技术领域technical field
本发明属于工件定位方法领域，更具体地，涉及一种工件位置追踪定位方法及定位系统。The invention belongs to the field of workpiece positioning methods, and more specifically relates to a workpiece position tracking and positioning method and a positioning system.
背景技术Background technique
传统的工业生产管理主要通过人力来实现生产库存的记录、生产质量的检查、生产成本的计算和生产进度的控制等工作。随着信息技术的高速发展，使得很多领域的生产效率得到较大的提升。机械制造行业由于其在国民经济中的基础产业的地位，提高工业生产效率和质量变得愈加重要。因而，进一步提高工业生产的自动化程度，实现智能制造是发展机械制造业的一个主要方向。Traditional industrial production management mainly uses manpower to realize production inventory records, production quality inspections, production cost calculations, and production schedule control. With the rapid development of information technology, the production efficiency in many fields has been greatly improved. Due to its status as a basic industry in the national economy, the machinery manufacturing industry has become increasingly important to improve industrial production efficiency and quality. Therefore, further improving the automation of industrial production and realizing intelligent manufacturing is a main direction for the development of machinery manufacturing.
目前，国外在机械自动化方面已经取得了显著的成果，但对于国内制造领域来说，智能制造程度明显较低，在工件的生产管理方面仍存在人工干预较多、自动化程度不高的问题。很多工厂的工件在进行加工工序之前，需要人工用扫描器手动扫描工件上的条码，进行工件的识别，以获取工件的信息。此外，虽然可以利用超高频RFID技术实现较为方便快捷的信息扫描和记录，但由于RFID设备不具备智能开关的功能，因而存在长时间处于信号发送的工作状态等问题，不仅浪费电力、造成信息冗余，而且发热后稳定性降低，损耗仪器寿命，增加工厂成本。目前为解决RFID设备常开的问题已有人设计出了专门的散热系统，但其结构复杂，适用性较低。而如果完全采用图像识别处理的方法进行工件的记录追踪，又存在算法复杂、可靠性低等问题。At present, foreign countries have made remarkable achievements in mechanical automation, but for the domestic manufacturing field, the level of intelligent manufacturing is obviously low, and there are still problems of more manual intervention and low automation in the production management of workpieces. Before the workpieces in many factories are processed, they need to manually scan the barcode on the workpiece with a scanner to identify the workpiece and obtain the information of the workpiece. In addition, although UHF RFID technology can be used to realize more convenient and quick information scanning and recording, since RFID equipment does not have the function of intelligent switch, there are problems such as being in the working state of signal transmission for a long time, which not only wastes power, but also causes information Redundancy, and the stability decreases after heating, which will reduce the life of the instrument and increase the cost of the factory. At present, a special heat dissipation system has been designed to solve the problem that the RFID equipment is always on, but its structure is complex and its applicability is low. However, if the method of image recognition processing is completely used to record and track workpieces, there will be problems such as complex algorithms and low reliability.
发明内容Contents of the invention
针对现有技术的以上缺陷或改进需求，本发明提供了一种工件位置追踪定位方法及定位系统，利用现代机器视觉、图像处理、电子通信技术实现对工件的追踪定位及工序进出状态的监测。In view of the above defects or improvement needs of the prior art, the present invention provides a workpiece position tracking and positioning method and positioning system, which utilizes modern machine vision, image processing, and electronic communication technologies to realize tracking and positioning of workpieces and monitoring of process entry and exit states.
为实现上述目的，按照本发明，提供了一种工件位置追踪定位方法，其特征在于，包括如下步骤：In order to achieve the above object, according to the present invention, a workpiece position tracking and positioning method is provided, which is characterized in that it includes the following steps:
1)在车间划分出多个监测区域，在各监测区域处分别设置摄像头，以利用摄像头实时采集与其对应的监测区域的视频图像，并对各摄像头进行位置标定，以获得工件的位置及工序进出状态；1) Divide multiple monitoring areas in the workshop, and install cameras in each monitoring area to use the cameras to collect video images of the corresponding monitoring areas in real time, and perform position calibration on each camera to obtain the position of the workpiece and the process entry and exit state;
2)将各摄像头采集到的视频图像分别传送给计算机，并进行运动物体识别，当有工件进入监测区域时，利用视频分析子系统获得工件在监测区域内的位置；2) Send the video images collected by each camera to the computer respectively, and perform moving object recognition. When a workpiece enters the monitoring area, use the video analysis subsystem to obtain the position of the workpiece in the monitoring area;
3)根据各超高频RFID读写器的读取距离，在各监测区域内再分别选定一个与超高频RFID读写器的读写距离相应的扫描区域，当有运动中的工件进入该扫描区域时，利用视频分析子系统唤醒超高频RFID读写器，让超高频RFID读写器读取工件的RFID标签信息，以获取工件信息并传送给计算机；其中，根据具体加工现场的情况，一个监测区域内设置一个扫描区域或多个彼此之间不相交的扫描区域，一台摄像头的监测范围内覆盖一个扫描区域或多个彼此之间不相交的扫描区域，并且一个超高频RFID读取器只对应一个扫描区域，不同扫描区域对应不同的超高频RFID读取器；3) According to the reading distance of each UHF RFID reader, select a scanning area corresponding to the reading and writing distance of the UHF RFID reader in each monitoring area. When a moving workpiece enters When scanning the area, use the video analysis subsystem to wake up the UHF RFID reader, so that the UHF RFID reader can read the RFID tag information of the workpiece to obtain the workpiece information and send it to the computer; among them, according to the specific processing site In the case of a monitoring area, one scanning area or multiple disjoint scanning areas are set in one monitoring area, and the monitoring range of a camera covers one scanning area or multiple disjoint scanning areas, and a super high The high-frequency RFID reader only corresponds to one scanning area, and different scanning areas correspond to different UHF RFID readers;
4)根据计算机获得的摄像头的位置信息、视频图像的分析结果和超高频RFID读写器的读写结果，确定工件的位置信息及所处的加工状态，并将所得到的上述信息上传至MES生产管理系统。4) According to the position information of the camera obtained by the computer, the analysis results of the video image and the reading and writing results of the UHF RFID reader, determine the position information and processing status of the workpiece, and upload the obtained above information to MES production management system.
优选地，所述视频分析子系统包括运动检测模块、定位模块和RFID触发模块，其中，所述运动检测模块用于对当前视频图像进行运动工件的检测，并记录工件的运行路径，所述定位模块用于确定工件在监测区域内的具体位置，以便结合摄像头的位置标定信息进行工件的定位，并判断工件是否进入超高频RFID读写器的扫描区域；RFID触发模块用于在工件进入扫描区域时唤醒超高频RFID读写器。Preferably, the video analysis subsystem includes a motion detection module, a positioning module and an RFID trigger module, wherein the motion detection module is used to detect a moving workpiece on the current video image, and record the running path of the workpiece, and the positioning The module is used to determine the specific position of the workpiece in the monitoring area, so as to locate the workpiece in combination with the position calibration information of the camera, and judge whether the workpiece enters the scanning area of the UHF RFID reader; the RFID trigger module is used to scan when the workpiece enters Wake up the UHF RFID reader when in the area.
优选地，步骤2)中，进行运动物体识别前，对监测到的视频图像进行前景和背景分割以及去噪处理。Preferably, in step 2), before performing moving object recognition, foreground and background segmentation and denoising processing are performed on the monitored video image.
优选地，步骤2)中采用高斯模糊移除高频噪点的算法进行去噪处理。Preferably, in step 2), a Gaussian blur algorithm for removing high-frequency noise is used for denoising processing.
优选地，步骤2)中，所述运动物体识别是采用基于混合高斯模型的前景和背景分割算法锁定运动工件图像，然后进行轮廓识别。Preferably, in step 2), the moving object recognition is to use a mixed Gaussian model-based foreground and background segmentation algorithm to lock the moving workpiece image, and then perform contour recognition.
优选地，步骤3)中采用Cohen-Surtherland裁剪算法判断运动工件是否进入扫描区域。Preferably, in step 3), the Cohen-Surtherland clipping algorithm is used to judge whether the moving workpiece enters the scanning area.
优选地，步骤3)中，初始没有工件进行加工时，所有的超高频RFID读写器处于休眠状态；当有工件进行加工时，在工件所进入的扫描区域内仅有一个对应的超高频RFID读写器启动并对工件进行扫描，从而避免了监测区域内由于超高频RFID读写器多位置布置所造成的检测信号干涉现象，保证超高频RFID读写器的有效识别。Preferably, in step 3), when initially no workpiece is processed, all UHF RFID readers are in a dormant state; when a workpiece is processed, there is only one corresponding ultrahigh frequency RFID reader in the scanning area entered by the workpiece The high-frequency RFID reader starts and scans the workpiece, thereby avoiding the detection signal interference phenomenon caused by the multi-position arrangement of the UHF RFID reader in the monitoring area, and ensuring the effective identification of the UHF RFID reader.
按照本发明的另一个方面，还提供了一种工件位置追踪定位系统，其特征在于，包括视频采集子系统、视频分析子系统、RFID读取信息子系统和生产线报警子系统，其中，According to another aspect of the present invention, a workpiece position tracking and positioning system is also provided, which is characterized in that it includes a video acquisition subsystem, a video analysis subsystem, an RFID reading information subsystem and a production line alarm subsystem, wherein,
视频采集子系统，用于实时采集监测区域内的工件的视频图像；The video acquisition subsystem is used for real-time acquisition of video images of workpieces in the monitoring area;
视频分析子系统，用于对采集的视频图像进行运动检测，记录工件运行路径、追踪工件位置及工序进出状态，在工件进入监测区域内的扫描区域时，向超高频RFID读取器发送触发信号，以唤醒超高频RFID读取器并读取工件信息；其中，根据具体加工现场的情况，一个监测区域内设置一个扫描区域或多个彼此之间不相交的扫描区域，一台摄像头的监测范围内覆盖一个扫描区域或多个彼此之间不相交的扫描区域，并且一个超高频RFID读取器只对应一个扫描区域，不同扫描区域对应不同的超高频RFID读取器；The video analysis subsystem is used to perform motion detection on the collected video images, record the workpiece running path, track the workpiece position and process entry and exit status, and send a trigger to the UHF RFID reader when the workpiece enters the scanning area in the monitoring area signal to wake up the UHF RFID reader and read the workpiece information; among them, according to the specific processing site conditions, one scanning area or multiple non-intersecting scanning areas are set in one monitoring area, and one camera's The monitoring range covers one scanning area or multiple non-intersecting scanning areas, and one UHF RFID reader corresponds to only one scanning area, and different scanning areas correspond to different UHF RFID readers;
RFID读取信息子系统，用于读取工件上的RFID标签信息，并将获得的数据上传到工厂的MES生产管理系统；The RFID reading information subsystem is used to read the RFID tag information on the workpiece and upload the obtained data to the MES production management system of the factory;
生产线报警子系统，用于在工件的位置信息和加工工序与MES生产管理系统中设定的参考信息不同时进行报警，以便对生产现场进行检查。The production line alarm subsystem is used to give an alarm when the position information and processing procedure of the workpiece are different from the reference information set in the MES production management system, so as to check the production site.
总体而言，通过本发明所构思的以上技术方案与现有技术相比，能够取得下列有益效果：Generally speaking, compared with the prior art, the above technical solutions conceived by the present invention can achieve the following beneficial effects:
1)本发明采用基于混合高斯模型的前景和背景分割算法，降低阴影和光线变化的影响，从而高效地识别运动中的物体；1) The present invention adopts a foreground and background segmentation algorithm based on a mixed Gaussian model to reduce the influence of shadows and light changes, thereby efficiently identifying moving objects;
2)本发明采用Cohen-Surtherland裁剪算法，准确高效的判断工件是否进入RFID扫描区域；2) The present invention adopts the Cohen-Surtherland cutting algorithm to accurately and efficiently judge whether the workpiece enters the RFID scanning area;
3)本发明通过运动跟踪和摄像头位置标定，能有效获取工件的位置、运动路径和加工工序等信息；3) The present invention can effectively obtain information such as the position, motion path, and processing procedure of the workpiece through motion tracking and camera position calibration;
4)本发明通过判断工件进入扫描区域从而唤醒RFID扫描程序，避免超高频RFID读写器长时间工作导致稳定性降低，能有效减少电力消耗、设备消耗和实时扫描带来的信息冗余。4) The present invention wakes up the RFID scanning program by judging that the workpiece enters the scanning area, avoids the stability reduction caused by the long-term work of the UHF RFID reader, and can effectively reduce power consumption, equipment consumption and information redundancy caused by real-time scanning.
5)本发明通过摄像头和视频分析子系统控制超高频RFID读取器的启动和休眠，并通过合理分布摄像头与RFID设备的位置来实现分区域的工件追踪与定位，整合所有区域的数据信息可得到一个工件的运行路径和加工状态，同时避免了由于RFID多位置布置所造成的检测信号干涉现象，保证了RFID的有效识别。5) The present invention controls the startup and dormancy of the UHF RFID reader through the camera and the video analysis subsystem, and realizes the tracking and positioning of workpieces in sub-regions by reasonably distributing the positions of the cameras and RFID devices, and integrates the data information of all regions The running path and processing state of a workpiece can be obtained, and at the same time, the detection signal interference phenomenon caused by the multi-position arrangement of the RFID is avoided, and the effective identification of the RFID is guaranteed.
6)本发明采用实时视频监控和报警系统，实现了对工件的追踪定位及工序进出状态的自动监控报警功能。6) The present invention adopts a real-time video monitoring and alarm system to realize the tracking and positioning of the workpiece and the automatic monitoring and alarm function of the entry and exit status of the process.
7)本发明结合现代信息处理技术、通信技术，提出了一种对加工工件进行位置追踪及定位的监测方法，能够提供客观可靠的工件位置、加工工序等状态信息，同时可将采集到的数据上传至车间的MES生产管理系统，替代了以往的人工操作，有效提升工业生产管理的效率，对工业生产的智能化和自动化有很好的促进作用。7) The present invention combines modern information processing technology and communication technology to propose a monitoring method for tracking and locating workpieces, which can provide objective and reliable status information such as workpiece locations and processing procedures, and at the same time collect the collected data The MES production management system uploaded to the workshop replaces the previous manual operation, effectively improves the efficiency of industrial production management, and has a good role in promoting the intelligence and automation of industrial production.
附图说明Description of drawings
图1是本发明定位方法的流程图；Fig. 1 is the flowchart of positioning method of the present invention;
图2是本发明的运动检测流程图。Fig. 2 is a flow chart of motion detection in the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。此外，下面所描述的本发明各个实施方式中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.
参照图1、图2，一种工件位置追踪定位方法，包括如下步骤：Referring to Fig. 1 and Fig. 2, a method for tracking and locating a workpiece position includes the following steps:
1)在车间划分出多个监测区域，在各监测区域处分别设置摄像头，以利用摄像头实时采集与其对应的监测区域的视频图像，并对各摄像头进行位置标定，以获得工件的位置及工序进出状态；1) Divide multiple monitoring areas in the workshop, and install cameras in each monitoring area to use the cameras to collect video images of the corresponding monitoring areas in real time, and perform position calibration on each camera to obtain the position of the workpiece and the process entry and exit state;
2)将各摄像头采集到的视频图像分别传送给计算机，并进行运动物体识别，当有工件进入监测区域时，利用视频分析子系统获得工件在监测区域内的位置；2) Send the video images collected by each camera to the computer respectively, and perform moving object recognition. When a workpiece enters the monitoring area, use the video analysis subsystem to obtain the position of the workpiece in the monitoring area;
3)根据各超高频RFID读写器的读取距离，在各监测区域内再分别选定一个与超高频RFID读写器的读写距离相应的扫描区域，当有运动中的工件进入该扫描区域时，利用视频分析子系统唤醒超高频RFID读写器，让超高频RFID读写器读取工件的RFID标签信息，以获取工件信息并传送给计算机；3) According to the reading distance of each UHF RFID reader, select a scanning area corresponding to the reading and writing distance of the UHF RFID reader in each monitoring area. When a moving workpiece enters When scanning the area, use the video analysis subsystem to wake up the UHF RFID reader, so that the UHF RFID reader can read the RFID tag information of the workpiece to obtain the workpiece information and send it to the computer;
4)根据计算机获得的摄像头的位置信息、视频图像的分析结果和超高频RFID读写器的读写结果，确定工件的位置信息及所处的加工状态，并将所得到的上述信息上传至MES生产管理系统。4) According to the position information of the camera obtained by the computer, the analysis results of the video image and the reading and writing results of the UHF RFID reader, determine the position information and processing status of the workpiece, and upload the obtained above information to MES production management system.
优选地，所述视频分析子系统包括运动检测模块、定位模块和RFID触发模块，其中，所述运动检测模块用于对当前视频图像进行运动工件的检测，并记录工件的运行路径，所述定位模块用于确定工件在监测区域内的具体位置，以便结合摄像头的位置标定信息进行工件的定位，并判断工件是否进入超高频RFID读写器的扫描区域；RFID触发模块用于在工件进入扫描区域时唤醒超高频RFID读写器。Preferably, the video analysis subsystem includes a motion detection module, a positioning module and an RFID trigger module, wherein the motion detection module is used to detect a moving workpiece on the current video image, and record the running path of the workpiece, and the positioning The module is used to determine the specific position of the workpiece in the monitoring area, so as to locate the workpiece in combination with the position calibration information of the camera, and judge whether the workpiece enters the scanning area of the UHF RFID reader; the RFID trigger module is used to scan when the workpiece enters Wake up the UHF RFID reader when in the area.
优选地，步骤2)中，进行运动物体识别前，对监测到的视频图像进行前景和背景分割以及去噪处理。Preferably, in step 2), before performing moving object recognition, foreground and background segmentation and denoising processing are performed on the monitored video image.
优选地，步骤2)中采用高斯模糊移除高频噪点的算法进行去噪处理。Preferably, in step 2), a Gaussian blur algorithm for removing high-frequency noise is used for denoising processing.
优选地，步骤2)中，所述运动物体识别是采用基于混合高斯模型的前景和背景分割算法锁定运动工件图像，然后进行轮廓识别。Preferably, in step 2), the moving object recognition is to use a mixed Gaussian model-based foreground and background segmentation algorithm to lock the moving workpiece image, and then perform contour recognition.
优选地，步骤3)中采用Cohen-Surtherland裁剪算法判断运动工件是否进入扫描区域。Preferably, in step 3), the Cohen-Surtherland clipping algorithm is used to judge whether the moving workpiece enters the scanning area.
优选地，步骤3)中，根据具体加工现场的情况，一个监测区域内可设置一个扫描区域或多个彼此之间不相交的扫描区域，一台摄像头的监测范围内可覆盖一个扫描区域或多个彼此之间不相交的扫描区域，并且一个超高频RFID读取器只对应一个扫描区域，不同扫描区域对应不同的超高频RFID读取器。Preferably, in step 3), according to the conditions of the specific processing site, one scanning area or multiple non-intersecting scanning areas can be set in one monitoring area, and one scanning area or multiple scanning areas can be covered within the monitoring range of one camera. There are two disjoint scanning areas, and one UHF RFID reader corresponds to only one scanning area, and different scanning areas correspond to different UHF RFID readers.
优选地，步骤3)中，初始没有工件进行加工时，所有的超高频RFID读写器处于休眠状态；当有工件进行加工时，在工件所进入的扫描区域内仅有一个对应的超高频RFID读写器启动并对工件进行扫描，从而避免了监测区域内由于超高频RFID读写器多位置布置所造成的检测信号干涉现象，保证超高频RFID读写器的有效识别。Preferably, in step 3), when initially no workpiece is processed, all UHF RFID readers are in a dormant state; when a workpiece is processed, there is only one corresponding ultrahigh frequency RFID reader in the scanning area entered by the workpiece The high-frequency RFID reader starts and scans the workpiece, thereby avoiding the detection signal interference phenomenon caused by the multi-position arrangement of the UHF RFID reader in the monitoring area, and ensuring the effective identification of the UHF RFID reader.
按照本发明的另一个方面，还提供了一种工件位置追踪定位系统，其特征在于，包括视频采集子系统、视频分析子系统、RFID读取信息子系统和生产线报警子系统，其中，According to another aspect of the present invention, a workpiece position tracking and positioning system is also provided, which is characterized in that it includes a video acquisition subsystem, a video analysis subsystem, an RFID reading information subsystem and a production line alarm subsystem, wherein,
视频采集子系统，用于实时采集监测区域内的工件的视频图像；The video acquisition subsystem is used for real-time acquisition of video images of workpieces in the monitoring area;
视频分析子系统，用于对采集的视频图像进行运动检测，记录工件运行路径、追踪工件位置及工序进出状态，在工件进入监测区域内的扫描区域时，向超高频RFID读取器发送触发信号，以唤醒超高频RFID读取器并读取工件信息；The video analysis subsystem is used to perform motion detection on the collected video images, record the workpiece running path, track the workpiece position and process entry and exit status, and send a trigger to the UHF RFID reader when the workpiece enters the scanning area in the monitoring area signal to wake up the UHF RFID reader and read the workpiece information;
RFID读取信息子系统，用于读取工件上的RFID标签信息，并将获得的数据上传到工厂的MES生产管理系统；The RFID reading information subsystem is used to read the RFID tag information on the workpiece and upload the obtained data to the MES production management system of the factory;
生产线报警子系统，用于在工件的位置信息和加工工序与MES生产管理系统中设定的参考信息不同时进行报警，以便对生产现场进行检查。The production line alarm subsystem is used to give an alarm when the position information and processing procedure of the workpiece are different from the reference information set in the MES production management system, so as to check the production site.
参照图1，本发明的工件位置追踪及定位的监测方法具体：Referring to Fig. 1, the monitoring method of workpiece position tracking and positioning of the present invention is specific:
1)实时采集监测区域的视频图像；1) Real-time collection of video images of the monitoring area;
2)对采集到的视频图像进行运动物体识别；进行运动物体识别前，为解决复杂背景中的光照、噪声等问题，对监测到的视频图像进行去噪处理，本实施例中采用高斯模糊移除高频噪点去噪算法进行高品质去噪处理；所述运动物体识别步骤包括：采用基于混合高斯模型的前景和背景分割算法，锁定运动工件图像，进行轮廓识别，并记录运动路径；。2) Carry out moving object recognition to the video image that gathers; Before carrying out moving object recognition, in order to solve problems such as illumination, noise in complex background, carry out denoising processing to the video image that monitors, adopt Gaussian fuzzy moving in the present embodiment The high-quality denoising processing is carried out by a denoising algorithm for removing high-frequency noise; the moving object recognition step includes: adopting a foreground and background segmentation algorithm based on a mixed Gaussian model, locking a moving workpiece image, performing contour recognition, and recording a moving path;
3)判定运动工件是否进入扫描区域，采用Cohen-Surtherland裁剪算法实现了对运动工件的位置识别，并以此为超高频RFID读写器提供触发信号；3) Determine whether the moving workpiece enters the scanning area, and use the Cohen-Surtherland clipping algorithm to realize the position recognition of the moving workpiece, and provide a trigger signal for the UHF RFID reader;
4)对于进入超高频RFID读写器扫描区域的工件，超高频RFID读取器读取其RFID标签信息，得到该工件信息，确定工件编号和生产批次。4) For the workpiece entering the scanning area of the UHF RFID reader, the UHF RFID reader reads its RFID tag information, obtains the workpiece information, and determines the workpiece number and production batch.
5)所述视频分析子系统，包括运动检测模块，定位模块和RFID触发模块；运动检测模块对当前视频图像进行运动工件的检测，同时记录工件的运行路径；定位模块确定工件在监测范围内的具体位置，以便结合摄像头的位置标定信息进行工件的定位，同时判断工件是否进入超高频RFID读写器的扫描区域；RFID触发模块在工件进入扫描区域时，通过GPIO接口向超高频RFID读写器发送跳变电压，以启动超高频RFID读写器。5) The video analysis subsystem includes a motion detection module, a positioning module and an RFID trigger module; the motion detection module detects the moving workpiece to the current video image, and records the running path of the workpiece simultaneously; the positioning module determines that the workpiece is within the monitoring range Specific location, in order to locate the workpiece in combination with the position calibration information of the camera, and at the same time determine whether the workpiece enters the scanning area of the UHF RFID reader; when the workpiece enters the scanning area, the RFID trigger module sends the UHF RFID reader through the GPIO interface The writer sends a jump voltage to start the UHF RFID reader.
6)所述RFID读取信息子系统包括超高频RFID读取器、RFID标签；所述超高频RFID读取器安装在加工设备附近的工作台上；所述RFID标签放置于工件指定位置上，RFID标签与每个工件信息之间具有一一对应关系。只在视频分析子系统发送触发信号时才启动。6) The RFID reading information subsystem includes a UHF RFID reader and an RFID tag; the UHF RFID reader is installed on a workbench near the processing equipment; the RFID tag is placed on a designated position of the workpiece Above, there is a one-to-one correspondence between the RFID tag and each workpiece information. Only starts when the video analytics subsystem sends a trigger signal.
7)根据超高频RFID读写器的读取结果和摄像头的标定信息，可得到工件的位置信息及工序进出状态，以此实现对工件的追踪和定位，并录入MES生产管理系统，方便工厂工作人员对工件进行管理和检查。7) According to the reading results of the UHF RFID reader and the calibration information of the camera, the position information of the workpiece and the status of the process can be obtained, so as to realize the tracking and positioning of the workpiece, and input it into the MES production management system, which is convenient for the factory Workers manage and inspect workpieces.
对采集到的监控视频进行运动检测，获取运动物体的检测结果。因为工厂加工工件一般均为标准规格，故可以通过对监控视频进行大小识别，初步判定是否为加工工件。Perform motion detection on the collected surveillance video to obtain the detection results of moving objects. Because the factory-processed workpieces are generally of standard specifications, it is possible to preliminarily determine whether they are processed workpieces by identifying the size of the surveillance video.
参照图2，以基于opencv和python的运动检测为例，该算法的原理是，首先将视频帧转换为灰阶图像，然后用高斯模糊去除高频噪音，再用基于混合高斯模型的算法进行前景和背景的分割，将运动物体作为前景分离出来，以此得到运动中的物体的外轮廓，进行特征匹配，检测出运动物体。Referring to Figure 2, taking motion detection based on opencv and python as an example, the principle of the algorithm is to first convert the video frame into a grayscale image, then use Gaussian blur to remove high-frequency noise, and then use an algorithm based on a mixture of Gaussian models for foreground Segmentation with the background, separating the moving object as the foreground, so as to obtain the outer contour of the moving object, perform feature matching, and detect the moving object.
本实施例中前背景分离算法利用混合高斯分布模型来表征视频帧中每一个像素点的特征：图像的每一个像素点按不同权值的多个高斯分布的叠加来建模，每种高斯分布对应一个可能产生像素点所呈现颜色的状态，各个高斯分布的权值和分布参数随时间更新。建立有M个分量的混合高斯模型为：In this embodiment, the foreground and background separation algorithm uses a mixed Gaussian distribution model to characterize the characteristics of each pixel in the video frame: each pixel of the image is modeled by the superposition of multiple Gaussian distributions with different weights, each Gaussian distribution The weights and distribution parameters of each Gaussian distribution are updated over time corresponding to a state that may produce the color of the pixel. The mixed Gaussian model with M components is established as:
其中χT＝{x(t),…,x(t-T为时间段T内的某一时间t处的训练样本集，表示t时刻像素的RGB值，BG表示背景，FG表示前景，是估计的样本均值，是估计的标准差，是估计的混合权重。Wherein χT ={x(t) ,..., x(tT is the training sample set at a certain time t in the time period T, Represents the RGB value of the pixel at time t, BG represents the background, FG represents the foreground, is the estimated sample mean, is the estimated standard deviation, is the estimated mixing weight.
当获取新的视频帧时，将每个新像素值与当前模型进行比较，找到与其匹配的分布模型。When a new video frame is fetched, each new pixel value is Compare with the current model to find a distribution model that matches it.
在当前时刻选取混合高斯模型中的一个子集表征当前背景，如果当前视频帧的某个像素点所匹配的模型与混合高斯模型的背景子集匹配，则判定为背景，否则判定为前景点。Select a subset of the mixed Gaussian model at the current moment to represent the current background. If the model matched by a certain pixel of the current video frame matches the background subset of the mixed Gaussian model, it is determined as the background, otherwise it is determined as the foreground point.
同时，适时更新混合高斯分布模型，即根据tn时刻产生的新数据样本更新混合高斯模型：At the same time, update the mixed Gaussian distribution model in a timely manner, that is, according to the new data samples generated at time tn Update the mixture Gaussian model:
其中，令α＝1/T，cT＝0.01，同时，对于匹配的模型，将设为1，其余情况设为0；当不存在相匹配的模型时，通过如下方式产生新的高斯模型：Among them, order α=1/T, cT =0.01, meanwhile, for the matched model, the Set to 1, and set to 0 in other cases; when there is no matching model, a new Gaussian model is generated as follows:
其中σ0是某个给定的初始变化值。where σ0 is some given initial change value.
而当某一高斯模型的样本集合中m所占的权重值为负时，舍弃该高斯模型，以此实现高斯模型数量的自适应，实现缩短前背景分离的时间和提高准确度的目的。When the weight value of m in the sample set of a certain Gaussian model is negative, the Gaussian model is discarded, so as to realize the self-adaptation of the number of Gaussian models, shorten the time of foreground and background separation and improve the accuracy.
工件是否进入RFID启动区域进行判断，基于Cohen-Surtherland裁剪算法，其是利用区域边界将整个监控画面分成9个区域，并为每个区域赋予一个编码，通过计算得到运动物体外轮廓的线段的端点编码，与规定的区域编码进行比较，相同则处在该区域中，然后进一步判断运动物体的外轮廓线段是否与区域边界相交或是完全包容，最后可以得到整个物体与扫描区域边界相交或相包容的情况。Whether the workpiece enters the RFID start-up area is judged based on the Cohen-Surtherland clipping algorithm, which uses the area boundary to divide the entire monitoring screen into 9 areas, and assigns a code to each area, and obtains the endpoint of the line segment of the outer contour of the moving object through calculation Code, compare it with the specified area code, if it is the same, it is in the area, and then further judge whether the outer contour segment of the moving object intersects with the area boundary or is completely contained, and finally you can get the entire object and the scanning area boundary Intersect or contain Case.
对每台摄像头进行位置标定和工序进出状态的标定，当监测到运动物体进入超高频RFID读写器的启动区域之后，超高频RFID读写器启动，扫描工件标签，得到工件信息，结合摄像头的标定信息，可以确定工件的位置信息以及加工工序。Calibrate the position of each camera and the status of the process entry and exit. When a moving object is detected entering the start-up area of the UHF RFID reader, the UHF RFID reader starts, scans the workpiece label, and obtains the workpiece information. The calibration information of the camera can determine the position information of the workpiece and the processing procedure.
对工件定位的算法原理是，通过运动检测判断工件在监测区域内的具体位置，结合摄像头的位置标定信息和工序进出状态的标定信息，可以得到工件此时所处生产线上的加工工序信息以及工序完成状态，当触发超高频RFID读写器扫描工件的标签信息后，可以得到该工件较为完整的工件位置与加工状态的信息，然后这些数据将被上传至MES生产管理系统中，当系统存在多条关于同一工件的定位信息时，这些信息将被自动整合，得到该工件在整条生产线上的追踪定位情况，以便工厂人员对工件进行管理。The algorithm principle of workpiece positioning is to judge the specific position of the workpiece in the monitoring area through motion detection, and combine the position calibration information of the camera and the calibration information of the process entry and exit status to obtain the processing process information and process information of the workpiece on the production line at this time. Completed state, when the UHF RFID reader is triggered to scan the label information of the workpiece, the relatively complete workpiece location and processing status information of the workpiece can be obtained, and then these data will be uploaded to the MES production management system. When the system exists When there are multiple pieces of positioning information about the same workpiece, these information will be automatically integrated to obtain the tracking and positioning of the workpiece on the entire production line, so that factory personnel can manage the workpiece.
本领域的技术人员容易理解，以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。It is easy for those skilled in the art to understand that the above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention, All should be included within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510979813.4ACN105488806B (en) | 2015-12-23 | 2015-12-23 | A kind of location of workpiece tracking positioning method and positioning system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510979813.4ACN105488806B (en) | 2015-12-23 | 2015-12-23 | A kind of location of workpiece tracking positioning method and positioning system |
| Publication Number | Publication Date |
|---|---|
| CN105488806A CN105488806A (en) | 2016-04-13 |
| CN105488806Btrue CN105488806B (en) | 2018-08-03 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510979813.4AExpired - Fee RelatedCN105488806B (en) | 2015-12-23 | 2015-12-23 | A kind of location of workpiece tracking positioning method and positioning system |
| Country | Link |
|---|---|
| CN (1) | CN105488806B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106303420A (en)* | 2016-08-15 | 2017-01-04 | 深圳市校联宝科技有限公司 | A kind of monitoring method being applied to moving target and monitoring system |
| CN109509233B (en)* | 2018-11-16 | 2020-11-10 | 厦门博聪信息技术有限公司 | PTZ camera target tracking method, system and device based on RFID label position information |
| US11209795B2 (en) | 2019-02-28 | 2021-12-28 | Nanotronics Imaging, Inc. | Assembly error correction for assembly lines |
| CN109905847B (en)* | 2019-03-05 | 2020-11-03 | 长安大学 | Collaborative correction system and method for accumulative error of GNSS blind spot intelligent vehicle assisted positioning system |
| US11156991B2 (en) | 2019-06-24 | 2021-10-26 | Nanotronics Imaging, Inc. | Predictive process control for a manufacturing process |
| US11063965B1 (en) | 2019-12-19 | 2021-07-13 | Nanotronics Imaging, Inc. | Dynamic monitoring and securing of factory processes, equipment and automated systems |
| US11100221B2 (en) | 2019-10-08 | 2021-08-24 | Nanotronics Imaging, Inc. | Dynamic monitoring and securing of factory processes, equipment and automated systems |
| US12165353B2 (en) | 2019-11-06 | 2024-12-10 | Nanotronics Imaging, Inc. | Systems, methods, and media for manufacturing processes |
| US12153408B2 (en) | 2019-11-06 | 2024-11-26 | Nanotronics Imaging, Inc. | Systems, methods, and media for manufacturing processes |
| TWI760916B (en)* | 2019-11-06 | 2022-04-11 | 美商奈米創尼克影像公司 | Manufacturing system for automatic production line in factory |
| WO2021102223A1 (en) | 2019-11-20 | 2021-05-27 | Nanotronics Imaging, Inc. | Securing industrial production from sophisticated attacks |
| CN111008537A (en)* | 2019-12-05 | 2020-04-14 | 上海双十信息科技有限公司 | Ultrahigh frequency RFID (radio frequency identification) triggering reading method |
| CN111127517B (en)* | 2019-12-20 | 2023-06-09 | 北京容联易通信息技术有限公司 | Production line product positioning method based on monitoring video |
| CN111222428B (en)* | 2019-12-27 | 2023-05-16 | 北京容联易通信息技术有限公司 | Detection method for device fastening operation based on monitoring video |
| US11086988B1 (en) | 2020-02-28 | 2021-08-10 | Nanotronics Imaging, Inc. | Method, systems and apparatus for intelligently emulating factory control systems and simulating response data |
| CN112016409B (en)* | 2020-08-11 | 2024-08-02 | 艾普工华科技（武汉）有限公司 | A method and system for visual recognition and determination of work step specifications based on deep learning |
| CN112132465A (en)* | 2020-09-23 | 2020-12-25 | 创新奇智(青岛)科技有限公司 | Workpiece processing time consumption statistical method and device, electronic equipment and readable storage medium |
| CN113902386A (en)* | 2021-12-10 | 2022-01-07 | 广州赛意信息科技股份有限公司 | Industrial management system and method based on internet of things indoor positioning |
| CN115146750A (en)* | 2022-07-04 | 2022-10-04 | 深圳艾灵网络有限公司 | Monitoring system, method, device, processing equipment and storage medium of mold table |
| CN116760955B (en)* | 2023-08-18 | 2023-10-31 | 张家港保税区恒隆钢管有限公司 | Information tracking system for seamless steel pipe production |
| CN119758973A (en)* | 2025-03-10 | 2025-04-04 | 常州奥比利智能科技有限公司 | Intelligent manufacturing equipment abnormality detection method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879472A (en)* | 2012-09-22 | 2013-01-16 | 华南理工大学 | Adaptive steel rail ultrasonic flaw detection method and device based on frequency spectrum recognition |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070075142A1 (en)* | 2005-09-30 | 2007-04-05 | Symbol Technologies, Inc. | Mobile computer with integrated UHF RFID reader |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879472A (en)* | 2012-09-22 | 2013-01-16 | 华南理工大学 | Adaptive steel rail ultrasonic flaw detection method and device based on frequency spectrum recognition |
| Title |
|---|
| Indoor Location Technology and its Applications Base on improved LANDMARC Algorithm;Xie Yinggang等;《 Proceedings of the 2011 Chinese Control and Decision Conference》;20110523;第2458-2463页* |
| 面向模具生产过程的RFID实时定位系统研究;张靖暹等;《模具工业》;20140815;第40卷(第8期);第1-6页* |
| Publication number | Publication date |
|---|---|
| CN105488806A (en) | 2016-04-13 |
| Publication | Publication Date | Title |
|---|---|---|
| CN105488806B (en) | A kind of location of workpiece tracking positioning method and positioning system | |
| US12020415B2 (en) | Method for monitoring manufacture of assembly units | |
| CN106845890B (en) | Storage monitoring method and device based on video monitoring | |
| US20200380899A1 (en) | Method and apparatus for detecting peripheral circuit of display screen, electronic device, and storage medium | |
| EP3176751B1 (en) | Information processing device, information processing method, computer-readable recording medium, and inspection system | |
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| CN110865077B (en) | Visual inspection system for appearance defects in RFID antenna production | |
| CN108318773B (en) | Method and system for detecting broken strands of power transmission wires | |
| Laga et al. | Image-based plant stornata phenotyping | |
| CN111079638A (en) | Target detection model training method, device and medium based on convolutional neural network | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN114049624B (en) | Ship cabin intelligent detection method and system based on machine vision | |
| CN112115927A (en) | Intelligent machine room equipment identification method and system based on deep learning | |
| CN113820333B (en) | Battery pole piece abnormality detection method, device, upper computer and detection system | |
| CN109308448A (en) | A method of using image processing technology to prevent misoperation of power distribution and distribution | |
| CN113778091A (en) | A kind of inspection method for wind farm booster station equipment | |
| CN117011216A (en) | Defect detection method and device, electronic equipment and storage medium | |
| KR20200123324A (en) | A method for pig segmentation using connected component analysis and yolo algorithm | |
| CN117314829A (en) | Industrial part quality inspection method and system based on computer vision | |
| CN116386120A (en) | Noninductive monitoring management system | |
| CN108364306A (en) | A kind of vision real-time detection method of high speed periodic motion | |
| CN114283413B (en) | Method and system for identifying digital instrument readings in inspection scene | |
| NDAYISHIMIYE et al. | SMD detection and classification using YOLO network based on robust data preprocessing and augmentation techniques | |
| CN116486141A (en) | Plank grade classification and cutting method and system based on multi-mode image recognition | |
| Tunsoiu et al. | Optimization of Real‐Time Monitoring and Control of Industrial Conveyor Systems Using Vision Automated Identification Methods |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20180803 Termination date:20201223 |