sanchit2843/Videoclassification
Crime detection in cctv footage using deep learning
Implements SlowFast Networks for action recognition across 8 crime categories (abuse, assault, arson, etc.) on the UCF-Crime dataset. Preprocesses videos by extracting 16-frame sequences with frame-skipping and data augmentation to generate 10x training samples. Achieves 99% training accuracy by combining frames into single inputs to optimize data transfer during training on PyTorch.
No commits in the last 6 months.
Stars
99
Forks
23
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 17, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sanchit2843/Videoclassification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Pavankunchala/Work-Showcase
Deep Learning and Computer Vision Applications using Streamlit
sumedh2424/Suspicious-Activity-Detection
Proposing a novel machine learning-based approach for real-time suspicious activity detection in...
oliverbravery/3D-Print-Sentinel
Docker-based 3D print monitoring with Home Assistant, OctoPrint, machine learning and featuring...
amurto/gearstalk
Textile Detection from CCTV Surveillance videos
kivancgunduz/expiration-date-detection
An API that detect expiration date from the product package's picture based on Deep Learning Algorithms