Rain spots on green plum are superficial micro-defects. Defect detection based on a two-dimensional image is easily influenced by factors such as placement position and light and is prone to misjudgment and omission, which are the main problems affecting the accuracy of defect screening of green plum. In this paper, using computer vision technology, an improved structure from motion (SFM) and patch-based multi-view stereo (PMVS) algorithm based on similar graph clustering and graph matching is proposed to perform three-dimensional sparse and dense reconstruction of green plums. The results show that, compared with the traditional algorithm, the running time of this algorithm is lower, at only 26.55 s, and the mean values of camera optical center error and pose error are 0.019 and 0.631, respectively. This method obtains a higher reconstruction accuracy to meet the subsequent plum micro-defect detection requirements. Aiming at the dense point cloud model of green plums, through point cloud preprocessing, the improved adaptive segmentation algorithm based on the Lab color space realizes the effective segmentation of the point cloud of green plum micro-defects. The experimental results show that the average running time of the improved adaptive segmentation algorithm is 2.56 s, showing a faster segmentation speed and better effect than the traditional K-means and K-means++ algorithms. After clustering the micro-defect point cloud, the micro-defect information of green plums was extracted on the basis of random sample consensus (RANSAC) plane fitting, which provides a theoretical model for further improving the accuracy of sorting the appearance quality of green plums.

In recent years, machine vision has played an important role in product surface quality detection. The promotion and use of this technology have largely avoided the subjectivity caused by human detection and improved detection efficiency and accuracy. Different from the image data commonly used in machine vision, point cloud can describe the spatial structure of an object, provide more information than image data, and have the ability to expand the data to build multi-dimensional data models. Due to the strong anti-interference ability of point cloud sensors and the high accuracy of three-dimensional positioning information point cloud, nondestructive testing technology based on point cloud has received more and more attention. This paper summarizes the research progress of product surface quality detection methods based on 3D point cloud in recent years. According to different data processing methods, the detection research is divided into five categories: based on point cloud contour, based on local geometric feature, based on template matching, based on multimodal point cloud, and based on deep learning. The five methods are reviewed and summarized respectively. Finally, the key problems of each detection method and the future trend of product surface quality detection technology based on 3D point cloud are discussed.

The growth quality of Pinus massoniana (Lamb.) seedlings is closely related to the survival rate of afforestation. Moisture content detection is an important indicator in the cultivation of forest seedlings because it can directly reflect the adaptability and growth potential of the seedlings to the soil environment. To improve the accuracy of quantitative analysis of moisture content in P. massoniana seedlings using near-infrared spectroscopy, a total of 100 P. massoniana seedlings were collected, and their near-infrared diffuse reflectance spectra were measured in the range of 2500 to 800 nm (12,000 to 4000 cm−1). An integrated learning framework was introduced, and a quantitative detection model for moisture content in P. massoniana seedlings was established by combining preprocessing and feature wavelength selection methods in chemometrics. Our results showed that the information carried by the spectra after multiple scattering correction (MSC) preprocessing had a good response to the target attribute. The stacking learning model based on the full-band spectrum had a prediction coefficient of determination R2 of 0.8819, and the prediction accuracy of moisture content in P. massoniana seedlings could be significantly improved compared to the single model. After variable selection, the spectrum processed by MSC and feature selection with uninformative variable elimination (UVE) showed good prediction effects in all models. Additionally, the prediction coefficient of determination R2 of the support vector regression (SVR)—adaptive boosting (AdaBoost)—partial least squares regression (PLSR) + AdaBoost model reached 0.9430. This indicates that the quantitative analysis model of moisture content in P. massoniana seedlings established through preprocessing, feature selection, and stacking learning models can achieve high accuracy in predicting moisture content in P. massoniana seedlings. This model can provide a feasible technical reference for the precision cultivation of P. massoniana seedlings.