Detection of Dead Broilers Based on Fusion of Color and Thermal Infrared Image Information
Abstract
In order to improve the accuracy of dead broiler detection in large-scale broiler farms, based on color images and thermal infrared images, two-stage and one-stage dead broiler detection methods for broilers were proposed, respectively. In the two-stage method, the YOLO v11-seg network was firstly used to segment broilers in color images to obtain broiler mask coordinates; then individual broiler thermal infrared images were extracted and classified by using the YOLO v8-cls classification network. In the one-stage method, G-channel replacement fusion images, weighted fusion images, wavelet transform fusion images, and frequency domain transform fusion images were constructed based on color images and registered thermal infrared images. Multi-source fusion image datasets were used to build a dead broiler detection model based on the YOLO v11s object detection network. The results showed that in the two-stage dead broiler detection method, the mAP of broiler instance segmentation was 94.2%, and the classification accuracy of individual broiler thermal infrared images was 99.4%. In the one-stage dead broiler detection method, the model built based on wavelet transform fusion images achieved the highest detection accuracy, with mAP of 93.0%. Compared with the two-stage method, the one-stage detection method had a higher precision rate of 92.3% on the public test set, faster inference speed (6.1 ms/f), and easier to be deployed. Analysis of the temperature distribution of individual broiler thermal infrared images indicated that there were significant differences in body surface temperature distribution between low-age and high-age broilers. The dead broiler detection method proposed can accurately identify dead broilers in the harsh imaging environment under high-density breeding, and it can provide a technical reference for the death detection of other livestock and poultry.
Keywords: dead broiler, thermal infrared image, color image, image registration, YOLO v11
Download Full Text:
PDFReferences
НАО Н, FANG Р, DUAN Е, el al. A dead broiler inspection system for large-scale breeding farms based on deep learning [J]. Agriculture, 2022, 12(8): 1176.
NASIRI A, AMIRIVOJDAN A, ZHAO Y, et al. An automated video action recognition-based system for drinking time estimation of individual broilers [J] . Smart Agricultural Technology, 2024, 7; 100409.
LIU H W, CHEN С H, TSAI Y C, et al. Identifying images of dead chickens with a chicken removal system integrated with a deep learning algorithm[J]. Sensors, 2021 , 21 (11) ; 3579.
LI Q, SI Y, CHU M, et al. A novel lameness detection method for dairy cows based on temporal gait and spatial post features [J] . Computers and Electronics in Agriculture, 2024, 224; 109172.
XIA Yuantian, KOU Xupeng, XUE Hongcheng, et al. Behavior detection algorithm for caged white-feather broilers based on improved YOLO detection framework [J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(11); 103 - 111. (in Chinese)
CHEN Jia, DING Qi'an, LIU Longshen, et al. Early detection of broilers respiratory diseases based on YOLO v5 and short time tracking [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 :271 -279.
WEN Yuchen, ZHAO Yongjie, PU Liuru, et al. Thermal infrared image detection method of (lain1 goat breast region based on improved YOLO v5s model [J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(6) ; 237 -245.
GUO Yanjiao, YANG Shenghui, (-HI Yu, et al. Recognizing mastitis using temperature distribution from thermal infrared images in cow udder regions [J]. Transactions of the CSAE, 2022, 38(2) :250 -259. (in Chinese)
ZHANG Xudong, KANG Xi, MA Li, et al. Automatic detection method of dairy cow mastitis based on thermal infrared image [J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(Supp. ) :248 -255,282. (in Chinese)
HARRIS-BRIDGE G, YOUNG L, HANDEL I, et al. The use of infrared thermography for detecting digital dermatitis in dairy cattle; what is the best measure of temperature and foot location to use? [J]. The Veterinary Journal, 2018, 237: 26 -33.
MACHADO N A F, DA COSTA LBS, BARBOSA-FILHO J A D, et al. Using infrared thermography to detect subclinical mastitis in dairy cows in compost barn systems [J]. Journal of Thermal Biology, 2021 , 97: 102881.
XU Zhiqiang, SHEN Mingxia, LIU Longs hen, et al. Abnormal recognition method of broiler leg based on infrared thermal image [J]. Journal of Nanjing Agricultural University , 2021 , 44(2) ; 384 -393.
DA FONSECA F N, ABE J M, DE ALENCAR NAAS I, et al. Automatic prediction of stress in piglets (Sus scrofa) using infrared skin temperature [J] . Computers and Electronics in Agriculture, 2020, 168: 105148.
JIA Yanlin, XUE Hao, ZHOU Zixuan, et al. Automatic detection method for dead chicken in cage based on infrared thermal imaging technology[J]. Journal of Hebei Agricultural University,2023, 46(3) ; 105 - 112. (in Chinese)
LUO S, MA Y, JIANG F, et al. Dead laying hens detection using TIR - NIK - Depth images and deep learning on a commercial farm[J]. Animals, 2023 , 13( 11): 1861.
HE K, GKIOXARI G, DOLLAR P, et al. Mask R - CNN [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 36(9): 1137 -1149.
BOLYA D, ZHOU C, XIAO F, et al. YOLACT; real-time instance segmentation[С]//IEEE/CVF International Conference on Computer Vision (ICCV) , 2019: 9156 -9165.
WANG X, ZHANG R, KONG T, et al. SOLOv2; dynamic and fast instance segmentation [J]. arXiv e-prints; 2003. 10152,
JJOCHER G, NISHIMURA K, MINEEVA T, et al. YOLOvll [EB/OL]. (2024 - 10 - 11 ) [2024 - 09 - 30]. https: // github. com/ultralytics/ultralytics.
QIN D, LEICHNER C, DELAKIS M, et al. MobileNetV4—universal models for the mobile ecosystem [J]. arXiv: 2404. 10518, 2024.
CAI H, LI J, HU M, et al. EfficientViT; multi-scale linear attention for high-resolution dense prediction [С]/7 IEEE/CVF International Conference on Computer Vision (ICCV) ,2023: 17256 - 17267.
ZHAO Y, LV W, XU S, et al. DETRs beat YOLOs on real-time object detection [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2024; 16965 - 16974.
ZHAO Y, PARAJULI P, et al. Automatic detection of broiler mortality using image processing technology[С]7 10th International Livestock Environment Symposium ( ILES X). American Society of Agricultural and Biological Engineers, 2018.
Refbacks
- There are currently no refbacks.