  Michael Unser,et al.  On the asymptotic convergence of B-spline wavelets to Gabor functions , 1992, IEEE Trans. Inf. Theory.

[4]  Kohei Arai,et al.  Visualization of 3D object shape complexity with wavelet descriptor and its application to image retrievals , 2011, Journal of Visualization.

[5]  Meltem Akkaş,et al.  10-year evaluation of train accidents. , 2011, Ulusal travma ve acil cerrahi dergisi = Turkish journal of trauma & emergency surgery : TJTES.

[6]  Michael G. Lenné,et al.  Associations between task, training and social environmental factors and error types involved in rail incidents and accidents. , 2012, Accident; analysis and prevention.

[7]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[8]  Yajun Li,et al.  Reforming the theory of invariant moments for pattern recognition , 1992, Pattern Recognit..

[9]  Daniele D. Giusto,et al.  Detection of foreign bodies in food by thermal image processing , 2004, IEEE Transactions on Industrial Electronics.

[10]  Andrew S McIntosh,et al.  Understanding the human factors contribution to railway accidents and incidents in Australia. , 2008, Accident; analysis and prevention.

[11]  Hong Jeong,et al.  Adaptive Determination of Filter Scales for Edge Detection , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Lei Zhang,et al.  A wavelet-based edge detection method by scale multiplication , 2002, Object recognition supported by user interaction for service robots.

[13]  M. Thali,et al.  Virtopsy: postmortem imaging of laryngeal foreign bodies. , 2009, Archives of pathology & laboratory medicine.

[14]  M. Teague.  Image analysis via the general theory of moments , 1980 .

[15]  M. Luntz,et al.  Three-Dimensional Computed Tomography for Detection and Management of Ingested Foreign Bodies , 2009, Ear, nose, & throat journal.