Method(s) and system(s) for vehicular cargo management
A method for identifying a position of an object in a cargo space includes identifying a region of interest (ROI) from a field of view of the cargo space being captured by a camera, where the camera captures at least one of depth and color of the field of view, extracting a plurality of planes from the ROI, where the plurality of planes correspond to a geometry of the object, clustering similar and nearby planes, where the clustering is based on a weight of two or more planes of the plurality of planes and where the weight is assigned based on a property of orthogonality and a property of dimensions of two or more planes of the plurality of planes, modelling a multi-dimensional bounding box corresponding to the object based on the clustered planes, and identifying a position of the object based on a position of the multi-dimensional bounding box.
1. A method for identifying a position of an object in a cargo space, comprising the steps of:
identifying a region of interest (ROI) from a field of view of the cargo space being captured by one or more cameras, wherein the one or more cameras capture at least one of depth and color of the field of view;
extracting a plurality of planes from the ROI, wherein the plurality of planes correspond to a geometry of the object;
clustering similar and nearby planes, wherein the clustering is based on a weight of two or more planes of the plurality of planes, and wherein the weight is assigned based on a property of orthogonality and a property of dimensions of two or more planes of the plurality of planes;
modelling a multi-dimensional bounding box corresponding to the object based on the clustered planes; and
identifying a position of the object based on a position of the multi-dimensional bounding box, wherein the weight assigned based on the property of orthogonality is more than the weight assigned based on the property of dimensions of the two or more planes of the plurality of planes.
2. The method as claimed in claim 1 , wherein the object comprises a parcel or other objects inside the cargo space and wherein a deep neural network identifies the parcel from the other objects.
3. A system for identifying a position of an object in a cargo space, comprising:
an identification unit configured to identify a region of interest (ROI) from a field of view of the cargo space being captured by one or more cameras, wherein the one or more cameras capture at least one of depth or color of the field of view;
an extraction unit configured to extract a plurality of planes from the ROI, wherein the plurality of planes correspond to a geometry of the object;
a clustering unit configured to cluster similar and nearby planes, wherein the clustering is based on a weight of two or more planes of the plurality of planes, and wherein the weight is assigned based on a property of orthogonality and a property of dimensions of two or more planes of the plurality of planes;
a model generation unit configured to model a multi-dimensional bounding box corresponding to the object based on the clustered planes; and
a position identification unit configured to identify a position of the object based on a position of the multi-dimensional bounding box, wherein the weight assigned based on the property of orthogonality is more than the weight assigned based on the property of dimensions of the two or more planes of the plurality of planes.
4. The system as claimed in claim 3 , wherein the position identification unit is configured to identify a change in the position of the object based on modelling of the modelled multi-dimensional bounding box at a different position.
5. The system as claimed in claim 3 further comprising a transceiver configured to transmit position information corresponding to the identified position of the object to a device.