Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/96462
標題: 應用嵌入式影像平台於雞隻及位置辨識系統之開發
Recognition System Development for Chicken and Location Using Embedded Imaging Platform
作者: 黃庭彥
Ting-Yen Huang
關鍵字: 禽流感
機器視覺
機器學習
HOG
SVM
Avian Influenza
Machine Vision
Machine Learning
HOG
SVM
引用: 1. 聯合國糧食及農業組織(F.A.O) 。網址:http://www.thepoultrysite.com/focus/global-poultry-trends/2403/global-poultry-trends-asia 上網日期:2015-12-04。 2. 謬紹綱。2003。數位影像處理。台北:全華科技圖書股份有限公司。 3. 徐子建。2007。檬果外部品質線上檢測系統之應用研究。碩士論文。國立中興大學生物產業機電工程學系。 4. 李淵百。1992。臺灣的土雞。國立中興大學畜牧學系。臺中。 5. 蔡祥益。2005。基於機器視覺測重技術的果實分類。碩士論文。國立台灣科技大學。 6. 蘇金樹、張博鋒、徐昕。2006。基於機器學習的文本分類技術研究進展。軟件學報,17(9),1848-1849。 7. 劉光仁。2007。嵌入式路口行人偵測系統設計與實現。碩士論文。國立交通大學。 8. 彭彥松。2010。基於支持向量機的養雞場死雞檢測方法研究。碩 士論文。江蘇大學。 9. 勞鳳丹、騰光輝、李卓、余禮根。2012。機器視覺識別單隻蛋雞行為的方法。農業工程學報,28(24)157-163。 10. 勞鳳丹、騰光輝、李卓、余禮根。2012。複雜環境中蛋雞識別及黏連分離方法研究。農業機器學報,(4), 213-216。 11. 畢敏娜、張鐵民、庄曉霖、楊秀麗、梁莉、焦培榮。2016。基於色差訊息多色彩魔行的黃羽雞快速分割方法。農業機械學報,47(12),293-298。 12. 應義斌、趙匀。2000。機器視覺技術在農產品品質自動識別中的應用(Ⅰ) 。農業工程學報,16(1),103-108。 13. 李騰飛。2016。籠養蛋雞健康行為監測機器人系統研究。博士論文。北京:中國農業大學。 14. 黃國益。2002。應用機器視覺於蝴蝶蘭大苗幾何特徵與病害檢測之研究。博士論文。台中:國立中興大學農業機械工程學研究所。 15. Ahrendt, P., T. Gregersen and H. Karstoft.2011. Development of a real-time computer vision system for tracking loose-housed pigs. Computers and Electronics in Agriculture, 76(2), 169-174. 16. Arróspide, J., L. Salgado and M. Camplani.2013. Image-based on-road vehicle detection using cost-effective histograms of oriented gradients. Journal of Visual Communication and Image Representation, 24(7), 1182-1190. 17. Aydin, A., O. Cangar, S. E. Ozcan, C. Bahr and D. Berckmans.2010. Application of a fully automatic analysis tool to assess the activity of broiler chickens with different gait scores. Computers and Electronics in Agriculture, 73(2), 194-199. 18. Boser, B. E., I. M. Guyon, and V. N. Vapnik.1992. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152). ACM. 19. Burges, C. J. 1998. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121-167. 20. Leroy, T., E. Vranken, A.Van Brecht, E.Struelens, B. Sonck and D.Berckmans, 2006. A computer vision method for on-line behavioral quantification of individually caged poultry. Transactions of the ASABE, 49(3), 795-802. 21. J. B. Cunha.2003.Application of Image Processing Techniques in the Characterization of Plant Leafs, Proc. IEEE Intl' Symposium on Industrial Electronics. 22. OuYang, A. G., R. J. Gao, X. D. Sun, Y. Y. Pan and X. L. Dong.2010.An automatic method for identifying different variety of rice seeds using machine vision technology. In Natural Computation (ICNC), 2010 Sixth International Conference on (Vol. 1, pp. 84-88). IEEE. 23. Cristianini, N. and J. Shawe-Taylor.2004.支持向量機導論(李國正、王猛、曾華軍,譯)。北京:電子工業出版社。(原著第一版出版於2000年) 24. Corkery, G., S. Ward, C. Kenny and P. Hemmingway.2013. Incorporating smart sensing technologies into the poultry industry. Journal of World's Poultry Research, 3(4), 106-128. 25. Chang, C. C. and C. J. Lin.2011. LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 27. 26. Cangar, Ö., T. Leroy, M. Guarino, E. Vranken, R. Fallon, J. Lenehan and D. Berckmans.2008.Automatic real-time monitoring of locomotion and posture behaviour of pregnant cows prior to calving using online image analysis. Computers and electronics in agriculture, 64(1), 53-60. 27. Dalal ,N. and B. Triggs .2005. Histograms of Oriented Gradients for Human Detection. In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. 28. Gerónimo, D., A. Sappa, A.López, and D.Ponsa.2007. Adaptive image sampling and windows classification for on-board pedestrian detection. In Proceedings of the International Conference on Computer Vision Systems, Bielefeld, Germany (Vol. 39). 29. Gavrila, D. M. 2000. Pedestrian detection from a moving vehicle. In European conference on computer vision (pp. 37-49). Springer, Berlin, Heidelberg. 30. Gero´nimo D., A. M. Lo´pez , A. D. Sappa and T. Graf .2010.Survey of Pedestrian Detection for Advanced Driver Assistance Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence . 31. Hussain S. and B. Triggs .2010. Feature sets and dimensionality reduction for visual object detection. In British Machine Vision Conference. 32. Hussain, M., S.K. Wajid, A.Elzaart and M. Berbar. 2011. A comparison of SVM kernel functions for breast cancer detection. In Computer Graphics, Imaging and Visualization (CGIV), 2011 Eighth International Conference on (pp. 145-150). IEEE. 33. Husin, Z., A.Shakaff, A.Aziz, R.Farook, M. Jaafar, U. Hashim, et al.2012.Embedded portable device for herb leaves recognition using image processing techniques and neural network algorithm. Computersand Electronics in Agriculture, 89, 18–29. 34. Keerthi, S. S. and C. J. Lin. 2003. Asymptotic behaviors of support vector machines with Gaussian kernel. Neural computation, 15(7), 1667-1689. 35. Kashiha, M., C. Bahr, S. Ott, C. P. Moons , T. A. Niewold, F. O. Ödberg and D. Berckmans.2013. Automatic identification of marked pigs in a pen using image pattern recognition. Computers and electronics in agriculture, 93, 111-120. 36. Lin, H. T. and C. J. Lin. 2003. A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods. submitted to Neural Computation, 1-32. 37. Hsu, C. W., C. C. Chang and C. J. Lin. 2003. A practical guide to support vector classification. 38. Liu, Y., J. Yao, R. Xie and S. Zhu. 2013. Pedestrian Detection from Still Images Based on Multi-Feature Covariances In Proceeding of the IEEE International Conference on Information and Automation. 39. Marıa, G. A., J. Escós and C. L. Alados.2004.Complexity of behavioural sequences and their relation to stress conditions in chickens (Gallus gallus domesticus): a non-invasive technique to evaluate animal welfare. Applied Animal Behaviour Science, 86(1), 93-104. 40. Neubeck, A.and G. Van , L.2006. Efficient non-maximum suppression. In Pattern Recognition, 2006. ICPR 2006. 18th International Conference on (Vol. 3, pp. 850-855). IEEE. 41. Otsu, N.1979. A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1), 62-66. 42. Pereira, D. F., B. C. Miyamoto, G. D. Maia, G. T. Sales, M. M. Magalhães and R. S. Gates.2013. Machine vision to identify broiler breeder behavior. Computers and electronics in agriculture, 99, 194-199. 43. Ramazani, R. B., H. R. Krishnan, S. E. Bergeson and N. S. Atkinson.2007.Computer automated movement detection for the analysis of behavior. Journal of neuroscience methods, 162(1), 171-179. 44. Rangdal, M. B. and D. B. Hanchate.2014. Animal detection usinghistogram oriented gradient. Int. J. Recent Innov. Trends Comput.Commun, 2(2), 178-183. 45. Sauvola, J.and M. Pietikäinen. 2000. Adaptive document image binarization. Pattern recognition, 33(2), 225-236. 46. Shafait, F., D. Keysers and T. M. Breuel.2008.Efficient implementation of local adaptive thresholding techniques using integral images. DRR, 6815, 681510. 47. Sezgin, M.2004. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic imaging, 13(1), 146-168. 48. Viola, P. and M. J. Jones.2004.Robust Real-Time Face Detection. International Journal of Computer Vision, Vol. 52, No. 2, pp. 137-154. 49. Yadav, R., V. Senthamilarasu, K. Kutty, V. Vaidya and S. Ugale.2015. A review on day-time pedestrian detection (No. 2015-01-0311). SAE Technical Paper. 50. Zhu, Q., S. Avidan, M.-C. Yeh and K.-T. Cheng. 2006. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients.Proc. IEEE International Conference on Computer Vision and Pattern Recognition.
摘要: 近年來禽流感疫情嚴重,雞隻飼養管理人員需要每日觀察雞隻健康狀況,以確保有無疾病或異常行為的個體影響其他雞,由於平飼系統飼養需要更大的空間,在工作時會非常消耗時間和人力,管理人員也應該減少出入量,降低傳病的風險。一般影像處理的系統,大多使用攝影機和影像擷取卡,將影像傳入個人電腦做處理,不但體積大,成本也昂貴,所以本研究主要目的是建立雞隻位置偵測方法再移植進嵌入式系統,以節省人力和成本的消耗。 本研究在雞隻特徵方面選用梯度方向直方圖(Histogram of Oriented Gradient,HOG)計算偵側窗口局部梯度方向和強度的統計值,可以有效的避免複雜的背景和照明。使用徑向基底核函數(Radial basis function kernel,RBF)的支持向量機(Support Vector Machine,SVM)作為機器學習演算法。在影像前處理應用背景相減統計出雞隻活動範圍ROI,降低運算時間和降低誤偵率,在前後的攝影機上,應用預先設置的雞舍座標轉換模型,可以找出雞隻位置。最後現場測試顯示,偵測率有80%以上的水準,正確率達到70%。
In recent years, the outbreak of avian influenza has been so severe that chicken keeping managers need to observe daily the health condition of chickens to ensure that individuals with no disease or abnormal behavior will affect other chickens. Since flat feeding systems require more space for keeping, Time and manpower consumption, managers should also reduce the amount of access, reduce the risk of transmission. Generally, the image processing system mainly uses a camera and an image capture card to transfer images to a personal computer for processing, which is not only bulky and expensive. Therefore, the main purpose of this research is to establish a method for detecting the position of a chicken and then transplanted into an embedded System to save labor and cost of consumption. In this study, Histogram of Oriented Gradient (HOG) was used to calculate the local gradient direction and intensity of the detection window in terms of chicken characteristics, which can effectively avoid complicated background and illumination. Radial basis function kernel (RBF) support vector machine (SVM) is used as a machine learning algorithm. In the image preprocessing application background subtraction statistical chicken ROI range of activity, reducing computing time and reduce the rate of false detection.In the CamFront and CamBack, used the pre-set coop coordinate conversion model, you can find the chicken position. The final field test showed that the detection rate of more than 80% level, the correct rate of 70%.
URI: http://hdl.handle.net/11455/96462
文章公開時間: 2021-02-09
Appears in Collections:生物產業機電工程學系

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.