Build a model that detects Intruders(humans)
- The purpose of this notebook is to build model capable of detecting intruders
- The algorithm of choice here is YOLOV7 and we would be using it to detect humans(intruders)
- Details of the Problem Statement , Data Set , Data Pre-processing & Splits, Architecture/Algorithm , Summary of the Code/Solution , Sample Output/Prediction from the program and Final Result of the project are listed in the sections to follow.
Computer vision can be used to pro-actively detect intruders
NA
Surveillance
NA
YOLOV7 by https://github.com/WongKinYiu/yolov7
The code aims at running YOLOV7 out of the box on intruder images and capture results
- The YOLOV7 API used in this notebook is @https://github.com/WongKinYiu/yolov7 by WonkinYui
- In this notebook we firsy explore/Sanity test on YOLOV7 API as is and run some general inferences
- The task at hand is to use YOLOV7 to detect intruders. YOLOV7 has been pre-trained on a dataset where 'human' or 'person' is already present as a class.Therefore , we can use YOLOV7 out of the box for intruder detection, we do not need to custom train it on 'human' data
- We then Publish scores
- Run a couple of inferences on images
Here are a couple of Sample Ouput images from the program/model .
NA