Object detection: two-stage vs one-stage (Faster R-CNN, YOLO ideas)

Object detection: find it and draw the box

Classification answers “what”. Detection answers “what and where”: find every object in the image and draw a bounding box with a class label around each. That is harder in principle—the count is unknown, objects vary in size, and they may overlap. In a decade, methods went from RCNN (2013, ~47 s per frame) to YOLOv8 (2023, ~160 FPS).

Full content is available with a subscription.

Get full access to all courses on the platform for one year with a single payment.

Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.