Indian Institute of Technology Ropar

About: Indian Institute of Technology Ropar is a education organization based out in Ropar, India. It is known for research contribution in the topics: Catalysis & Computer science. The organization has 1014 authors who have published 2878 publications receiving 35715 citations.

Comparative High Temperature Analysis of HVOF-Sprayed and Detonation Gun Sprayed Ni–20Cr Coating in Laboratory and Actual Boiler Environments

Abstract: High-velocity-oxy-fuel (HVOF) spray and detonation-gun (D-gun) spray techniques were used to deposit Ni–20Cr coatings on a commonly used boiler steel ASTM-SAE 213-T22. The specimens, with and without coating, were subjected to molten salt (Na2SO4–60%V2O5) deposition in a laboratory furnace at 900 °C to determine hot-corrosion resistance. Specimens were also exposed to the superheater zone of a thermal power plant boiler at an average temperature of 700 °C under cyclic conditions to ascertain their erosion-corrosion (E-C) behavior. Mass-change measurements were taken to approximate the kinetics of corrosion and erosion-corrosion. In the case of E-C, the thickness lost data were also taken at the end of the exposure. The exposed specimens were characterized by X-ray diffraction (XRD) and field-emission scanning electron microscopy/energy dispersive spectroscopy (FE-SEM/EDS). The HVOF-sprayed coating was found to be intact during exposure to both given environments; whereas the D-gun coating showed spallation of its oxide scale during exposure to the molten salt environments. An overall analysis of the results indicated that the HVOF-sprayed Ni–20Cr coating should be a better choice for the given boiler applications.

MsEDNet: Multi-Scale Deep Saliency Learning for Moving Object Detection

Abstract: Moving object detection (foreground and background) is an important problem in computer vision. Most of the works in this problem are based on background subtraction. However, these approaches are not able to handle scenarios with infrequent motion of object, illumination changes, shadow, camouflage etc. To overcome these, here a two stage robust and compact method for moving object detection (MOD) is proposed. In first stage, to generate the saliency map, background image is estimated using a temporal histogram technique with the help of several input frames. In the second stage, multiscale encoder-decoder network is used to learn multiscale semantic feature of estimated saliency for foreground extraction. The encoder is used to extract multi-scale features from multi-scale saliency map. The decoder part is designed to learn the mapping of low resolution multi-scale features into high resolution output frame. To observe the efficacy of proposed MsEDNet, experiments are conducted on two benchmark datasets (change detection (CDnet-2014) [1] and Wallflower [2]) for MOD. The precision, recall and F-measure are used as performance parameter for comparison with the existing state-of-the-art methods. Experimental results show a significant improvement in detection accuracy and decrement in execution time as compared to the state-of-the-art methods for MOD.