Source: Deep Learning on Medium
Identifying Out-Of-Stock & misplaced/ disarranged products on Grocery Shelves in Real Time
Grocery Store or Big marts lose a good part of business due to 2 reasons:
- Product Out of Stock: Products that are out of stock on shelves, but available in the stores is a missed opportunity. Manual process of checking stock is labour intensive and time consuming.
- Product Misplaced: Often misplaced product or disarranged product can cost money for business specially in high end fashion outlets where everything needs to be perfect.
A deep learning based Model to detect out of stock or misplaced product in real time. It allows the real time monitoring and helps in pin-pointing these issue which results in better customer experience and more business for Store or Mart.
- Using a CCTV, continuous video stream is getting captured.
- The live stream is being passed to the model.
- The model using that live video predicting Out of stock and misplaced items and showing them as output.
- System alerts like SMS can be triggered alerting the right person to fix the situation.
Example images from our solution:
Technical Approach :
We are using state of Art Deep learning based model and using custom data-set from our nearest mart.
- Architecture: Retina-net with Res-net-101 as Backbone.
- Loss Function: Focal Loss
- Data-Set: Custom Data-set collected from 20 minutes video of our nearest local mart .
- Image Size Used: Trained on 128×128, 256×256 ,512×512 and 600×600 size images using gradual resizing to achieve higher accuracy and better generalization of the model.