The MisFit
Our Product has two modules to it. To detect and identify all the PnG products realtime accurately. To detect the empty slots in the racks and to identify the misfits. i.e. Pampers cannot go into the rack where Tide is arranged. We could accurately identify the objects, find the empty slots if any . ...learn more
Project status: Published/In Market
Intel Technologies
Intel Python,
OpenVINO
Overview / Usage
Our Product has two modules to it.
- To detect and identify all the PnG products realtime accurately.
- To detect the empty slots in the racks and to identify the misfits. i.e. Pampers cannot go into the rack where Tide is arranged. We could accurately identify the objects, find the empty slots if any in the rack and we also spot the wrongly fit items into PnG racks.
This help us in smart space optimization, accommodate more items in the shelves appropriately. This also helps the store keepers in refilling the items in time to avoid customers facing challenges.
Methodology / Approach
Implementation - The implementation is out and out with the Deep learning concepts and the Fast RCNN was found the best fit. We get close to 100% accuracy for both the modules.
Results Most of the P&G products belonging to 6 classes are being identified with 99% accuracy, Majority, and Minority classes were found by extracting all the detected regions having more than a certain accuracy threshold and segregating based on the number of objects belonging to different classes in a given frame So we were able to identify the misplaced objects by getting minority classes and localized them. As a next step, we will be finding how many empty slots are thereafter a product has been sold.
Technologies Used
OpenVino, Python, CNN, Fast RCNN
Repository
Collaborators
There are no people to show.