Industrial CCD Camera Research Articles

An Improved Crack Identification Method for Asphalt Concrete Pavement

The results of high-precision asphalt concrete pavement crack identification can provide help for pavement maintenance. Therefore, methods of image feature enhancement and crack identification of asphalt concrete pavement cracks are proposed. First of all, we used an industrial CCD camera mounted on a vehicle to collect an asphalt concrete pavement crack image. Then, after using the NeighShrink algorithm to denoise the acquired image, a fractional differential image enhancement algorithm was designed based on image feature blocks to enhance the image features. On this basis, crack characteristics were segmented and processed by watershed algorithm. Through crack direction identification and crack parameter extraction, crack distribution direction, crack length and width and other parameters of asphalt concrete pavement were obtained in order to achieve accurate identification of asphalt concrete pavement cracks. The experiment found that this method can effectively remove noise information from asphalt concrete crack images; after applying this method, the image entropy value of each image was improved, with a minimum improvement of 0.38 and a maximum improvement of 1.98. The time consumed by this method in identifying cracks in asphalt concrete pavement varied between 1.4 s and 2.4 s. When identifying the length of cracks in asphalt concrete pavement, the maximum deviation value was only 0.47 mm; when identifying the width of cracks in asphalt concrete pavement, the maximum deviation value was only 0.31 mm. The above results indicate that by enhancing the image features of asphalt concrete cracks, this method achieves more accurate identification results for crack distribution direction, length and width values, with high identification efficiency and good application effect.

Vision and sound fusion-based material removal rate monitoring for abrasive belt grinding using improved LightGBM algorithm

Accurate material removal modeling is the basis for optimizing the surface quality and improving the performance of equipment components. In this study, a multi-sensor fusion method of vision and sound is used to monitor in-process grinding material removal rate (MRR). First, belt grinding experiments are conducted using different grinding parameters, and vision and sound signals are captured by industrial CCD cameras and an omnidirectional condenser microphone, respectively. Second, the features of the captured grinding spark images are extracted based on two aspects: color and texture, and those of the grinding sound are investigated in the time, frequency, and time–frequency domains. Moreover, the complementarity between the vision and sound signals and their sensitivity to different grinding parameters are discussed. Finally, based on feature-level fusion strategies, the Pearson correlation coefficient and the sequential backward selection algorithms are jointly used to select the optimal feature subsets. MRR prediction models are established using the selected feature subsets and an improved light gradient boosting machine (LightGBM) algorithm. The test results show that the error in the MRR prediction model of same-specification abrasive belts is less than 3 %, and the coefficient, R2, is as high as 99.2 %. The proposed method can be used to predict the MRR resulting from a single grinding parameter and multiple ones, using the same-specification abrasive belts. Compared to other prediction models, the improved LightGBM model is superior in terms of the time factor without reduction in the accuracy of the model.

A Colony Picking Control System Based on Machine Vision

With rapid growth of the number of genomic sequences, researchers are faced with the task of managing huge clone libraries. A single experiment may involve classifying tens of thousands of bacterial, yeast or phage colonies. While, repetitive manual operation is followed by a lower efficiency and accuracy of colony picking and inoculating, leading to the fail in high throughput. In order to improve the efficiency and accuracy of colony picking process, this paper introduces a prototype, which picks colonies automatically. After analysis of colony picking process, we develop a colony picking control system based on industrial computer and CCD camera. Beyond that, we put forward the design of hardware and software of system. Finally, picking and inoculating colonies, as well as cleaning and heating needles come true.

An electrode misalignment inspection system based on image processing technology for use in resistance spot welding

Weld quality in resistance spot welding (RSW) is greatly affected by any misalignment of the upper and lower electrodes. This work presents a non-contacting system for measuring electrode misalignment. It uses two industrial CCD cameras, oriented perpendicular to one another in the same plane. The electrode cap images taken by the CCD cameras are sent to a computer through an Ethernet switch. The original red, green and blue (RGB) images are converted to greyscale images. The left and right edge points of the cap images are determined by computing the first derivative of the grey level gradient of the images; the edge points are the locations of local maxima in the horizontal direction. Using the edge points, linear boundaries are fitted via the least squares method, and the noise points are eliminated. The axes of the electrode caps are calculated from the left and right linear boundaries of the images, and then the spatial and angular offsets of the two electrode axes can be determined by the two axis functions. The results of comparison experiments indicate that the abovementioned system can rapidly and accurately measure the misalignment of electrodes during the process of RSW. The measurement results will provide critical input for equipment adjustment and maintenance.

Online droplet monitoring in inkjet 3D printing using catadioptric stereo system

Inkjet 3D printing is becoming one of the most disruptive additive manufacturing technologies, due to its unique capability of precisely depositing micro-droplets of multi-functional materials. It has found widespread industrial applications in aerospace, energy and health areas by processing multi-functional metal-materials, nano-materials, and bio-materials. However, the current inkjet 3D printing system still suffers from a low production quality issue, due to low process reliability caused by the complex and dynamic droplet dispensing behavior. Due to the challenges in terms of efficiency, accuracy, and versatility, robust droplet monitoring and process inspection tools are still largely unavailable. To this end, a novel catadioptric stereo system is proposed for online droplet monitoring in an inkjet 3D printing process. In this system, a regular industrial CCD camera is coupled with a flat mirror and magnification lens system to capture the tiny droplet images to detect the droplet location in 3D space. A mathematical model is formulated to calculate the droplet location in 3D world space from 2D image space. A holistic hardware and software framework is constructed to evaluate the performance of the proposed system in terms of resolution, accuracy, efficiency, and versatility, both theoretically and experimentally. The results show that the proposed catadioptric stereo system can achieve single micron resolution and accuracy, which is one-order-of-magnitude higher than the 3D printing system itself. The proposed droplet location detection algorithm has low time complexity, and the detection efficiency can meet the online monitoring requirement. Multi-facet features including the droplet location and speed can be effectively detected by the presented technique. The proposed catadioptric stereo system is a promising online droplet monitoring tool and has tremendous potential to enable trustworthy quality assurance in inkjet 3D printing.

Principle of an innovative visual sensor based on combined laser structured lights and its experimental verification

To promote development of sensing technology applied in the welding process and improvement of production automation in the welding manufacturing industry, an innovative multi-functional monocular visual sensor based on combined laser structured lights (single-line & cross-lines) is proposed and devised. It can realize the detection of cross-sectional size parameters of welding groove, space position and posture of welding torch relative to the weldment or welding groove by using monocular vision. Its calibration makes full use of the intrinsic parameters, such as its internal structure parameters and the focal length of industrial CCD camera. Therefore, it is unnecessary to re-calibrate when the position and posture of welding torch have some variations during the welding process or the visual sensor reassembles with the welding torch, which availably improves the adaptability of this sensor in engineering application, so that it can apply to the welding process with complex space welding trajectory. Furthermore, with the use of combined laser structured lights, it effectively eliminates the problem of information loss in depth commonly existing in usual monocular visual sensor. Meanwhile, all the detection functions of this sensor are derived from the processing results of a single image captured by industrial CCD camera, which avoids the problems of time-consuming and large amount of calculation resulting from multi-images processing (multi-vision method or multi-angle time-sharing imaging in monocular vision), and thus significantly improves its real-time performance in engineering application. Its functional detection algorithms for the cross-sectional size parameters of welding groove and the height of welding torch derived from the principle of optical triangulation are given. After establishing a test platform, we carried out a series of detecting experiments for different types or sizes of V-type butt groove. By image processing, recognition and extraction of the feature points, the cross-sectional size parameters of welding groove and the height of welding torch calculate out through the derived detection algorithms. The acquired detection results have enough accuracy and their maximum relative errors are not exceeding 3.9%, which demonstrate the rationality of the physical design for the proposed visual sensor and the validity of the derived detection algorithms.

Liquid metals surface temperature fields measurements with a two-colour pyrometer

Abstract The paper presents an apparatus to measure surface temperature distribution of liquid metals during fusion processes. The apparatus is based on dual wavelength radiation thermometry and is designed to measure temperature from 1500 to 3000 K. The pyrometer is based on standard optical parts and industrial CCD cameras. Uncertainties are analysed on the base of the radiometric equations. To insure relative precision in the measurement, a calibration procedure is conducted on tungsten ribbon with known emissivity in the temperature range. This procedure is also used to discuss the influence of wavelength couples. To conclude, experimental measurements on pure laser melted materials are conducted to assess the validity of the apparatus and methodology.

Measurement of the Average Two-Dimensional Surface Temperature Distribution of Drops in a Melt Atomization Process

During the production of metal and alloy powders by melt atomization, the knowledge of the surface temperature distribution of drops is essential. This paper shows the application of low-cost industrial CCD-cameras in connection with advanced image processing techniques to measure the average two-dimensional surface temperature distribution of drops in a melt atomization process. These measurements are necessary for comparison with the results of numerical investigations. The two-color pyrometer consists of two standard industrial CCD-cameras with appropriate optical filters. After calibration using a high-temperature furnace, the relative measurement error was smaller than 1.6% within the temperature range of 1273-1873 K. The pyrometer was applied to measure the average temperature distribution during the metal spraying process in a vacuum inert gas atomization facility. The measured temperature distribution averaged over 10 ms shows the development of a hollow cone spray of the atomized metal. The average axial distance between the atomization nozzle and the region of the liquidus temperature was found to be approximately 40 times the diameter of the atomization nozzle.

Weld Pool and Keyhole Detection Based on Visual Sensors in Plasma Arc Welding

An observation system is developed with three ordinary industrial CCD cameras to capture the images of the weld pool and the keyhole. Experiments are conducted to evaluate the affecting relationship between welding parameters (welding current and welding speed) and the size of weld pool and keyhole. The observation results lay foundation to understand the weld pool and the keyhole behavior in PAW process and to design the future control system.

In-line imaging measurements of particle size, velocity and concentration in a particulate two-phase flow

A novel method is developed for in-line measurements of particle size, velocity and concentration in a dilute, particulate two-phase flow based on trajectory image processing. The measurement system consists of a common industrial CCD camera, an inexpensive LED light and a telecentric lens. In this work, the image pre-processing steps include stitching, illumination correction, binarization, denoising, and the elimination of unreal and defocused particles. A top-hat transformation is found to be very effective for the binarization of images with non-uniform background illumination. Particle trajectories measured within a certain exposure time are used to directly obtain particle size and velocity. The particle concentration is calculated by using the statistics of recognized particles within the field of view. We validate our method by analyzing experiments in a gas-droplet cyclone separator. This in-line image processing method can significantly reduce the measurement cost and avoid the data inversion process involved in the light scattering method.

The Design of a Rubik's Cube Robot

This paper depicts the system design of a robot that can recover the disrupted Rubiks Cube automatically. The robot is a typical mechatronics system consisted of the mechanical structure and the electrical system. The recovery procedures of the Rubiks Cube are shown as follows. Firstly, the color recognition of each face of the Rubiks Cube is conducted with an industrial CCD camera. Then the embedded recovery algorithm is called, and the recovery steps are achieved. Finally, the pneumatic manipulators are driven by the pressurized air controllable via an electrical relay array, the Rubiks Cube is recovered step by step following the recovery sequences. The Rubiks Cube robots have been exhibited in several science museums in China, they are well welcomed by the audiences.

Vacuum Casting Bubble Automatic Elimination System Based on on-Line Machine Vision Detection

Bubbles in vacuum casting process are dense, tiny and overlapped. The difference between bubbles and the background is so indistinct that makes bubble detection a great difficulty. Bubble elimination has become the main obstacle in the way of vacuum casting machine’s automation development. Bubble automatic detection is the base of bubble elimination. A machine vision bubble on-line detecting and eliminating platform is constructed, using industrial high-speed CCD camera and professional LED illumination. According to the features of vacuum casting bubbles, the edge pixel ratio algorithm is designed especially for vacuum casting bubble detection. The algorithm is realized using VC++ and Open CV. The integrated system proposed can detect and eliminate vacuum casting bubbles on-line automatically. As it’s confirmed, there is an obviously positive correlation between the edge pixel ratio and the bubble denseness. This detection system makes sense in vacuum casting bubble elimination.

Detection and anadysis of weld pool shape for CO2 short circuiting arc welding

A general industrial CCD(ICCD) camera is redesigned to detect the weld pool without arc at the period of short circuiting,so that the interference of arc and spatter during CO2 short circuiting arc welding is eliminated. Through the analysis of weld pool image, both size parameters (such as weld pool area A, weld pool length L1, L2 and weld pool breadth b) and contour parameters (bi which describe the curves of weld pool boundany) ,which could indicate the shape features of weld pool, had been defined to express weld pool information quantitatively. The investigation of the relationships between weld pool shape parameters and welding process parameters may be beneficial to the quality control of CO2 welding.

Setting of a Low Price CCD Camera on the View Window of TEM for Printing Out Electron Diffraction Patterns

In order to print out electron diffraction patterns quickly, an industrial CCD camera is conveniently set on the view window of an electron microscope. Although the observed pattern on the camera is distorted since the view direction has an angle of 41.5 degrees from the normal of the screen, however, the printed pattern is successfully restored to the correct one by varying the aspect ratio from 3:4 for the CCD camera to 1:1 for the printer. Note that cos(41.5) = 3/4. The camera used has a sensitivity of 1 lux. The aperture ratio of the lens is F 1.4, and the focal length is 50 mm.