I am trying to allocate object detection (bounding box) results from YOLO/CNN to spreadsheet data.
Let's suppose we are working with images that contain a car and a pedestrian. First, I have manual object identification data of the type of car (color and sedan or SUV or truck) and pedestrians (women, men, boy, girl) of each image in CSV file. Then, how would I allocate the CSV file data to the bounding box of the car and pedestrian of each image accordingly?
Basically, I am trying to make a multi-labeled image that contains a label from object detection (car and pedestrian) plus csv data( color and type of the car and sex of pedestrian ). Can anyone provide some idea to start with or similar tutorial/work that I can follow?