Sugarcane mechanized planting technology consists of seed preparation and field planting. This study aims at the issues of easy damage to the seeds during the operation of the automatic cutting machine for single-bud segment sugarcane, lack of intelligent seed selection and calibration technology, low recognition accuracy, and the need for manual feeding of the planting machine’s seed meter which leads to seed leakage. This study, based on machine vision and deep learning, optimizes the seed calibration method and proposes an improved YoloV5-STD target detection algorithm to improve the recognition accuracy of seed characteristics and optimize the overall engineering structure. For the planting machine, a new type of hopper for the seed meter is designed using natural rubber as the base material mixed with polystyrene, and the flexible automatic seed metering mechanism is analyzed to achieve automatic feeding and seed metering. Test assessment indicators were formulated based on the enterprise standards of the Institute of Agricultural Machinery Research, Chinese Academy of Tropical Agricultural Sciences. Experimental results show that the recognition accuracy of the 2DZ-2 type single-bud segment intelligent cutting machine is ≥95%, the bud injury rate is <1.8%, the qualified rate of cutting is 95.8%, and the single-channel cutting efficiency is 64 buds/min. The 2CZD-2C type single-bud segment planter has a planting qualification rate of 96.6%, a planting efficiency of 208 buds/min, and a seed leakage rate of <2.1%.

This paper proposes a sugarcane image stitching algorithm based on an improved SURF method to capture high-quality, wide-field images of complete sugarcane stalks. To enhance registration accuracy, artificial markers are introduced into the background, helping to address the challenges posed by the smooth surface of sugarcane and low feature point matching precision. Additionally, a mesh segmentation technique combined with an enhanced SURF algorithm is used for feature extraction, which tackles issues such as uneven feature distribution and slow processing speed caused by global image feature extraction. A double screening registration method is also proposed to further improve the accuracy of image mosaicing. To reduce stitching gaps, an image fusion technique based on the optimal suture line is employed. Experimental results show that the algorithm has an average runtime of about 2900 ms, slightly longer than the ORB algorithm at 2000 ms but significantly faster than the original SURF at 4200 ms. In terms of stitching quality, the average image information entropy is 6.34, which is higher than both the SURF (6.325) and ORB (6.075) algorithms, indicating better image quality.