Active Contours have been widely acknowledged for providing a dependable solution to complex image segmentation problems which are represented as a functional optimization problem. Inhomogeneous image intensity regions present difficulties… Click to show full abstract
Active Contours have been widely acknowledged for providing a dependable solution to complex image segmentation problems which are represented as a functional optimization problem. Inhomogeneous image intensity regions present difficulties for the evolving curve, which are driven by nonlinear variations in a region’s intensity pixels. The problem was approached using the local region’s statistical information for improving the segmentation accuracies. However, the local information of the region was calculated using the inhomogeneous pixel intensities, which in turn degrade the segmentation outputs. In this paper, we approach this problem by introducing a weakly supervised shape image (WSSI), which form a pre-defied shape term within a local window and a local region difference term to improve the segmentation results. The proposed model is robust to image intensity variations and are computationally efficient on high-resolution images. To test and validate the proposed active contour model, we choose a real-time application, Automated Rolling Stock Examination using computer vision. The problem here is to extract the bogie parts using the proposed method to monitor their conditional health on a moving train from the captured high speed video sequence. We have created the bogie dataset with five trains at different time zones using a 240fps sports action camera in full HD mode. We apply our proposed method on these video frames to segment 10 vital parts of the train bogie on a 10000-frame video sequence per train. The proposed method has been compared with similar state-of-the-art localized region based active contour methods for segmentation accuracy.
               
Click one of the above tabs to view related content.