Object detection answers 'what is where' by returning a labelled bounding box for every object it finds — person, car, package. It is the most-used CV task in video products and the foundation that tracking, counting, and analytics build on.

Book cover: AI for Video, Volume 6 of the Fora Soft Video Engineering Handbook

The book · Volume 6 of 7

AI for Video: A Complete Guide to Intelligence in Video Products: From Models and Inference to Computer Vision, Speech, Search, and Generative Video

Object detection is the base layer for tracking, counting and analytics, so its misses carry through every feature above it. This volume covers object detection in depth: detectors and bounding boxes, open-vocabulary detection, evaluation with mAP and IoU, and deployment topologies for edge and cloud. Written by Nikolay Sapunov, CEO at Fora Soft.

Read it on Amazon →Kindle & paperback · Fora Soft Video Engineering Handbook

Need object detection that works on your camera angles and lighting?

Send us sample footage and target classes, and we will benchmark detectors on it and recommend one with accuracy, speed and hardware needs. 250+ video products shipped since 2005.

Book a 30-min call →WhatsApp →Email us →