{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T08:59:06Z","timestamp":1768726746489,"version":"3.49.0"},"reference-count":59,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The characteristics of chicken droppings are closely linked to their health status. In prior studies, chicken droppings recognition is treated as an object detection task, leading to challenges in labeling and missed detection due to the diverse shapes, overlapping boundaries, and dense distribution of chicken droppings. Additionally, the use of intelligent monitoring equipment equipped with edge devices in farms can significantly reduce manual labor. However, the limited computational power of edge devices presents challenges in deploying real-time segmentation algorithms for field applications. Therefore, this study redefines the task as a segmentation task, with the main objective being the development of a lightweight segmentation model for the automated monitoring of abnormal chicken droppings. A total of 60 Arbor Acres broilers were housed in 5 specific pathogen-free cages for over 3\u00a0wk, and 1650 RGB images of chicken droppings were randomly divided into training and testing sets in an 8:2 ratio to develop and test the model. Firstly, by incorporating the attention mechanism, multi-loss function, and auxiliary segmentation head, the segmentation accuracy of the DDRNet was enhanced. Then, by employing the group convolution and an advanced knowledge-distillation algorithm, a lightweight segmentation model named DDRNet-s-KD was obtained, which achieved a mean Dice coefficient (mDice) of 79.43% and an inference speed of 86.10 frames per second (FPS), showing a 2.91% and 61.2% increase in mDice and FPS compared to the benchmark model. Furthermore, the DDRNet-s-KD model was quantized from 32-bit floating-point values to 8-bit integers and then converted to TensorRT format. Impressively, the weight size of the quantized model was only 13.7 MB, representing an 82.96% reduction compared to the benchmark model. This makes it well-suited for deployment on the edge device, achieving an inference speed of 137.51 FPS on Jetson Xavier NX. In conclusion, the methods proposed in this study show significant potential in monitoring abnormal chicken droppings and can provide an effective reference for the implementation of other agricultural embedded systems.<\/jats:p>","DOI":"10.1093\/jas\/skae098","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T13:16:33Z","timestamp":1712582193000},"source":"Crossref","is-referenced-by-count":4,"title":["An efficient segmentation model for abnormal chicken droppings recognition based on improved deep dual-resolution network"],"prefix":"10.1093","volume":"102","author":[{"given":"Pengguang","family":"He","sequence":"first","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Dou","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khawar","family":"Hayat","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Shang","sequence":"additional","affiliation":[{"name":"Dandong Ruifeng Animal Pharmaceutical Co., Ltd , Dandong, Liaoning 118000 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinming","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjian","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Biosystems Engineering and Food Science, Zhejiang University , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture , Hangzhou, Zhejiang 310058 ,","place":["China"]},{"name":"Ministry of Agriculture and Rural Affairs, Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province , Hangzhou, Zhejiang 310058 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,4,8]]},"reference":[{"key":"2024102315173725300_CIT0001","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1007\/s00521-019-04296-5","article-title":"Interpretation of intelligence in CNN-pooling processes: a methodological survey","volume":"32","author":"Akhtar","year":"2020","journal-title":"Neural Comput. Appl"},{"key":"2024102315173725300_CIT0002","first-page":"JST-S0111-2016","article-title":"Binary classification using SVM for sick and healthy chicken based on chicken\u2019s excrement image","volume":"25","author":"Aziz","year":"2017","journal-title":"Pertanika J. Sci. Technol"},{"key":"2024102315173725300_CIT0003","first-page":"4413","article-title":"The lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks","author":"Berman","year":"2018"},{"key":"2024102315173725300_CIT0004","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2024102315173725300_CIT0005","first-page":"969","article-title":"Research on salt body recognition based on DeepLab V3 combined with auxiliary classifier and attention module","author":"Cheng","year":"2022"},{"key":"2024102315173725300_CIT0006","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"2024102315173725300_CIT0007","first-page":"9716","article-title":"Rethinking bisenet for real-time semantic segmentation","author":"Fan","year":"2021"},{"key":"2024102315173725300_CIT0008","doi-asserted-by":"crossref","first-page":"100123","DOI":"10.1016\/j.animal.2020.100123","article-title":"Review: mitigating the risks posed by intensification in livestock production: the examples of antimicrobial resistance and zoonoses","volume":"15","author":"Gilbert","year":"2021","journal-title":"Animal"},{"key":"2024102315173725300_CIT0009","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis"},{"key":"2024102315173725300_CIT0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3487045","article-title":"Compression of deep learning models for text: a survey","volume":"16","author":"Gupta","year":"2022","journal-title":"ACM Trans. Knowl. Discovery Data"},{"key":"2024102315173725300_CIT0011","doi-asserted-by":"crossref","first-page":"5601","DOI":"10.3390\/app12115601","article-title":"Research progress in the early warning of chicken diseases by monitoring clinical symptoms","volume":"12","author":"He","year":"2022","journal-title":"Appl. Sci"},{"key":"2024102315173725300_CIT0012","first-page":"2101.06085v2","article-title":"Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes","author":"Hong","year":"2021"},{"key":"2024102315173725300_CIT0013","doi-asserted-by":"crossref","first-page":"3450","DOI":"10.3390\/ani12243450","article-title":"A high-precision method for 100-day-old classification of chickens in edge computing scenarios based on federated computing","volume":"12","author":"Huang","year":"2022","journal-title":"Animals"},{"key":"2024102315173725300_CIT0014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3508391","article-title":"Tensorrt-based framework and optimization methodology for deep learning inference on jetson boards","volume":"21","author":"Jeong","year":"2022","journal-title":"ACM Trans. Embedded Comput. Syst"},{"key":"2024102315173725300_CIT0015","first-page":"487","author":"Jiang","year":"2021"},{"key":"2024102315173725300_CIT0016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3531479","article-title":"A low-power programmable machine learning hardware accelerator design for intelligent edge devices","volume":"27","author":"Kee","year":"2022","journal-title":"ACM Trans. Des. Autom. Electron. Syst"},{"key":"2024102315173725300_CIT0017","first-page":"2304.02643v1","article-title":"Segment anything","volume-title":"arXiv preprint arXiv","author":"Kirillov","year":"2023"},{"key":"2024102315173725300_CIT0018","doi-asserted-by":"crossref","first-page":"106695","DOI":"10.1016\/j.compag.2022.106695","article-title":"ChickenNet\u2014an end-to-end approach for plumage condition assessment of laying hens in commercial farms using computer vision","volume":"194","author":"Lamping","year":"2022","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0019","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1017\/S1751731119002155","article-title":"Review: automated techniques for monitoring the behaviour and welfare of broilers and laying hens: towards the goal of precision livestock farming","volume":"14","author":"Li","year":"2020","journal-title":"Animal"},{"key":"2024102315173725300_CIT0020","first-page":"17413","article-title":"Automated knowledge distillation via Monte Carlo tree search","author":"Li","year":"2023"},{"key":"2024102315173725300_CIT0021","doi-asserted-by":"crossref","first-page":"11463","DOI":"10.1109\/JSEN.2022.3174251","article-title":"Lightweight residual convolutional neural network for soybean classification combined with electronic nose","volume":"22","author":"Lin","year":"2022","journal-title":"IEEE Sens. J"},{"key":"2024102315173725300_CIT0022","first-page":"3999","article-title":"1xN pattern for pruning convolutional neural networks","volume":"45","author":"Lin","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2024102315173725300_CIT0023","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"2024102315173725300_CIT0024","first-page":"1755","article-title":"A hybrid model of ghost-convolution enlightened transformer for effective diagnosis of grape leaf disease and pest","volume":"34","author":"Lu","year":"2022","journal-title":"J. King Saud Univ. Comput. Informat. Sci"},{"key":"2024102315173725300_CIT0025","doi-asserted-by":"crossref","first-page":"733345. (Article)","DOI":"10.3389\/frai.2022.733345","article-title":"Poultry diseases diagnostics models using deep learning","volume":"5","author":"Machuve","year":"2022","journal-title":"Front. Artif. Intell"},{"key":"2024102315173725300_CIT0026","doi-asserted-by":"crossref","first-page":"105100","DOI":"10.1016\/j.compag.2019.105100","article-title":"Ability evaluation of a voice activity detection algorithm in bioacoustics: a case study on poultry calls","volume":"168","author":"Mahdavian","year":"2020","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0027","doi-asserted-by":"crossref","first-page":"107517","DOI":"10.1016\/j.compag.2022.107517","article-title":"Real-time fruit detection using deep neural networks on CPU (RTFD): an edge AI application","volume":"204","author":"Mao","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0028","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.biosystemseng.2023.01.021","article-title":"Identification of aflatoxin-poisoned broilers based on accelerometer and machine learning","volume":"227","author":"Mei","year":"2023","journal-title":"Biosyst. Eng"},{"key":"2024102315173725300_CIT0029","author":"MMdeploy Contributors","year":"2021"},{"key":"2024102315173725300_CIT0030","author":"MMrazor Contributors","year":"2021"},{"key":"2024102315173725300_CIT0031","author":"MMsegmentation Contributors","year":"2020"},{"key":"2024102315173725300_CIT0032","doi-asserted-by":"crossref","first-page":"3041","DOI":"10.3390\/ani13193041","article-title":"Towards early poultry health prediction through non-invasive and computer vision-based dropping classification","volume":"13","author":"Nakrosis","year":"2023","journal-title":"Animals"},{"key":"2024102315173725300_CIT0033","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.biosystemseng.2019.09.015","article-title":"A machine vision system for early detection and prediction of sick birds: a broiler chicken model","volume":"188","author":"Okinda","year":"2019","journal-title":"Biosyst. Eng"},{"key":"2024102315173725300_CIT0034","doi-asserted-by":"crossref","first-page":"105704","DOI":"10.1016\/j.compag.2020.105704","article-title":"Cluster index for estimating thermal poultry stress (gallus gallus domesticus)","volume":"177","author":"Pereira","year":"2020","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0035","doi-asserted-by":"crossref","first-page":"105216","DOI":"10.1016\/j.compag.2020.105216","article-title":"Agricultural robotics research applicable to poultry production: a review","volume":"169","author":"Ren","year":"2020","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0036","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"2024102315173725300_CIT0037","doi-asserted-by":"crossref","first-page":"117181","DOI":"10.1016\/j.eswa.2022.117181","article-title":"Enhancement of neural networks with an alternative activation function tanhLU","volume":"199","author":"Shen","year":"2022","journal-title":"Expert Syst. Appl"},{"key":"2024102315173725300_CIT0038","first-page":"5311","article-title":"Channel-wise knowledge distillation for dense prediction","author":"Shu","year":"2021"},{"key":"2024102315173725300_CIT0039","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/JPROC.2022.3226481","article-title":"Efficient acceleration of deep learning inference on resource-constrained edge devices: a review","volume":"111","author":"Shuvo","year":"2023","journal-title":"Proc. IEEE"},{"key":"2024102315173725300_CIT0040","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"2024102315173725300_CIT0041","doi-asserted-by":"crossref","first-page":"108319","DOI":"10.1016\/j.compag.2023.108319","article-title":"Research on white feather broiler health monitoring method based on sound detection and transfer learning","volume":"214","author":"Sun","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0042","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"2024102315173725300_CIT0043","doi-asserted-by":"crossref","first-page":"108000","DOI":"10.1016\/j.compag.2023.108000","article-title":"An efficient multi-task convolutional neural network for dairy farm object detection and segmentation","volume":"211","author":"Tian","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0044","first-page":"1185","article-title":"Comparing performance of machine learning tools across computing platforms","author":"Vicente","year":"2023"},{"key":"2024102315173725300_CIT0045","first-page":"1","article-title":"Recognition and classification of broiler droppings based on deep convolutional neural network","volume":"2019","author":"Wang","year":"2019","journal-title":"J. Sens"},{"key":"2024102315173725300_CIT0046","doi-asserted-by":"crossref","first-page":"1047077","DOI":"10.3389\/fphy.2022.1047077","article-title":"The estimation of broiler respiration rate based on the semantic segmentation and video amplification","volume":"10","author":"Wang","year":"2022","journal-title":"Front. Phys"},{"key":"2024102315173725300_CIT0047","first-page":"1","article-title":"Fused adaptive receptive field mechanism and dynamic multiscale dilated convolution for side-scan sonar image segmentation","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"2024102315173725300_CIT0048","first-page":"3","article-title":"Cbam: convolutional block attention module","author":"Woo","year":"2018"},{"key":"2024102315173725300_CIT0049","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","article-title":"Cgnet: a light-weight context guided network for semantic segmentation","volume":"30","author":"Wu","year":"2020","journal-title":"IEEE Trans. Image Process"},{"key":"2024102315173725300_CIT0050","doi-asserted-by":"crossref","first-page":"107131","DOI":"10.1016\/j.compag.2022.107131","article-title":"Information perception in modern poultry farming: a review","volume":"199","author":"Wu","year":"2022","journal-title":"Comput. Electron. Agric"},{"key":"2024102315173725300_CIT0051","first-page":"38087","article-title":"SmoothQuant: accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2023"},{"key":"2024102315173725300_CIT0052","doi-asserted-by":"crossref","first-page":"100269","DOI":"10.1016\/j.animal.2021.100269","article-title":"Classification of broiler behaviours using triaxial accelerometer and machine learning","volume":"15","author":"Yang","year":"2021","journal-title":"Animal"},{"key":"2024102315173725300_CIT0053","doi-asserted-by":"crossref","first-page":"100692","DOI":"10.1016\/j.animal.2022.100692","article-title":"Modeling gait score of broiler chicken via production and behavioral data","volume":"17","author":"Yang","year":"2023","journal-title":"Animal"},{"key":"2024102315173725300_CIT0054","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","article-title":"Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation","volume":"129","author":"Yu","year":"2021","journal-title":"Int. J. Comput. Vis"},{"key":"2024102315173725300_CIT0055","first-page":"106342","article-title":"A method of cotton root segmentation based on edge devices","volume":"14","author":"Yu","year":"2023","journal-title":"Front. Plant Sci"},{"key":"2024102315173725300_CIT0056","doi-asserted-by":"crossref","first-page":"106342","DOI":"10.1016\/j.cropro.2023.106342","article-title":"YOLOv5s-CBAM-DMLHead: a lightweight identification algorithm for weedy rice (Oryza sativa f. spontanea) based on improved YOLOv5","volume":"172","author":"Yuan","year":"2023","journal-title":"Crop Prot"},{"key":"2024102315173725300_CIT0057","doi-asserted-by":"crossref","first-page":"9528","DOI":"10.1109\/TNNLS.2022.3151138","article-title":"DualConv: dual convolutional kernels for lightweight deep neural networks","volume":"34","author":"Zhong","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst"},{"key":"2024102315173725300_CIT0058","first-page":"2011","article-title":"Exploring TensorRT to Improve Real-Time Inference for Deep Learning","author":"Zhou","year":"2022"},{"key":"2024102315173725300_CIT0059","first-page":"243","article-title":"Detection of abnormal chicken droppings based on improved faster R-CNN","volume":"16","author":"Zhou","year":"2023","journal-title":"Int. J. Agric. Biol. Eng"}],"container-title":["Journal of Animal Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jas\/advance-article-pdf\/doi\/10.1093\/jas\/skae098\/57182640\/skae098.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skae098\/60005114\/skae098.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skae098\/60005114\/skae098.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T15:18:29Z","timestamp":1729696709000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jas\/article\/doi\/10.1093\/jas\/skae098\/7642165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1093\/jas\/skae098","relation":{},"ISSN":["0021-8812","1525-3163"],"issn-type":[{"value":"0021-8812","type":"print"},{"value":"1525-3163","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1,1]]},"published":{"date-parts":[[2024,1,1]]},"article-number":"skae098"}}