Night-time fruit-picking technology is important to picking robots. This paper proposes a method of night-time detection and picking-point positioning for green grape-picking robots to solve the difficult problem of green grape detection and picking in night-time conditions with artificial lighting systems. Taking a representative green grape named Centennial Seedless as the research object, daytime and night-time grape images were captured by a custom-designed visual system. Detection was conducted employing the following steps: (1) The RGB (red, green and blue). Color model was determined for night-time green grape detection through analysis of color features of grape images under daytime natural light and night-time artificial lighting. The R component of the RGB color model was rotated and the image resolution was compressed; (2) The improved Chan–Vese (C–V) level set model and morphological processing method were used to remove the background of the image, leaving out the grape fruit; (3) Based on the character of grape vertical suspension, combining the principle of the minimum circumscribed rectangle of fruit and the Hough straight line detection method, straight-line fitting for the fruit stem was conducted and the picking point was calculated using the stem with an angle of fitting line and vertical line less than 15°. The visual detection experiment results showed that the accuracy of grape fruit detection was 91.67% and the average running time of the proposed algorithm was 0.46 s. The picking-point calculation experiment results showed that the highest accuracy for the picking-point calculation was 92.5%, while the lowest was 80%. The results demonstrate that the proposed method of night-time green grape detection and picking-point calculation can provide technical support to the grape-picking robots.

The non-destructive testing of litchi fruit is of great significance to the fresh-keeping, storage and transportation of harvested litchis. To achieve quick and accurate micro-damage detection, a non-destructive grading test method for litchi fruits was studied using 400–1000 nm hyperspectral imaging technology. The Huaizhi litchi was chosen in this study, and the hyperspectral data average for the region of interest (ROI) of litchi fruit was extracted for spectral data analysis. Then the hyperspectral data samples of fresh and micro-damaged litchi fruits were selected, and a partial least squares discriminant analysis (PLS-DA) was used to establish a prediction model for the realization of qualitative analysis for litchis with different qualities. For the external validation set, the mean per-type recall and precision were 94.10% and 93.95%, respectively. Principal component analysis (PCA) was used to determine the sensitive wavelength for recognition of litchi quality characteristics, with the results of wavelengths corresponding to the local extremum for the weight coefficient of PC3, i.e., 694, 725 and 798 nm. Then the single-band images corresponding to each sensitive wavelength were analyzed. Finally, the 7-dimension features of the PC3 image were extracted using the Gray Level Co-occurrence Matrix (GLCM). Through image processing, least squares support vector machine (LS-SVM) modeling was conducted to classify the different qualities of litchis. The model was validated using the experiment data, and the average accuracy of the validation set was 93.75%, while the external validation set was 95%. The results indicate the feasibility of using hyperspectral imaging technology in litchi postpartum non-destructive detection and classification.

It is very important to classify and identify the quality of potato by computer vision. In order to realize the accurate and fast classification of potato, a classification and recognition method based on support vector machine and PCA is proposed. Study uses normal potato, green potato, germinated potato and damaged potato as the experiment sample. A total of 600 images were collected where 150 images of each sample was collected. The SVM multi classifier is designed to train the classifier based on the PCA principal component vector, and the key parameters of the classifier are optimized to improve the overall recognition rate of 96.6%. Separately, the normal potato recognition rate is 97.5%, the greened potatoes is 96.3%, the damaged potato is 95.0% and the germinated potato is 97.5%. The research results provide technical support for the intelligent grading of fruit and vegetable quality.