Aiming at the problem of grain breakage during the harvesting of fresh corn, this paper theoretically analyzes the collision process between the ear picking device and the corn ear, and a flexible ear picking structure composed of flexible materials and buffer springs is determined. Combined with a new harvesting method that reverses the growth direction from top to bottom, a reverse flexible ear plucking device for fresh corn was designed. We used the ADAMS software to simulate the ear picking process of fresh corn, analyze the contact force between the rigid structure and flexible buffer structure under different picking claw speeds and stalk feeding speeds, and obtain the optimal parameter combination: the picking claw speed was 2 m/s, and the stalk feeding speed was 1 m/s. On the basis of the simulation, a reverse flexible fresh corn harvesting bench was built, and the optimal operating parameters were obtained from the test: the speed of ear picking claws was 2.11 m/s; the number of ear picking claws was four; the thickness of the flexible body was 4.52 mm; the stem feeding speed was 1.04 m/s; the corresponding grain breakage rate was 0.128%, which was far lower than the national standard (0.5%); and the ear impurity content was 0.3%, which was far lower than the national standard (2%). The results are consistent with the simulation results, proving that the model is reliable. This research achieved the harvest of fresh corn ears with a low grain damage rate, verified the possibility of reverse flexible ear picking, and provided a reference for the research and development of low-damage fresh corn harvesting machines.

Real-time knowledge of kernel breakage during corn harvesting plays a significant role in the adjustment of operational parameters of corn kernel harvesters. (1) Transfer learning by initializing the DenseNet121 network with pre-trained weights for training and validating a dataset of corn kernels was adopted. Additionally, the feature extraction capability of DenseNet121 was improved by incorporating the attention mechanism of a Convolutional Block Attention Module (CBAM) and a Feature Pyramid Network (FPN) structure. (2) The quality of intact and broken corn kernels and their pixels were found to be coupled, and a linear regression model was established using the least squares method. The results of the test showed that: (1) The MAP^b50 and MAP^m50 of the improved Mask Region-based Convolutional Neural Network (RCNN) model were 97.62% and 98.70%, in comparison to the original Mask Region-based Convolutional Neural Network (RCNN) model, which were improved by 0.34% and 0.37%, respectively; the backbone FLOPs and Params were 3.09 GMac and 9.31 M, and the feature extraction time was 206 ms; compared to the original backbone, these were reduced by 3.87 GMac and 17.32 M, respectively. The training of the obtained prediction weights for the detection of a picture of the corn kernel took 76 ms, so compared to the Mask RCNN model, it was reduced by 375 ms; based on the concept of transfer learning, the improved Mask RCNN model converged twice as quickly with the loss function using pre-training weights than the loss function without pre-training weights during training. (2) The coefficients of determination R² of the two models, when the regression models of the pixels and the quality of intact and broken corn kernels were analyzed, were 0.958 and 0.992, respectively. These findings indicate a strong correlation between the pixel characteristics and the quality of corn kernels. The improved Mask RCNN model was used to segment mask pixels to calculate the corn kernel breakage rate. The verified error between the machine vision and the real breakage rate ranged from −0.72% to 0.65%, and the detection time of the corn kernel breakage rate was only 76 ms, which could meet the requirements for real-time detection. According to the test results, the improved Mask RCNN method had the advantages of a fast detection speed and high accuracy, and can be used as a data basis for adjusting the operation parameters of corn kernel harvesters.