Semi-supervised and Deep learning Frameworks for Video Classification and Key-frame Identification

TL;DR

This paper introduces two semi-supervised deep learning frameworks that automate scene classification and key-frame extraction in videos, significantly reducing manual effort and enabling scalable training of perception systems.

Contribution

It presents novel rule-based and deep learning-based methods for automated scene and key-frame identification in videos, improving efficiency and scalability.

Findings

Achieved 64-93% accuracy in scene categorization.

Filtered less than 10% of frames as key-frames.

Framework scalable to large video datasets.

Abstract

Automating video-based data and machine learning pipelines poses several challenges including metadata generation for efficient storage and retrieval and isolation of key-frames for scene understanding tasks. In this work, we present two semi-supervised approaches that automate this process of manual frame sifting in video streams by automatically classifying scenes for content and filtering frames for fine-tuning scene understanding tasks. The first rule-based method starts from a pre-trained object detector and it assigns scene type, uncertainty and lighting categories to each frame based on probability distributions of foreground objects. Next, frames with the highest uncertainty and structural dissimilarity are isolated as key-frames. The second method relies on the simCLR model for frame encoding followed by label-spreading from 20% of frame samples to label the remaining frames for scene and lighting categories. Also, clustering the video frames in the encoded feature space further isolates key-frames at cluster boundaries. The proposed methods achieve 64-93% accuracy for automated scene categorization for outdoor image videos from public domain datasets of JAAD and KITTI. Also, less than 10% of all input frames can be filtered as key-frames that can then be sent for annotation and fine tuning of machine vision algorithms. Thus, the proposed framework can be scaled to additional video data streams for automated training of perception-driven systems with minimal training images.