Search Results (6)

Corn is one of the global staple grains and the largest grain crop in China. During harvesting, grain separation, and corn production, corn is susceptible to mechanical damage including surface cracks, internal cracks, and breakage. However, the internal cracks are difficult to observe. In this study, hyperspectral imaging was used to detect mechanical damage in corn seeds. The corn seeds were divided into four categories that included intact, broken, internally cracked, and surface-crackedtv. This study compared three feature extraction methods, including principal component analysis (PCA), kernel PCA (KPCA), and factor analysis (FA), as well as a joint feature extraction method consisting of a combination of these methods. The dimensionality reduction results of the three methods (FA + KPCA, KPCA + FA, and PCA + FA) were combined to form a new combined dataset and improve the classification. We then compared the effects of six classification models (ResNet, ShuffleNet-V2, MobileNet-V3, ResNeSt, EfficientNet-V2, and MobileNet-V4) and proposed a ResNeSt_E network based on the ResNeSt and efficient multi-scale attention modules. The accuracy of ResNeSt_E reached 99.0%, and this was 0.4% higher than that of EfficientNet-V2 and 0.7% higher than that of ResNeSt. Additionally, the number of parameters and memory requirements were reduced and the frames per second were improved. We compared two dimensionality reduction methods: KPCA + FA and PCA + FA. The classification accuracies of the two methods were the same; however, PCA + FA was much more efficient than KPCA + FA and was more suitable for practical detection. The ResNeSt_E network could detect both internal and surface cracks in corn seeds, making it suitable for mobile terminal applications. The results demonstrated that detecting mechanical damage in corn seeds using hyperspectral images was possible. This study provides a reference for mechanical damage detection methods for corn. Full article

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. Full article

Accurately and effectively measuring the breaking quality of harvested corn kernels is a critical step in the intelligent development of corn harvesters. The detection of broken corn kernels is complicated during the harvesting process due to turbulent corn kernel movement, uneven lighting, and interference from numerous external factors. This paper develops a deep learning-based detection method in real time for broken corn kernels in response to these issues. The system uses an image acquisition device to continuously acquire high-quality corn kernel image data and cooperates with a deep learning model to realize the rapid and accurate recognition of broken corn kernels. First, we defined the range of broken corn kernels based on image characteristics captured by the acquisition device and prepared the corn kernel datasets. The corn kernels in the acquired image were densely distributed, and the highly similar features of broken and whole corn kernels brough challenges to the system for visual recognition. To address this problem, we propose an improved model called BCK-YOLOv7, which is based on YOLOv7. We fine-tuned the model’s positive sample matching strategy and added a transformer encoder block module and coordinate attention mechanism, among other strategies. Ablation experiments demonstrate that our approach improves the BCK-YOLOv7 model’s ability to learn effectively broken corn kernel features, even when high-density features are similar. The improved model achieved a precision rate of 96.9%, a recall rate of 97.5%, and a mAP of 99.1%, representing respective improvements of 3.7%, 4.3%, and 2.8% over the original YOLOv7 model. To optimize and deploy the BCK-YOLOv7 model to the edge device (NVIDIA Jetson Nano), TensorRT was utilized, resulting in an impressive inference speed of 33 FPS. Finally, the simulation system experiment for corn kernel broken rate detection was performed. The results demonstrate that the system’s mean absolute deviation is merely 0.35 percent compared to that of manual statistical results. The main contribution of this work is the fact that this is the first time that a set of deep learning model improvement strategies and methods are proposed to deal with the problem of rapid and accurate corn kernel detection under the conditions of high density and similar features. Full article

At present, Chinese corn grain harvesters lack cleaning loss monitoring. Cleaning parameters cannot be automatically adjusted, and the loss rate is high. In view of the above problems, a cleaning loss monitoring sensor is designed, composed of a metal impact plate, piezoelectric ceramic and signal processing circuit. The factors affecting the characteristics of vibration signals are analyzed from the material, size and other aspects. The sensitive plate is composed of a 304 stainless steel impact plate and piezoelectric ceramic. The sensitive plate can convert the vibration signal of the impact plate into a voltage signal, and the output voltage range can reach ±3 V or more. The signal generated by the collision of corn kernel and damaged corn cob with the sensitive plate was analyzed.It was found that the frequency domain range of corn grains was wider, with signals above 6 kHz, but broken corncobs did not have such signals. Based on the frequency distribution, a signal processing circuit is designed, which consists of high-pass filter circuit, an envelope detection circuit, and a voltage comparison circuit. The circuit can convert analog signals into pulse signals, which facilitates the counting process by the microprocessor. In order to obtain the monitoring accuracy and installation parameters of the integrated corn cleaning loss monitoring sensor, a Central Composite Design was carried out with the installation height and angle of the sensitive plate as the test factors and monitoring accuracy as the test index. Based on the test results and field test conditions, a regression model was established to determine the optimal installation parameters: the installation angle of the sensitive plate is 30°, and the installation height is 30 cm. At this stage, the accuracy of the sensor monitoring corn grains was 92.82%, and the accuracy of monitoring the mixture of corn grains and broken corncobs was 90.07%. The verification test shows that the monitoring accuracy can reach more than 94% after the sensor is debugged. This research can provide a reference for the design of corn cleaning loss monitoring devices. Full article

In order to improve the accuracy and efficiency of the methods that are used for the detection of impurities in and the breakage rate of harvested corn grains, we propose a classification and identification method using a feature threshold and a backpropagation (BP) neural network that is based on a genetic algorithm. We also constructed a continuous single-layer discrete tile detection system for application to harvested corn grains containing impurities and broken kernels. We conducted an evaluation of the proposed approach with a three-factor and three-level orthogonal experimental design. By setting the working parameters, we realized the continuous single-layer discrete tiling of the grains and 50 grain materials were collected on average in a single picture. In the static test, the error between the system monitoring value and the manual detection value was small, the maximum absolute errors of the breakage and impurity rates were 2.16% and 1.03%, and the average time that was required for each image recognition was 1.71 s. In the experimental environment, the maximum absolute error values of the breakage and impurity rates were 3.48% and 1.78%. The system’s identification accuracy and processing time meet the requirements of the online detection of corn characteristics in grain harvesting. Full article

At present, the wide application of the CNN (convolutional neural network) algorithm has greatly improved the intelligence level of agricultural machinery. Accurate and real-time detection for outdoor conditions is necessary for realizing intelligence and automation of corn harvesting. In view of the problems with existing detection methods for judging the integrity of corn kernels, such as low accuracy, poor reliability, and difficulty in adapting to the complicated and changeable harvesting environment, this paper investigates a broken corn kernel detection device for combine harvesters by using the yolov4-tiny model. Hardware construction is first designed to acquire continuous images and processing of corn kernels without overlap. Based on the images collected, the yolov4-tiny model is then utilized for training recognition of the intact and broken corn kernels samples. Next, a broken corn kernel detection algorithm is developed. Finally, the experiments are carried out to verify the effectiveness of the broken corn kernel detection device. The laboratory results show that the accuracy of the yolov4-tiny model is 93.5% for intact kernels and 93.0% for broken kernels, and the value of precision, recall, and F1 score are 92.8%, 93.5%, and 93.11%, respectively. The field experiment results show that the broken kernel rate obtained by the designed detection device are in good agreement with that obtained by the manually calculated statistic, with differentials at only 0.8%. This study provides a technical reference of a real-time method for detecting a broken corn kernel rate. Full article