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

Search research articles

Related Experiment Video

Updated: May 28, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

SLP-Net: A Dual-Level Contrastive Learning Framework with Stripe Attention for Elongated Pepper Detection in Complex

Jiangquan Zeng¹, Jiangzhang Zhu², Guoxiong Zhou²

¹College of Computer and Mathematics, Central South University of Forestry and Technology, Changsha 410004, China.

Plants (Basel, Switzerland)

|May 27, 2026

Summary

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

Multimodal collaborative UAV framework for single rubber tree parsing.

Plant phenomics (Washington, D.C.)·2026

Same author

Advances in Artificial Intelligence for Plant Research.

Plants (Basel, Switzerland)·2026

Same author

Sparse-MoE-SAM: A Lightweight Framework Integrating MoE and SAM with a Sparse Attention Mechanism for Plant Disease Segmentation in Resource-Constrained Environments.

Plants (Basel, Switzerland)·2025

Same author

DKWM-XLSTM: A Carbon Trading Price Prediction Model Considering Multiple Influencing Factors.

Entropy (Basel, Switzerland)·2025

Same author

KBNet: A Language and Vision Fusion Multi-Modal Framework for Rice Disease Segmentation.

Plants (Basel, Switzerland)·2025

Same author

Detection of Pine Wilt Disease in UAV Remote Sensing Images Based on SLMW-Net.

Plants (Basel, Switzerland)·2025

SLP-Net enhances pepper detection in challenging field conditions by preserving shape cues, improving accuracy for slender or partially obscured fruits. This novel approach offers greater stability and reliability in complex agricultural settings.

Area of Science:

Computer Vision
Agricultural Technology
Machine Learning

Background:

Accurate pepper detection in field images is hindered by fruit appearance variations, partial occlusion by leaves, and challenges with slender or incomplete contours.
Existing detection models struggle with the geometric variability and occlusions common in agricultural environments.

Purpose of the Study:

To develop a robust pepper detection system, SLP-Net, designed to maintain performance in cluttered field scenes.
To improve localization accuracy for peppers with varying shapes and visibility.

Main Methods:

SLP-Net was designed to preserve crucial shape cues, avoiding increased model complexity.
The network focuses on maintaining detection integrity despite weakened shape information in occluded or incomplete views.

Keywords:

contrastive learning elongated object detection pepper detection

Related Experiment Videos

Last Updated: May 28, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Main Results:

SLP-Net demonstrated superior performance over existing detectors on the PP-Set dataset, especially at higher Intersection over Union (IoU) thresholds and for small targets.
Similar performance improvements were noted on the CH-Set, which includes diseased and deformed peppers with significant background interference.

Conclusions:

SLP-Net offers enhanced stability for pepper detection amidst variations in geometry, surface condition, and visibility.
The model's design effectively addresses the challenges of detecting peppers in complex, real-world agricultural scenarios.