Two-stream fusion edge detection network

This thesis introduces a method to combine static and dynamic features in a convolutional neural network (CNN) to produce a motion and object boundary prediction map. This approach provides the CNN with dynamic and static cues and information, thus improving its predictions. The spatial stream of the CNN learns to compute an object boundary prediction map from a single RGB frame, while the temporal stream learns to compute a motion boundary prediction map from the corresponding optical ow map. The streams are then combined through an encoder-decoder architecture, where the decoder learns to fuse the features from both streams to obtain a task specific output. The proposed method yields state-of-the-art results on a motion boundaries benchmark, and systematic improvements in object boundaries benchmarks over methods that solely rely on static features extracted from a single RGB frame.

Two-stream fusion edge detection network

This thesis introduces a method to combine static and dynamic features in a convolutional neural network (CNN) to produce a motion and object boundary prediction map. This approach provides the CNN with dynamic and static cues and information, thus improving its predictions. The spatial stream of the CNN learns to compute an object boundary prediction map from a single RGB frame, while the temporal stream learns to compute a motion boundary prediction map from the corresponding optical ow map. The streams are then combined through an encoder-decoder architecture, where the decoder learns to fuse the features from both streams to obtain a task specific output. The proposed method yields state-of-the-art results on a motion boundaries benchmark, and systematic improvements in object boundaries benchmarks over methods that solely rely on static features extracted from a single RGB frame.

Vibration of a Segmented Rod

This paper presents the governing equation of motion, boundary conditions and exact vibration frequencies of a segmented rod where the segments are connected by hinges with elastic rotational springs of constant stiffness. The mass of each segment is assumed to be evenly distributed along the length of the rod. Another discrete model called Hencky bar-chain model (short for HBM; which is equivalent to the finite difference model for discretizing continuous rod) assumes the rod mass to be lumped at the ends instead and a different set of boundary conditions are adopted clamped end. The vibration results of a clamped–clamped segment rod are compared with those of the HBM. It is shown that the HBM underestimates the vibration frequencies when compared to the segmented rod model for a finite number of segments while both models furnish vibration solutions that converge to the solutions of Euler beam for infinitely large number of segments.