Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8

With global climate change and the deterioration of the ecological environment, the safety of hydraulic engineering faces severe challenges, among which soil-dwelling termite damage has become an issue that cannot be ignored. Reservoirs and embankments in China, primarily composed of earth and rocks...

Full description

Saved in:
Bibliographic Details
Main Authors: Peidong Jiang, Lai Jiang, Fengyan Wu, Tengteng Che, Ming Wang, Chuandong Zheng
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212740978704384
author Peidong Jiang
Lai Jiang
Fengyan Wu
Tengteng Che
Ming Wang
Chuandong Zheng
author_facet Peidong Jiang
Lai Jiang
Fengyan Wu
Tengteng Che
Ming Wang
Chuandong Zheng
author_sort Peidong Jiang
collection DOAJ
description With global climate change and the deterioration of the ecological environment, the safety of hydraulic engineering faces severe challenges, among which soil-dwelling termite damage has become an issue that cannot be ignored. Reservoirs and embankments in China, primarily composed of earth and rocks, are often affected by soil-dwelling termites, such as Odontotermes formosanus and Macrotermes barneyi. Identifying soil-dwelling termite damage is crucial for implementing monitoring, early warning, and control strategies. This study developed an improved YOLOv8 model, named MCD-YOLOv8, for identifying traces of soil-dwelling termite activity, based on the Monte Carlo random sampling algorithm and a lightweight module. The Monte Carlo attention (MCA) module was introduced in the backbone part to generate attention maps through random sampling pooling operations, addressing cross-scale issues and improving the recognition accuracy of small targets. A lightweight module, known as dimension-aware selective integration (DASI), was added in the neck part to reduce computation time and memory consumption, enhancing detection accuracy and speed. The model was verified using a dataset of 2096 images from the termite damage survey in hydraulic engineering within Hubei Province in 2024, along with images captured by drone. The results showed that the improved YOLOv8 model outperformed four traditional or enhanced models in terms of precision and mean average precision for detecting soil-dwelling termite damage, while also exhibiting fewer parameters, reduced redundancy in detection boxes, and improved accuracy in detecting small targets. Specifically, the MCD-YOLOv8 model achieved increases in precision and mean average precision of 6.4% and 2.4%, respectively, compared to the YOLOv8 model, while simultaneously reducing the number of parameters by 105,320. The developed model is suitable for the intelligent identification of termite damage in complex environments, thereby enhancing the intelligent monitoring of termite activity and providing strong technical support for the development of termite control technologies.
format Article
id doaj-art-aa72aa03e08344779813dee2cbc2f532
institution OA Journals
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-aa72aa03e08344779813dee2cbc2f5322025-08-20T02:09:17ZengMDPI AGSensors1424-82202025-03-01257219910.3390/s25072199Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8Peidong Jiang0Lai Jiang1Fengyan Wu2Tengteng Che3Ming Wang4Chuandong Zheng5Hubei Water Resources Research Institute, Wuhan 430070, ChinaHubei Water Resources Research Institute, Wuhan 430070, ChinaHubei Water Resources Research Institute, Wuhan 430070, ChinaHubei Water Resources Research Institute, Wuhan 430070, ChinaHubei Water Resources Research Institute, Wuhan 430070, ChinaYangxin County Bureau of Water Resources and Lakes, Huangshi 435200, ChinaWith global climate change and the deterioration of the ecological environment, the safety of hydraulic engineering faces severe challenges, among which soil-dwelling termite damage has become an issue that cannot be ignored. Reservoirs and embankments in China, primarily composed of earth and rocks, are often affected by soil-dwelling termites, such as Odontotermes formosanus and Macrotermes barneyi. Identifying soil-dwelling termite damage is crucial for implementing monitoring, early warning, and control strategies. This study developed an improved YOLOv8 model, named MCD-YOLOv8, for identifying traces of soil-dwelling termite activity, based on the Monte Carlo random sampling algorithm and a lightweight module. The Monte Carlo attention (MCA) module was introduced in the backbone part to generate attention maps through random sampling pooling operations, addressing cross-scale issues and improving the recognition accuracy of small targets. A lightweight module, known as dimension-aware selective integration (DASI), was added in the neck part to reduce computation time and memory consumption, enhancing detection accuracy and speed. The model was verified using a dataset of 2096 images from the termite damage survey in hydraulic engineering within Hubei Province in 2024, along with images captured by drone. The results showed that the improved YOLOv8 model outperformed four traditional or enhanced models in terms of precision and mean average precision for detecting soil-dwelling termite damage, while also exhibiting fewer parameters, reduced redundancy in detection boxes, and improved accuracy in detecting small targets. Specifically, the MCD-YOLOv8 model achieved increases in precision and mean average precision of 6.4% and 2.4%, respectively, compared to the YOLOv8 model, while simultaneously reducing the number of parameters by 105,320. The developed model is suitable for the intelligent identification of termite damage in complex environments, thereby enhancing the intelligent monitoring of termite activity and providing strong technical support for the development of termite control technologies.https://www.mdpi.com/1424-8220/25/7/2199soil-dwelling termite damageimage recognitionlight weightimproved YOLOv8 model
spellingShingle Peidong Jiang
Lai Jiang
Fengyan Wu
Tengteng Che
Ming Wang
Chuandong Zheng
Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
Sensors
soil-dwelling termite damage
image recognition
light weight
improved YOLOv8 model
title Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
title_full Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
title_fullStr Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
title_full_unstemmed Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
title_short Target Detection Method for Soil-Dwelling Termite Damage Based on MCD-YOLOv8
title_sort target detection method for soil dwelling termite damage based on mcd yolov8
topic soil-dwelling termite damage
image recognition
light weight
improved YOLOv8 model
url https://www.mdpi.com/1424-8220/25/7/2199
work_keys_str_mv AT peidongjiang targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8
AT laijiang targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8
AT fengyanwu targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8
AT tengtengche targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8
AT mingwang targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8
AT chuandongzheng targetdetectionmethodforsoildwellingtermitedamagebasedonmcdyolov8