摘要
无论是为了提高鲜蛋出口,还是进行禽蛋的纵深加工,都必须对禽蛋进行清洗、消毒、检测和分级。而目前在完成这些工作方面,我国多数企业仍沿用人工作业,无论是在加工质量方面,还是在加工效率方面,我们与发达国家都存在较大差距。在美国,禽蛋的采集、保鲜、分级、包装均采用机械操作,自动化程度高,成本低。
本系统的工作原理是首先由场景摄像机采集蛋的群体图像,经过图像处理,提取每枚蛋的中心坐标和长轴方向等特征值,将该数据经过坐标变换和机器人运动逆解,获得机器人关节运动量,机器人末端执行器运动到蛋的中心位置,调整位姿,发送信号给末端执行器吸盘单片机控制器,启动真空吸附气路,将蛋吸取。机器人根据运动规划,将蛋搬运到蛋壳敲击装置上方,蛋壳被敲击发出声音,麦克风采集该声音信号,送DSP系统处理,识别破损蛋,将识别结果传递给机器人运动控制器,如果是破损蛋,就放到破损蛋蛋箱;如果不是破损蛋,机械手运动到灯箱和彩色摄像头之间,获得蛋内容物彩色图像,经过图像处理,按反映蛋新鲜度的哈夫值与蛋芯颜色HSI之间的关系模型进行模式识别,并按新鲜度分级,将分级信息传递给机器人运动控制器,控制机械手将蛋放入相应等级的蛋箱中。
本文使用图像一阶矩与像素总面积的比作为每枚蛋中心在图像坐标系下的坐标,采用线性标定方法转换到绝对坐标系下,使用二维平面上与最小惯量轴同方向的最小二阶矩轴为蛋的长轴。使用最佳阈值变换和二维零均值离散高斯函数平滑处理,通过多次图像的腐蚀与膨胀,进行图像分割,并采用四连通成分序贯算法,对图像中的连通成分(同一个蛋的区域)进行标记。使用边界跟踪计算蛋的周长,从而得到区域的密集度,用于修正蛋的大小计算。对以上内容在理论研究的基础上,得出的相应算法,能够满足引导机器人准确定位每枚蛋的工作要求。
为了让机械手准确将蛋吸取,通过大量的矩阵变换,将蛋中心的绝对坐标和长轴方向解算到机械人各关节转角,即运动逆解;为了在一次吸放蛋运动过程中完成全部检测和分级工作,对机器人进行运动轨迹规划,将检测和分级工作中机器人运动始点和终点都是变化的这一复杂过程简化为始点变化终点固定(从吸起到破损检测)、始点终点都固定(从破损检测到品质检测)和始点固定终点变化(从品质检测到放下)三段,这种
Whether for the export of fresh eggs or for egg processing, it is necessary to clean out, antisepticise, detect and grade eggs. At present, most processing plants in China are still employing manual eyes in fulfilling these tasks; as a result, there is a remarkable gap between China and developed countries both in processing quality and in efficiency. In the US, mechanical operation is applied to the collection, preservation, grading and packing of eggs, which is highly automatized and less costly.
The principles of the system are as follows. First, a scene video camera captures the image of the massive members of eggs. Through image processing, the character extraction of the central coordinate, the major axis direction, etc. of each egg is used to obtain motion angles of the robot joints by coordinate transformation and kinematic inverse computation of the data. A robot end-effector then moves to the center of the egg, coordinates its pose, transmits signals to SCM controller of the suction cup, starts the suction circuit, and then adsorbs the egg. According to the motion planning, the robot carries the egg to the top of the knocking device. The eggshell is knocked and the sound is collected by a microphone and sent to DSP for processing and diagnosing eggs' dilapidation, and the signals of the result are sent to a robot motion controller. If it is cracked, the egg will be put in the eggcrate for cracked eggs. Otherwise, the manipulator will carry the egg to the place between the light room and color camera. The interior color image of the egg is captured and processed. The depth of greenness of eggs is judged and graded by the formula of connection between Haugh, which reflects the depth of greenness of eggs, and HIS of color in yolk. According to the grading information the robot motion controller controls the manipulator to put the eggs in corresponding eggcrate.
In this paper, the ratio between one rank moments in image and total area
引文
[1] 张新焕,阎新华,杨德刚,陶江.中国畜牧业发展的时空演变及趋势分析.干旱区地理,2003,26(3)
[2] 谢承光,杨长锁.实施国际化战略促进中国禽蛋业中国禽蛋业进一步升级.中国家禽2003,25(19)
[3] 刘桂珍,石有龙.前三季度畜牧业生产形势分析.中国牧业通讯,2004,12
[4] 宁欣.禽蛋的分级、检测与包装.中国家禽,2004,26(12)
[5]. Gunasekaran S, Cooper T M, Berlage A G, etal. Image processing for stress cracks in corn kernels. Trans of the ASAE, 1988, 31(1): 257~263
[6]. Zayas I, Converse H, Steele J. Discrimination of whole from broken corn kernelswith image analysis. Trans of the ASAE, 1990, 33(5): 1642~1646
[7] Delwiche M J, Tang S, Thompson J F. Prune defect detection by line-scan imaging. Trans of the ASAE, 1990, 33(3): 950~954
[8] Elster R T, Goodrum J W. Detection of cracks in eggs using machine vision. Trans of the ASAE, 1991, 34(1): 307~312
[9] Liao K, Reid J J, Ni B, etal. Cornkernel shape identification by machine vision using aneural network classifier. ASAEPaper, 1992. 92~7017
[10] Rigney M P, Brusew itz G H, Kranzler G A. A sparagus defect in spection with machine vision. Trans of the ASAE, 1992, 35(6): 1873~1878
[11] Sarkar N, Wolfe R R. Image processing for tomato grading. Trans of the ASAE, 1990, 33(4): 564~572
[12] Shearer S A, Payne F A. Color and defect sorting of bell peppers using machine vision. Trans of theASAE, 1990, 33(6): 2045~2050
[13] B. S. Bennedsen, D. L. Peterson, Amy Tabb. Identifying defects in images of rotating apples. Computers and Electronics in Agriculture. 2005, 48(2): 92~102
[14] Tao Y, Heinemann P H, Varghese Z, etal. Machine vision for color inspection of potatoes and apples. Trans of the ASAE, 1995, 38(5): 1555~1561
[15] Taylor R W, Rehkugler G E, Throop J A. Apple bruise detection using adigital line scan camera system. In Agricultural Electronics-1983 and Beyond Volune. St. Joseph, M I: ASAE, 1984
[16] Rehkugler G E, Throop J A.Apple sorting with machine vision. Trans of the ASAE, 1986, 29(5): 1388-1397
[17] Thomason R L. June3—5. High speed machine vision in spection for surface flaws,textures and contours. Proc Vision 86 Conf. Detroit,Michigan, 1986, 5:51—61
[18] Godinez P A. Inspection of surface flows and textures. Sensors, 1987 (June): 27—32
[19] Davenel A, Guizard C H. Automatic detection of surface defects on fruit by using a vision system. Journal of Agricultural Engineering Research, 1988, 41:1—9
[20] Rehkugler G E, Throop J A. Image processing algorithm for apple defect detection. Trans of the ASAE, 1989, 32(1): 267-272
[21] Miller B K,Delwiche M J. Peach defect detection with machine vision. Trans of the ASAE, 1991,34(6):.2588-2597
[22] Pearson T C, Slaughter D C. Machine vision detection of early split pistachio nuts. Trans of the ASAE, 1996, 39(3): 1203—1207
[23] Yang Q. Finding stalk and calyx of apples using structured lighting. Computer and Electronics in Agriculture, 1993, 8(1) :31—42
[24] Crowe T G, Delwiche M J. Realtime defect detection in fruit-part II: An algorithm and performance of aprototype system. Trans of the ASAE, 1996, 39(6): 2309—2317
[25] Byler R K, Diehl K C, Stephens J W, etal. Digital imaging of oyster means. ASAE Paper, 1987. 87-6502
[26] Marchant J A, Onyango C M, Street M J. High speed sorting of potatoes using computer vision. ASAE Paper, 1988. 88—3540
[27] Churchill D B,Bilsland D M,Cooper T M. Comparison of machine vision with human measurement of seed dimensions. Trans of the ASAE, 1992, 35(1):61—64
[28] Trooien T P, Heermann D F. Measurement and simulation of potato leaf area using image processing III . Measurement.Trans of the ASAE,1992,35(5):1719—1721
[29] Panigrahi S, Misra M K.Bern C,etal. Background segmentation and dimensional measurement of corn germplasm. Trans of the ASAE, 1995,38(1):291—297
[30] Liao K, Paulsen M R, Reid J F. Real-time detection of color and surface defects of maize kernels using machine vision. Journal of Agricultural Engineering Research, 1994, 59: 263~271
[31] Chang Y C, Reid J F. Characterization of a color vision system. Trans of the ASAE, 1996, 39(1): 263~273
[32] Tao Y. Methods and apparatus for sorting objects by color. United States Patent, 1994. 5, 339, 963
[33] Tao Y. Methods for sorting objects in cluding stable color trans formation. United States Patent, 1996. 5, 533, 628
[34] 应义斌,景寒松,马俊福,蒋亦元,赵匀.黄花梨品质检测机器视觉系统.农业机械学报.2000年,31(2):113-115
[35] 应义斌,饶秀勤,赵均,蒋亦元.机器视觉技术在农产品品质自动识别中的应用.农业工程学报,2000,16(1):103~107
[36] 应义斌,傅宾忠,蒋亦元等.机器视觉技术在农业生产自动化中的应用.农业工程报,1999,15(3):199~203
[37] 应义斌,景寒松,马俊福,蒋亦元,赵匀.黄花梨品质检测机器视觉系统.农业机械学报,2000.31(2):113-115
[38] 曹其新,刘成良,殷跃红,付庄,永田雅辉.基于彩色图像处理的西红柿品质特征的提取研究.机器人,2001,23(7):652-543
[39] 刘全良,王洪.苹果分类识别中的分形问题研究.计算机工程与应用,2002,17:244-245
[40] Sugiyamma J. T. Katsural J. Hong etal. Portable melon firmness tester using acoustic impulse transmission [R]. Orlando Florida: Proceedings from the sensors for nondestructive testing international conference, 1997
[41] Armstrong P. R. Stone M. L. Peach firmness determination using two different nondestructive vibrational sensing instruments [J]. Trans of the ASAE, 1997, 40(3): 699~703
[42] Saltveit M. E, Upadhyaya S. K, Happ J. F, etal. Maturity determination of tomatoes using acoustic methods [J]. ASAE paper, 1985, (1): 35~36
[43] Schotte S. Acoustic impulse response technique for evaluation and modeling of firmness of tomato fruit [J]. Postharvest biology and technology, 1999, 17(2): 105~115
[44] Belie N. Firmness changes of pear fruit before and after harvest with the acoustic impulse response technique [J]. Journal of Agricultural Engineering Research, 2000, 77(2): 183~191
[45] Sinha D. N, Johnston. W. K, Grace C. L. Asoustic Resonance in Chicken Eggs, Biotechnol. Prog. 1993, 8(3): 240~243
[46] Cho. H. K., Y. Kwon. Crack Detection in Eggs by Machine Vision, In 6th Int. Conf. On Computers in Agriculture, St. Joseph. Mich. ASAE, 1996: 777-784
[47] B. De Ketelaere; P. Coucke; J. De Baerdemaeker. Eggshell Crack Detection based on Acoustic Resonance Frequency Analysis. agric. Engng Res. 2000 (76): 157-163
[48] 何东健,李增武,王洪群.西瓜打击波特性的研究.西北农业大学学报,1994,22(3);105~107
[49] 王书茂,焦群英等.西瓜成熟度无损检验的冲击震荡方法.农业工程学报,1999,15(3):241~245
[50] 公茂法,汤元信等,禽蛋质量自动检测方法与实现.自动化与仪器仪表,1995,5;36~39
[51] 黄耀志.基于神经网络分析的鲜蛋破损检测.振动、测试与检测,2003,23(3):205~230
[52] United States Department of Agriculture Egg Grading Manual. Agricultural Handbook Number 75, Agricultural Marketing Service, USDA. 1990.
[53] Moba Newsletters, Crania 330: the bold advance. Barneveld, Holland. 1996.
[54] North, M. O. and Bell, D. D. Commercial Chicken Production Manual, Fourth Edition. Van Nostrand Reinhold: New York, NY. 1990.
[55] Elster, R. T. and J. w. Goodurm. Detecting of Cracks in Eggs Using Machine Vision. Transactions of the ASAE. 1991. Vol. 34(1): 307—312.
[56] Goodur m. J. w. and R. T. Elster. Machine Vision for Cracks Detection in Rotation Eggs. Transactions of the ASAE. 1992(4): 1323—1328.
[57] V. C. Patel, R. W. Mc Cle ndon, J. W. Goodru m. Detection of cracks in eggs using color computer vision and artificial neural net works. ASAE Annual Intern. Meeting, St. Joseph. 1995.
[58] V. C. Patel, R. w. Mc Cle ndon, J. w. Goodru m. Crack detection in eggs using computer vision and neural networks. A. I. Applications. 1994. (2): 21—31.
[59] V. C. Patel, R. W. Mc Cle ndon, J. W. Goodru m. Color Computer Vision and Artificial Neural Networks for the Detection of Defects in Poultry Enns. Artificial Intellinence Review. 1998. 12. 163—176.
[60] Nakano, K., J.Us ui., Y.Motonaga and J.Mizutani. Development of non—destructive detector for abnormal eggs. Workshop on Control Applications in Post—Harvest and Processing Technology, 2001.71—76.
[61] M.C. Ga rci a—Alegre, A. Ribeiro, D. Guinea, and G. Cristobal. Eggshell defects detection based on color processing. SPIE 2000 Electronic Imaging Conf., CA, Jan. 2000.
[62] Angela Ribeiro, Maria C.Ga rci a—Ale g re, Domingo Guinea.Automatic Rules Generation by G.A. for Eggshell Detect Classification.European Congress on Computational Methods in Applied Sciences and Engineering.2000.Barcelona.
[63] Keigo kuchida, Miho Fukaya.Nondestructive Predition Method for Yolk:Albumen Ratio in Chicken Eggs by Computer Image Analysis.Poultry Science.1999.78:909—913.
[64] Das K., Evans M.D. Detecting Fertility of Hatching Eggs Using Machine Vision 11:Neural Network Classifie'rs.Transactions of the ASAE.1992.35(6):2035—2041
[65] 杨秀坤.农产品品质检测中的人工智能方法研究[D].博士论文:东北农业大学1997.12
[66] 周维忠.基于机器视觉的孵化生产质量检测技术研究[D].博士论文:西安交通大学2000.12
[67] 王树才,文友先等.利用敲击声音信号对鸭蛋破损进行模糊识别[J].农业工程学报,2004 20(4):130-134.
[68] 苏臣,吴安翔.鸡蛋六种品质的数字图像特征[J].中国家禽,1995,05.18-20.
[69] 文友先,王巧华.鸭蛋蛋心颜色等级模型研究[J].农业工程学报,2001.17(6):139-141.
[70] 陈佳娟,陈晓光,纪寿文.采用计算机视觉孵化鸡蛋成活性的自动检测[J].计算机应用与软件,2001.18(6):5-10.
[71] 郁志宏,倪志华,李海军等.机器视觉技术在禽蛋品质和孵化成活性检测方面的应用.内蒙古农业大学学报,2004.25(3):116-120.
[72] Yongtae Do. Applications of neural networks for stereo-Camera Calibration. Proc. of International Joint Conference on Neural Networks. Washington:IEEE, 1999. 2719-2722.
[73] Ganapathy S. Decomposition of transformation matrices for robot vision. Proc. Int. Conference on Robotics and Automation. 1984.130-139.
[74] Abdel-Aziz YI., Karara H.M.. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. In U. of Illinois Symposium on Close-Range Photogrammetry. Urbana: Univ. of Illinois at Urbana-Champaign, 1971.1-18.
[75] 夏良正.数字图像处理.东南大学出版社,南京,1999.08:218-228
[76] 贾云得.机器视觉.科学技术出版社,北京,2004.06:196-204
[77] 雷晓峰,王耀南,段峰.利用vc++开发图像采集卡与图像预处理库.电脑编程技巧与维护,2002 2:48-50
[78] 王腾蛟,刘云峰,汤晋主.Visual C++6.0.教程北京科海集体公司.2001.05
[79] 何斌,马天予,王运坚,朱红莲.Visual C++数字图像处理.人民邮电出版社.2001.04:338-358
[80] 殷际英,何广平.关节型机器人.化学工业出版社.北京3003.05:3-8
[81] 高桥友一,秋田纯一著,宗光华译.小型机器人的基础技术与制作.科学出版社.北京.
[82] 方建军,何广平.智能机器人.化学工业出版社.北京.3003.11:37-46
[83] 孙桓,陈作模.机械原理(第六版).高等教育出版社.北京2000.08:463-481 2004.05:53-58
[84] 朱振友,徐爱杰,林涛,陈善本.机器人视觉的“手眼”关系快速标定算法.光学技术,2004,30(2)150-154
[85] 李超,董继先.浅析机器人轨迹规划中关节空间轨迹的插值方法.西北轻工业学院学报,2002,20(5):42-45
[86] PMAC用户手册.北京元茂兴控制设备技术责任有限公司.2003.02
[87] 迈克.普瑞德科著,宗光华,李大寨译.机器人控制器与程序设计.科学出版社.北京.2004.05
[88] 船仓一郎,土屋著,宗光华,扬洋译.机器人控制电子学.科学出版社.北京.2004.05
[89] 张泽峰,陈小平.一种实时快速低耗的机器人视觉处理系统.计算机工程.2004.30(10):40-42
[90] 熊有伦,熊蔡华.机器人多指抓取的研究进展与展望.第32卷增刊 华中科技大学学报(自然科学版).2004.09,第32卷增刊
[91] 李雪梅.真空吸盘的设计与应用.华南理工大学学报,2004,03.
[92] 单景德.真空吸取器设计及应用技术.北京:国防工业出版社,1999:184-188
[93] 滕红华.真空吸盘吸持物体的动力学分析.武汉工学院学报,2004,02.
[94] 姚朝晖,何枫等.真空发生器系统吸附响应时间的确定.清华大学学报,2002,05.
[95] 陆鑫盛主编.气动自动化系统的优化设计.上海:上海科学技术文献出版社,2000.
[96] 陈光东,赵性初.单片微型计算机原理与接口技术.武汉:华中科技大学出版社,1995,06.
[97] 孟昕元.MCS-51单片机实验及课程设计电路板的设计.河南机电高等专科学校学 报,2004,12(6).
[98] 关学忠,周玉学.单片机在报警系统中的应用.自动化技术与应用.2000,19(4)
[99] 董晓剑.鸭蛋破损自动检测与系统设计.[硕士学位论文].武汉:华中农业大学,2002
[100] 陈家焱.鸭蛋破损声检与分级技术的研究.[硕士学位论文].武汉:华中农业大学,2004
[101] 莫牧.基于单片机的鸡蛋破损检测系统的研究.[硕士学位论文].武汉:华中农业大学,2005]。
[102] 刘金刚.基于DSP的鸡蛋破损检测系统的研究.[硕士学位论文].武汉:华中农业大学,2005
[103] 曹广忠,邱建.高性能浮点DSP芯片TMS320VC33.国外电子元器件,2001,(10):14-17
[104] De Ketelaere B., Coucke P., De Baerdemaeker J. Eggshell Crack Detection based on Acoustic Resonance Frequency Analysis. Journal of Agricultural Engineering Research, 2000,76(2):157-163.
[105] H.-K. Cho, W.-K. Choi, J.-H. Paek. DETECTION OF SURFACE CRACKS IN SHELL EGGS BY ACOUSTIC IMPULSE METHOD. the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www. asabe, org
[106] B. DE KETELAERE, F. BAMELIS, B. KEMPS. Non-destructive measurements of the egg quality. World's Poultry Science Journal. 2004,60(3):289-302.
[107] 熊利荣.鸭蛋品质无损检测与分级系统的研究.[硕士学位论文].武汉:华中农业大学,2002
[108] 王巧华.基于BP神经网络的鸡蛋新鲜度识别方法的研究.[硕士学位论文].武汉:华中农业大学,2003
[109] 丁幼春.基于机器视觉鸭蛋品质无损自动检测分级系统的改进.[硕士学位论文].武汉:华中农业大学,2003
[110] 何东健等.数字图像处理.西安电子科技大学出版社,西安,2003.07:30-34