This paper aims to design a multi-line structured light projector with equal spacing, small volume and long-term use. The application background of the projector is the rubber coating detection in the automobile industry, which needs to have the characteristics of high brightness, good monochromaticity, and clear visible projection on the black plastic material. Because the glue is slightly heated, the glue will affect the detection effect. Therefore, it is necessary to ensure sufficient light intensity, and the light is not too strong. Too strong light will cause the glue to be baked and lose the meaning of detection. The projector designed in this paper utilizes a plurality of semi-transparent mirror splitting and wire-cutting processing means to ensure the positional relationship of the light strips. It has the following advantages: simple structure, convenient calibration, small size and low price.
In the online measurement of automotive body-in-white, the fixed visual online measuring equipment and flexible visual online measuring equipment are often used in the field to meet different measurement requirements. Therefore, it is necessary to calibrate the two systems separately before measurement. The hybrid measurement equipment’s calibration is involuted and inefficient. So, in this paper, an integral-fast calibration method for flexible and fixed on-line detection equipment is proposed to solve these problems. In this paper, the calibration theory and the on-site calibration technique are described in detail. The following is a summary of the calibration process. First, measuring the same target simultaneously with the fixed vision sensor and the flexible vision sensor. Then, according to the robot's own coordinate equipment relationship in the flexible measurement, the control points are multipath measured and the hand-eye relationship of the robot is calculated. Then, the relationship between the vehicle body coordinate equipment and the robot base coordinate equipment is calculated by using the laser tracker according to the vehicle body positioning reference and the target control point. At last, and the coordinate equipment conversion relationship of the fixed measurement equipment is simultaneously calibrated according to the result of the flexible measurement equipment. Eliminating the section for separate measurement of the fixed measurement equipment by the laser tracker and saving calibration time. Ensuring the overall measurement consistency of the hybrid measurement equipment. We designed a verification test and the test results show that the standard deviation of the calibration method can reach 0.15mm, and the calibration method has high efficiency and simple method, which can meet the calibration requirements of the body-in-white measuring equipment in the field environment.
Food packaging bags are fast-moving consumer products with large output and fast production speed. Instant noodle bags need to be printed on the production date and number before packaging the food. For the possible date or code printing error, character sticking, incompleteness, etc., the correctness of the characters cannot be judged in real time by the human eye. A set of automatic recognition characters and detection systems are used to binarize, filter and tilt the picture, and use image morphology and horizontal and vertical projection to segment a single character. BP neural network is used to identify the character and compare it to the template to obtain the degree of defect and compare it with the threshold to determine whether the character is qualified. The detection speed of the system can reach 3 images per second, which can realize real-time recognition and detection of characters, so as to eliminate non-conforming products in time.