Abstract: Abstract: With the advancement of digital agriculture, researching on pig weight estimation by using machine vision technology has become one of hotspots. The outside light environment of machine vision has a great influence on the quality of captured images. Ignoring the significance of lighting system, majorities of studies on pig weight estimation focused on algorithms and image processing without quantitative assessment methods of light environment. This research focus on the light environment for machine vision in typical piggery and the purpose is to explore a method to achieve effectively screening images taken by monitoring platform to filter out a large amount of invalid images interfered by outside light environment. This paper, based on pig weight monitoring platform, LabVIEW software was used to analyze the image quality of actual light environment condition. Researches consisted of field test and laboratory test. Light measurement of region of interest was mainly carried out in field test during different breeding periods as well as with different heights of pig body. Laboratory test was divided into two parts. One was the calibration of light sensor and the other was image processing for comparing the difference between the algorithm value and the real value. Experiments were carried out in the experimental station of Shangzhuang of China Agricultural University and the test objects were 5 heads of castration landrace. AS813 illuminance meter of SMART SENSOR Company was used to conduct research in test spot. In order to ensure the data accuracy, it was conducted two times of sensor calibration. The analysis of uniformity of illumination in measurement area was referred to lighting engineering standards for evaluating the intensity of illumination evenness. U1 and U2 parameters were used to evaluate evenness index of illumination intensity. U1 is the ratio of the minimum illuminance and the maximum illuminance. U2 is the ratio of the minimum illuminance and the average illuminance. By means of computer software program, it could replace artificial measures to realize the measurement of illumination simulation values, the gray level change rate and image exposure judgement parameters. After on-site validation experiments as well as data analysis, it had not significant difference among light measurements of various height of pig body during breeding period. Also, it had no obvious difference between measured value and simulation value. The correlation coefficient of U1 between measured value and simulation value is 0.791 and the correlation coefficient of U2 between measured value and simulation value is 0.853. Replacing measured values, simulation can fast achieve the distribution of the light environment approximately. Illumination correction coefficient τ was put forward in order to ensure the validity of the data, reflect the true light environment and make up for 20% relative error of the measurement instrument. In addition, it is obviously different among ideal image, overexposed image, natural light image and Yin and Yang image in the parameters of exposure and uniformity ratio of illumination: the illumination uniformity parameters of ideal image and overexposed image meet the requirement of standards of illuminating engineering, and the normal rate of exposure for ideal image rate is higher. The illumination uniformity parameters of natural light image and Yin and Yang image did not meet the requirements of standards of illuminating engineering. Judgment standards of normal exposure were determined at U1>0.7 and U2>0.8 to realize the filter of ideal image which is convenient for researchers screening out ideal image.