LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection

Cigarette detection is a crucial component of public safety management. However, detecting such small objects poses significant challenges due to their size and limited feature points. To enhance the accuracy of small target detection, we propose a novel small object detection model, LSOD-YOLOv8 (Li...

Full description

Saved in:
Bibliographic Details
Main Authors: Yijie Huang, Huimin Ouyang, Xiaodong Miao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/7/3961
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738554057424896
author Yijie Huang
Huimin Ouyang
Xiaodong Miao
author_facet Yijie Huang
Huimin Ouyang
Xiaodong Miao
author_sort Yijie Huang
collection DOAJ
description Cigarette detection is a crucial component of public safety management. However, detecting such small objects poses significant challenges due to their size and limited feature points. To enhance the accuracy of small target detection, we propose a novel small object detection model, LSOD-YOLOv8 (Lightweight Small Object Detection using YOLOv8). First, we introduce a lightweight adaptive weight downsampling module in the backbone layer of YOLOv8 (You Only Look Once version 8), which not only mitigates information loss caused by conventional convolutions but also reduces the overall parameter count of the model. Next, we incorporate a P2 layer (Pyramid Pooling Layer 2) in the neck of YOLOv8, blending the concepts of shared convolutional information and independent batch normalization to design a P2-LSCSBD (P2 Layer-Lightweight Shared Convolutional and Batch Normalization-based Small Object Detection) detection head. Finally, we propose a new loss function, WIMIoU (Weighted Intersection over Union with Inner, Multi-scale, and Proposal-aware Optimization), by combining the ideas of WiseIoU (Wise Intersection over Union), InnerIoU (Inner Intersection over Union), and MPDIoU (Mean Pairwise Distance Intersection over Union), resulting in a significant accuracy improvement without any loss in performance. Our experiments demonstrate that LSOD-YOLOv8 enhances detection accuracy for cigarette detection specifically.
format Article
id doaj-art-2eb6db6a2f0b45248e7f4ee65b161732
institution DOAJ
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2eb6db6a2f0b45248e7f4ee65b1617322025-08-20T03:06:31ZengMDPI AGApplied Sciences2076-34172025-04-01157396110.3390/app15073961LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette DetectionYijie Huang0Huimin Ouyang1Xiaodong Miao2The School of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, ChinaThe School of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, ChinaThe School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211816, ChinaCigarette detection is a crucial component of public safety management. However, detecting such small objects poses significant challenges due to their size and limited feature points. To enhance the accuracy of small target detection, we propose a novel small object detection model, LSOD-YOLOv8 (Lightweight Small Object Detection using YOLOv8). First, we introduce a lightweight adaptive weight downsampling module in the backbone layer of YOLOv8 (You Only Look Once version 8), which not only mitigates information loss caused by conventional convolutions but also reduces the overall parameter count of the model. Next, we incorporate a P2 layer (Pyramid Pooling Layer 2) in the neck of YOLOv8, blending the concepts of shared convolutional information and independent batch normalization to design a P2-LSCSBD (P2 Layer-Lightweight Shared Convolutional and Batch Normalization-based Small Object Detection) detection head. Finally, we propose a new loss function, WIMIoU (Weighted Intersection over Union with Inner, Multi-scale, and Proposal-aware Optimization), by combining the ideas of WiseIoU (Wise Intersection over Union), InnerIoU (Inner Intersection over Union), and MPDIoU (Mean Pairwise Distance Intersection over Union), resulting in a significant accuracy improvement without any loss in performance. Our experiments demonstrate that LSOD-YOLOv8 enhances detection accuracy for cigarette detection specifically.https://www.mdpi.com/2076-3417/15/7/3961lightweight small object detectionpyramid pooling layer 2shared convolutionalbatch normalizationloss functiondetection accuracy
spellingShingle Yijie Huang
Huimin Ouyang
Xiaodong Miao
LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
Applied Sciences
lightweight small object detection
pyramid pooling layer 2
shared convolutional
batch normalization
loss function
detection accuracy
title LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
title_full LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
title_fullStr LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
title_full_unstemmed LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
title_short LSOD-YOLOv8: Enhancing YOLOv8n with New Detection Head and Lightweight Module for Efficient Cigarette Detection
title_sort lsod yolov8 enhancing yolov8n with new detection head and lightweight module for efficient cigarette detection
topic lightweight small object detection
pyramid pooling layer 2
shared convolutional
batch normalization
loss function
detection accuracy
url https://www.mdpi.com/2076-3417/15/7/3961
work_keys_str_mv AT yijiehuang lsodyolov8enhancingyolov8nwithnewdetectionheadandlightweightmoduleforefficientcigarettedetection
AT huiminouyang lsodyolov8enhancingyolov8nwithnewdetectionheadandlightweightmoduleforefficientcigarettedetection
AT xiaodongmiao lsodyolov8enhancingyolov8nwithnewdetectionheadandlightweightmoduleforefficientcigarettedetection