Abstract: A method for monitoring a gauge uses a machine learning model that was previously trained based on a set of training data to classify relative indicator positions between any pair of gauge images. The method receives an input indicative of a first reference gauge value and a first gauge image. The method classifies, using the machine learning model, the indicator position on the first gauge image relative to the indicator position on a first reference gauge image associated with the first reference gauge value and provides an output having a first value indicative of the indicator position of the first gauge image being on a first side of the indicator position of the first reference gauge image and a second value indicative of the indicator position of the first gauge image being on a second side of the indicator position of the first reference gauge image.

Abstract: A method for monitoring a gauge uses a machine learning model that was previously trained based on a set of training data to classify relative indicator positions between any pair of gauge images. The method receives an input indicative of a first reference gauge value and a first gauge image. The method classifies, using the machine learning model, the indicator position on the first gauge image relative to the indicator position on a first reference gauge image associated with the first reference gauge value and provides an output having a first value indicative of the indicator position of the first gauge image being on a first side of the indicator position of the first reference gauge image and a second value indicative of the indicator position of the first gauge image being on a second side of the indicator position of the first reference gauge image.

Abstract: The present invention provides a system and method to align and merge differently exposed digital images to create a HDR image. In the present system, all the modules starting from the receiving module to fusion module are configured to produce a HDR image with better color purity and sharpness. Each captured image in the system is configured to operate in the HSI color space. The alignment module is configured to align the pixels of each image in a pyramid shaped resolution structure to derive alignment vectors for one or more regional partitions of each image across one or more levels of the pyramid. The system is configured such that, the saturation component in the HSI color space is used to pick the color purity of pixels and intensity channel is used to weigh the sharpness of pixels of each of the differently exposed captured images.

Abstract: The present invention relates to system and method for minimizing motion artifacts during the fusion of an image bracket based on preview frame analysis. The system 100 mainly comprises a preview frame capture module 101 to render preview image frames typically invariant in exposure, focus and other related capture parameters at video rate. The system 100 also comprises a scene dynamic range assessment module 103 to assess the extent of dynamism of scene subjects and intensity expanse by sampling the scene at periodic intervals through preview image frames. The system 100 uses the calculated measure of dynamism and intensity distribution to control the parameters used for detecting and preventing motion artifacts during the fusion of subsequently captured bracket of images nuanced in capture parameters such as exposure or focus.

Abstract: The present invention provides a system and method to align and merge differently exposed digital images to create a HDR image. In the present system, all the modules starting from the receiving module to fusion module are configured to produce a HDR image with better colour purity and sharpness. Each captured image in the system is configured to operate in the HSI colour space. The alignment module is configured to align the pixels of each image in a pyramid shaped resolution structure to derive alignment vectors for one or more regional partitions of each image across one or more levels of the pyramid. The system is configured such that, the saturation component in the HSI colour space is used to pick the colour purity of pixels and intensity channel is used to weigh the sharpness of pixels of each of the differently exposed captured images.