Method and system for determining pipeline flow in non-editable schematic illustration

A system for determining pipeline flow in a non-editable schematic illustration, comprising:

• a processor;
• and
• a memory communicatively coupled to the processor (104), wherein the memory stores processor-executable instructions, which, on execution, cause the processor (104) to:
• detect a set of object-region of interests (object-ROIs) corresponding to a plurality of object-entities in the non-editable schematic illustration (300) and associated entity metadata from the set of object-ROIs using an object detection technique, wherein the entity metadata comprises object orientation information, class label information, and object location information associated to each of the set of object-ROIs;
• determine entity classification information by classifying one or more of the set of object-ROIs as one of a plurality of predefined child-classes based on the class label information of a corresponding object-ROI using a Deep Learning (DL) model;
• determine a set of lines based on determination of a skeletonized image of the non-editable schematic illustration, using an image processing technique, wherein the set of lines are determined based on a determination of a set of vertical lines and a set of horizontal lines;
• determine position information of each of the set of lines;
• determine one or more horizontal line clusters by clustering each of the set of horizontal lines based on the corresponding position information of each of the set of horizontal lines;
• determine one or more vertical line clusters by clustering each of the set of vertical lines based on the corresponding position information of each of the set of vertical lines;
• determine one or more pipeline nodes based on a determination of a line intersection between at least one of the set of vertical lines with at least one of the set of horizontal lines;
• for each of the set of lines:
• determine one or more intersection nodes based on intersection of a corresponding line and at least one of the set of object-ROIs;
• and
• classify each of the one or more intersection nodes as one of:
• a source node or a sink node based on:
• determination of a flow direction of the corresponding line;
• and
• the entity classification information of the at least one of the set of object-ROIs;
• create a directed graph based on the one or more horizontal line clusters, the one or more vertical line clusters, the one or more pipeline nodes and the classification of each of the one or more intersection nodes of each of the set of lines;
• and
• determine the pipeline flow in the non-editable schematic illustration by determining a set of flow-paths based on the directed graph.

A non-transitory computer-readable medium storing computer-executable instructions for determining pipeline flow in a non-editable schematic illustration, the computer-executable instructions configured for:

• detecting a set of object-region of interests (object-ROIs) corresponding to a plurality of object-entities in the non-editable schematic illustration and associated entity metadata from the set of object-ROIs using an object detection technique,
• wherein the entity metadata comprises object orientation information, class label information, and object location information associated to each of the set of object-ROIs;
• determining entity classification information by classifying one or more of the set of object-ROIs as one of a plurality of predefined child-classes based on the class label information of a corresponding object-ROI using a Deep Learning (DL) model;
• determining a set of lines based on determination of a skeletonized image of the non-editable schematic illustration, using an image processing technique, wherein the set of lines are determined based on a determination of a set of vertical lines and a set of horizontal lines;
• determining position information of each of the set of lines;
• determining, one or more horizontal line clusters by clustering each of the set of horizontal lines based on the corresponding position information of each of the set of horizontal lines;
• determining one or more vertical line clusters by clustering each of the set of vertical lines based on the corresponding position information of each of the set of vertical lines;
• determining, one or more pipeline nodes based on a determination of a line intersection between at least one of the set of vertical lines with at least one of the set of horizontal lines;
• for each of the set of lines:
• determining one or more intersection nodes based on intersection of a corresponding line and at least one of the set of object-ROIs;
• and
• classifying each of the one or more intersection nodes as one of:
• a source node or a sink node based on:
• determination of a flow direction of the corresponding line;
• and
• the entity classification information of the at least one of the set of object-ROIs;
• creating a directed graph based on the one or more horizontal line clusters, the one or more vertical line clusters, the one or more pipeline nodes and the classification of each of the one or more intersection nodes of each of the set of lines;
• and
• determining the pipeline flow in the non-editable schematic illustration by determining a set of flow-paths based on the directed graph.