MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection

Addressing the paucity of automated systems for the detection of dead poultry within large-scale agricultural settings, characterized by the onerous and time-consuming manual inspection processes, this study introduces an enhanced YOLO algorithm with multi-source image fusion (MIF-YOLO) for the auto...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiapan Li, Yan Zhang, Yong Zhang, Hongwei Shi, Xianfang Song, Chao Peng
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525003375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849421786764017664
author Jiapan Li
Yan Zhang
Yong Zhang
Hongwei Shi
Xianfang Song
Chao Peng
author_facet Jiapan Li
Yan Zhang
Yong Zhang
Hongwei Shi
Xianfang Song
Chao Peng
author_sort Jiapan Li
collection DOAJ
description Addressing the paucity of automated systems for the detection of dead poultry within large-scale agricultural settings, characterized by the onerous and time-consuming manual inspection processes, this study introduces an enhanced YOLO algorithm with multi-source image fusion (MIF-YOLO) for the autonomous identification of dead chicken. The proposed approach commences with the application of progressive illumination-ware fusion (PIA Fusion) to amalgamate thermal infrared and visible-light imagery, thereby accentuating the salient features indicative of dead chickens and counteracting the impact of non-uniform illumination. To address the challenge of feature extraction under conditions of significant occlusion, the model incorporates the Rep-DCNv3 module, which augments the backbone network's capacity to discern subtle characteristics of dead chickens. Additionally, an exponential moving average (EMA) attention mechanism is strategically embedded within the YOLO algorithm architecture's neck region to bolster the model's ability to discern targets under low-light scenarios, enhancing both its accuracy rates and adaptability. The loss function of the model is refined through the implementation of Modified Partial Distance-IoU (MPDIoU), facilitating a more nuanced evaluation of the overlap of objects. Validated against a dataset comprising caged white-feathered chickens procured from a farm in Suqian, Jiangsu Province, the empirical findings indicate that the model attains a precision of 99.2% and a mAP@0.5 metric of 98.9%, surpassing the performance of existing cutting-edge methodologies. The innovative detection methodology for dead chickens ensures not only rapid detection, but also marked improvement in detection fidelity, aligning with the demands of real-time monitoring in operational agricultural contexts.
format Article
id doaj-art-db2ca76b82b44f3d91aaf239e520d5c7
institution Kabale University
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-db2ca76b82b44f3d91aaf239e520d5c72025-08-20T03:31:23ZengElsevierSmart Agricultural Technology2772-37552025-12-011210110410.1016/j.atech.2025.101104MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken DetectionJiapan Li0Yan Zhang1Yong Zhang2Hongwei Shi3Xianfang Song4Chao Peng5The School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, ChinaSuqian University, Suqian, 223800, Jiangsu Province, China; Jiangsu Province Engineering Research Center of Smart Poultry Farming and Intelligent Equipment, Suqian University, Suqian, 223800, Jiangsu Province, China; Corresponding authors at: Suqian University, Suqian, 223800, Jiangsu Province, China; China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, China.The School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, China; Corresponding authors at: Suqian University, Suqian, 223800, Jiangsu Province, China; China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, China.The School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, ChinaThe School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, ChinaThe School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221008, Jiangsu Province, ChinaAddressing the paucity of automated systems for the detection of dead poultry within large-scale agricultural settings, characterized by the onerous and time-consuming manual inspection processes, this study introduces an enhanced YOLO algorithm with multi-source image fusion (MIF-YOLO) for the autonomous identification of dead chicken. The proposed approach commences with the application of progressive illumination-ware fusion (PIA Fusion) to amalgamate thermal infrared and visible-light imagery, thereby accentuating the salient features indicative of dead chickens and counteracting the impact of non-uniform illumination. To address the challenge of feature extraction under conditions of significant occlusion, the model incorporates the Rep-DCNv3 module, which augments the backbone network's capacity to discern subtle characteristics of dead chickens. Additionally, an exponential moving average (EMA) attention mechanism is strategically embedded within the YOLO algorithm architecture's neck region to bolster the model's ability to discern targets under low-light scenarios, enhancing both its accuracy rates and adaptability. The loss function of the model is refined through the implementation of Modified Partial Distance-IoU (MPDIoU), facilitating a more nuanced evaluation of the overlap of objects. Validated against a dataset comprising caged white-feathered chickens procured from a farm in Suqian, Jiangsu Province, the empirical findings indicate that the model attains a precision of 99.2% and a mAP@0.5 metric of 98.9%, surpassing the performance of existing cutting-edge methodologies. The innovative detection methodology for dead chickens ensures not only rapid detection, but also marked improvement in detection fidelity, aligning with the demands of real-time monitoring in operational agricultural contexts.http://www.sciencedirect.com/science/article/pii/S2772375525003375Dead chicken featuresExponential moving averageImage fusionMIF-YOLO
spellingShingle Jiapan Li
Yan Zhang
Yong Zhang
Hongwei Shi
Xianfang Song
Chao Peng
MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
Smart Agricultural Technology
Dead chicken features
Exponential moving average
Image fusion
MIF-YOLO
title MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
title_full MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
title_fullStr MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
title_full_unstemmed MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
title_short MIF-YOLO: An Enhanced YOLO with Multi-Source Image Fusion for Autonomous Dead Chicken Detection
title_sort mif yolo an enhanced yolo with multi source image fusion for autonomous dead chicken detection
topic Dead chicken features
Exponential moving average
Image fusion
MIF-YOLO
url http://www.sciencedirect.com/science/article/pii/S2772375525003375
work_keys_str_mv AT jiapanli mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection
AT yanzhang mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection
AT yongzhang mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection
AT hongweishi mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection
AT xianfangsong mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection
AT chaopeng mifyoloanenhancedyolowithmultisourceimagefusionforautonomousdeadchickendetection