MaskRCNN is the state of art for image segmentation. Here is a well done git repository that tells you all about it https://github.com/matterport/Mask_RCNN, (we suggest you read it fully)
We will do a deep learning problem on FMCG dataset available in the public domain. You are expected to create deep learning model(s) that can detect multiple products from shelf images and classify them into different categories as given in the dataset. Detected products should be categorized into 4 categories, mentioned in the dataset. In the dataset, all images are divided in 4 folders, where folder name is the category of all products inside that folder. Bounding box coordinates for each product are also provided, that can be used for detecting product from shelf images. You also need to calculate the quantity of that particular product or product category in the image or shop.
Note: We expect you to use MaskRCNN but feel free to use other DL models as well
(1) Object dataset (2) Annotated dataset
Please submit your solutions with test results (input and output images)