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

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.

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.

Vector Functions and Motion: Problem Solving

Vector Functions and Motion: Problem Solving

Accurate position tracking is fundamental to the safe and effective operation of unmanned aerial vehicles (UAVs), particularly during precision maneuvers near complex structures. In this scenario, a drone is programmed to perform a high-precision inspection of a vertical structure, starting at position ((x, y, z) = (3, 0, 0)), with an initial velocity oriented in the positive z-direction. The trajectory of the drone is governed by a time-dependent acceleration function a(t), which is predefined...

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.

You might also read

Related Articles

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

Sort by

Same author

A spatiotemporal state-inference framework for adaptive immunotherapy in glioblastoma.

Frontiers in oncology·2026

Same author

Cerenkov radiation modulates the extracellular matrix for improved pancreatic cancer chemotherapy.

Cell biomaterials·2026

Same author

The relationship between digital health literacy, self-efficacy, and self-management behaviors in patients with diabetes-related foot disease: a cross-sectional study.

Frontiers in public health·2026

Same author

A rare case of syphilitic hepatic inflammatory pseudotumor misdiagnosed as liver metastasis: Case report and mini-review.

Medicine·2026

Same author

Interaction between CD82 and integrin αVβ3 selectively regulates collective movement of tumor cells via endolysosomal trafficking.

Cellular and molecular life sciences : CMLS·2026

Same author

Association of diagnostic oral glucose tolerance test values with neonatal hypoglycemia in diet-controlled gestational diabetes mellitus: a retrospective cohort study.

BMC pregnancy and childbirth·2026

Search research articles

Related Experiment Videos

DSPE-ViT: a lightweight vision transformer with dynamic sparse positional encoding for dense small object detection

Liya Cai¹, Shuping Li¹

¹School of Intelligent Management, Suzhou Industrial Park Institute of Services Outsourcing, Suzhou, China.

Frontiers in Neurorobotics

|July 1, 2026

Summary

This study introduces DSPE-ViT, a new Vision Transformer (ViT) model for detecting small objects in drone imagery. The lightweight framework improves accuracy and efficiency for dense object detection tasks.

Keywords:

UAV object detection feature pyramid network lightweight model positional encoding small object detection vision transformer

Related Experiment Videos

Area of Science:

Computer Vision
Machine Learning
Remote Sensing

Background:

Detecting dense, small objects in Unmanned Aerial Vehicle (UAV) imagery is a significant computer vision challenge.
Standard Vision Transformers (ViTs) struggle with high-density small targets due to fixed positional encoding and computational inefficiency.

Purpose of the Study:

To develop a lightweight Vision Transformer (ViT)-based detection framework optimized for dense small object detection in UAV aerial imagery.
To address the limitations of fixed absolute positional encoding and redundant dimensions in ViTs for high-density scenes.

Main Methods:

Introduced the DSPE module with a PE Redundancy Pruner and a Local PE Enhancer for adaptive positional encoding.
Integrated a Small Object Feature Pyramid Network (SmallObjFPN) with SE channel attention and depthwise separable convolutions.
Utilized WIoU v3 loss for refined bounding-box regression of small targets.

Main Results:

DSPE-ViT achieved 43.2% mAP@0.5 on the VisDrone2019-DET dataset with approximately 6.0 M parameters and 15.8 GFLOPs.
Demonstrated strong cross-domain generalization on the SeaDronesSee dataset, achieving 30.1% mAP@0.5 (zero-shot) and 38.4% (fine-tuned).

Conclusions:

The proposed DSPE-ViT framework offers an efficient and effective solution for dense small object detection in UAV imagery.
The lightweight design and adaptive positional encoding enhance generalization capabilities across different aerial datasets.