Search research 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

Related Concept Videos

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

Absolute Motion Analysis- General Plane Motion

Absolute Motion Analysis- General Plane Motion

Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

One-Degree-of-Freedom System

One-Degree-of-Freedom System

In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

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

Sort by

Same author

Feature selection of pre-trained shallow CNN using the QLESCA optimizer: COVID-19 detection as a case study.

Applied intelligence (Dordrecht, Netherlands)·2023

Same author

A Hybrid Deep Learning Model for Brain Tumour Classification.

Entropy (Basel, Switzerland)·2022

Same author

Rules embedded harris hawks optimizer for large-scale optimization problems.

Neural computing & applications·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 25, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Optimized deep learning vision system for human action recognition from drone images.

Hussein Samma¹, Ali Salem Bin Sama²

¹SDAIA-KFUPM Joint Research Center for Artificial Intelligence (JRC-AI), King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia.

Multimedia Tools and Applications

|June 26, 2023

Summary

This summary is machine-generated.

This study introduces a lightweight computer vision system using an optimized SqueezeNet backbone and a two-layer particle swarm optimizer (TLPSO) for efficient human action recognition from drone imagery. The system achieves a sevenfold speed increase without accuracy loss.

Keywords:

Deep learning Human action recognition Optimization algorithms SqueezeNet YOLO

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: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Jul 25, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

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: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Area of Science:

Computer Vision
Machine Learning
Optimization Algorithms

Background:

Deep learning vision systems like YOLO often use computationally expensive backbone networks (e.g., ResNet, Inception).
SqueezeNet offers a compressed alternative but was trained for broad object classification, not specific action recognition.
Optimizing feature extraction is crucial for efficient, hardware-limited vision systems.

Purpose of the Study:

To develop a lightweight vision system for human action recognition from drone imagery.
To optimize the SqueezeNet backbone using a novel algorithm for improved efficiency and accuracy.
To evaluate the system's performance in recognizing walking and running behaviors.

Main Methods:

Integration of a two-layer particle swarm optimizer (TLPSO) with YOLO and SqueezeNet.
Utilizing TLPSO to reduce SqueezeNet's convolutional filters for human action recognition.
Dataset comprised 300 drone images (100 running, 200 walking) under varied conditions.

Main Results:

TLPSO reduced SqueezeNet filters by 52%, yielding a sevenfold increase in detection speed.
Achieved an F1 score of 94.65% with an inference time of 0.061 milliseconds.
TLPSO demonstrated superior convergence and fitness compared to PSO and RLMPSO.

Conclusions:

The proposed lightweight vision system effectively recognizes human actions from drone footage with high accuracy and speed.
TLPSO is an efficient algorithm for optimizing convolutional filters in lightweight networks.
The system outperforms previous methods for drone-based human behavior recognition.