Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Human Interaction Classification in Sliding Video Windows Using Skeleton Data Tracking and Feature Extraction.

Sensors (Basel, Switzerland)·2023

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 21, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Training Data Extraction and Object Detection in Surveillance Scenario.

Artur Wilkowski¹, Maciej Stefańczyk¹, Włodzimierz Kasprzak¹

¹Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warszawa, Poland.

Sensors (Basel, Switzerland)

|May 14, 2020

Summary

This study introduces a two-stage video analysis system for public security. It efficiently detects objects in surveillance footage using Cascade Classifiers, Support Vector Machines, or Convolutional Neural Networks, ensuring speed and reliability.

Keywords:

CNN SVM cascade classifier few shot learning object detection video surveillance

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Dec 21, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Computer Science
Artificial Intelligence
Image Processing

Background:

Public security relies heavily on video analysis for surveillance, event monitoring, and criminal investigations.
The vast data from surveillance systems necessitates automated processing for efficient object detection and tracking.
Current algorithms face challenges in balancing training speed, detection accuracy, and learning from limited datasets.

Purpose of the Study:

To develop an efficient and reliable two-stage object detection system for video surveillance.
To address the need for automatic data processing in public security applications.
To improve the reconciliation of speed, reliability, and data efficiency in object detection algorithms.

Main Methods:

A two-stage detection approach was implemented, featuring a Cascade Classifier for region proposals.
The second stage utilized either Support Vector Machines (SVMs) or Convolutional Neural Networks (CNNs) for classification.
Object tracking, background-foreground separation (using GrabCut), and sample synthesis were employed for robust training data generation.

Main Results:

The proposed system demonstrated effectiveness and applicability in practical surveillance scenarios.
The two-stage configuration successfully balanced detection speed with high reliability.
The integration of tracking and data synthesis enhanced the detector's performance with limited training data.

Conclusions:

The developed system offers a practical solution for enhancing public space security through automated video analysis.
The hybrid approach combining Cascade Classifiers with SVMs or CNNs provides a robust object detection framework.
The methodology effectively addresses key challenges in real-world surveillance applications, including data volume and training limitations.