Potato is one of the most important food crops in the world, which is of great significance for sustainable agricultural development. Mechanized planting is the essential technical link in mechanized production, which has an essential component in the potato growing industry. The mechanization of potato planting technology is an effective method of increasing potato yields. A variety of potato planting technologies and machines have been developed around the world. This review presents the research progress and application status of potato planters and planting technology worldwide. It classifies the planting technology into four types: research of materials characteristics for potatoes, soil cultivation, seed potato separation, and zero-speed seeding. The most critical seed potato separation technology was divided into six types according to the structure of the seed metering device. Detailed features have been provided for some typical potato planters and soil cultivation machines. Finally, the developing trend of intelligent planting technology was analyzed, and some suggestions were proposed to promote the development of potato planters.

The amplitude of excitation force from exciters used in fruit tree vibration harvesting remains constant at a given frequency, leading to poor fruit detachment ratio and tree damage. A solution has been proposed through the development of a Double-Symmetric Eccentric Exciter (DSEE). This new exciter allows for the adjustment of excitation force amplitude while maintaining a constant frequency by varying the phase angle of the DSEE. To validate the effectiveness of the DSEE, vibration tests were conducted on fruit trees using different parameter exciting forces. Acceleration sensors were employed to measure the vibration accelerations of the tree branches. The experimental results revealed that when a fixed frequency excitation force with a constant phase angle was applied to the trunk, the vibration acceleration of branches exhibited inconsistent variations due to differences in the vibration differential equation parameters of each branch. Furthermore, it was observed that increasing the phase angle of the DSEE at a fixed frequency led to larger vibration accelerations in every branch. This signifies that adjusting the phase angle of the DSEE can effectively increase the amplitude of the exciting force. Consequently, the ability to control both the amplitude and frequency of the excitation force independently can mitigate issues such as low fruit harvest rates and minimize damage to fruit trees.

In order to design a branch-cutting type green pepper harvesting device, we firstly study the whole process of straight knife green pepper cutting to reveal the cutting mechanism and provide theoretical guidance to the design. A finite element model was established for the cutting of pepper branches across the distance, and single-factor and multi-factor finite element simulation tests were conducted on the knife feed angle, tool edge angle, and knife feed speed of the working parts of the pepper cutting and harvesting device. The results of the experiment were analyzed by ANOVA, which showed the different degrees of importance of these factors, and the optimal parameters were obtained by response surface methodology (RSM). With the optimal parameters selected, the predicted maximum cutting force and cutting completion were 803.35 N and 98.58%, respectively, this satisfies the efficiency and economy requirements of agricultural machinery design. In addition, the cutting force of green pepper branches was analyzed and a theoretical mechanical model was developed to help us understand the variation of cutting force numerically. The stress–strain system, high-speed photography system and numerical prediction were innovatively combined to observe and measure the stress and other key state variables in the cutting process in detail, summarize their changing trend, and establish a time-based monitoring and comparison model. The above research results can provide a reference for the design of green pepper branch cutting and harvesting devices, such as direct guidance on the selection of working parameters, materials, etc., and guidance on the operation in actual work.

Image blur is a major factor that degrades object detection in agricultural applications, particularly in orchards where crop occlusion, leaf movement, and camera shake frequently reduce image quality. This study proposed a lightweight generative adversarial network, AGG-DeblurGAN, to address non-uniform motion blur in citrus tree images. The model integrates the GhostNet backbone, attention-enhanced Ghost modules, and a Gated Half Instance Normalization Module. A blur detection mechanism enabled dynamic routing, reducing computation on sharp images. Experiments on a citrus dataset showed that AGG-DeblurGAN maintained restoration quality while improving efficiency. For object detection, restored citrus images achieved an 86.4% improvement in mAP@0.5:0.95, a 76.9% gain in recall, and a 40.1% increase in F1 score compared to blurred images, while the false negative rate dropped by 63.9%. These results indicate that AGG-DeblurGAN can serve as a reference for improving image preprocessing and detection performance in agricultural vision systems.

Reliable detection of small agricultural targets is fundamental to precision crop protection, phenotyping, yield estimation, and robotic intervention. Typical examples include detecting aphids such as Aphis gossypii, whiteflies such as Bemisia tabaci, planthoppers such as Nilaparvata lugens, and other tiny pests on sticky traps or crop canopies for early warning, identifying crop-like weed seedlings for site-specific herbicide spraying, locating early disease lesions for targeted treatment, and detecting young fruits, flowers, or wheat heads for yield estimation and robotic manipulation. Agricultural small-object detection differs from generic small-object detection because target visibility is jointly determined by pixel area, physical size, imaging distance, ground sampling distance, canopy structure, biological similarity, and task-specific intervention requirements. Existing reviews have summarized agricultural object detection or general small-object detection, but they rarely connect agricultural failure modes with detector-level mechanisms and reproducible evaluation practices. This review addresses this gap through a mechanism-oriented synthesis of agricultural small-object detection. First, we revisit the limitations of the COCO-style 32²-pixel threshold and propose an agricultural scale-reporting framework that combines pixel area, physical scale, relative image occupancy, and acquisition geometry. Second, we organize recent methods according to the mechanisms by which they address detail loss, scale shift, occlusion, dense distributions, foreground–background confusion, localization uncertainty, and edge-deployment constraints. Third, we summarize public datasets, quantitative evaluation metrics, reporting checklists, and real-device deployment evidence to support fair and field-oriented comparison. Finally, we identify future directions in multimodal sensing, foundation-model adaptation, label-efficient learning, and hardware-aware optimization. By linking agricultural scene characteristics, detector mechanisms, and evaluation requirements, this review aims to provide a more actionable framework for developing robust small-object detection systems in precision agriculture.

Stem mustard, the main raw material for pickled mustard tuber, is widely planted in Chongqing, China, and is an important local cash crop. Under the working conditions of sticky and wet soil in the Chongqing area, conventional furrow seeding has problems such as soil sticking to the furrow opener, poor mulching effect, etc. In this regard, this paper proposes the use of non-contact, soil-based, pneumatic shot seeding, in which seeds are shot into the soil to a predetermined depth by a high-speed air stream. The diameter of stem mustard seeds was found to be 1.33 mm, with a spherical rate of 95.32% using physical and mechanical properties. The high-speed camera test was used to determine the air pressure at the appropriate sowing depth, and the seed entry process was simulated by EDEM 2021 software, which analysed the movement process of the seed after entering the soil, and the structure of the seeder was designed based on the resulting test data. The structural parameters of the shot seeding device were analysed by a hydrodynamic simulation using Fluent 2022 R1 software and the following results were obtained: an outlet pipe diameter D_C of 2 mm, mixing zone length H of 10 mm, mixing zone inlet diameter D of 15 mm, and steady-state gas flow rate of 80 m/s. Simulation seeding verification was conducted on the final determined structural parameters of the seeding device, and the simulation results showed that the seed velocity could reach 32.3 m/s. In actual experiments, it was found that when the vertical velocity of the seeds was greater than or equal to 26.59 m/s, the seeds could be completely and stably seeded into the soil. Therefore, the designed seeding device can meet the conditions of actual seeding experiments. In conclusion, this research offers a practical guideline for the rapid and precise sowing of stem mustard.