In the foxtail millet field, due to the dense distribution of the foxtail millet ears, morphological differences among foxtail millet ears, severe shading of stems and leaves, and complex background, it is difficult to identify the foxtail millet ears. To solve these practical problems, this study proposes a lightweight foxtail millet ear detection method based on improved YOLOv5. The improved model proposes to use the GhostNet module to optimize the model structure of the original YOLOv5, which can reduce the model parameters and the amount of calculation. This study adopts an approach that incorporates the Coordinate Attention (CA) mechanism into the model structure and adjusts the loss function to the Efficient Intersection over Union (EIOU) loss function. Experimental results show that these methods can effectively improve the detection effect of occlusion and small-sized foxtail millet ears. The recall, precision, F₁ score, and mean Average Precision (mAP) of the improved model were 97.70%, 93.80%, 95.81%, and 96.60%, respectively, the average detection time per image was 0.0181 s, and the model size was 8.12 MB. Comparing the improved model in this study with three lightweight object detection algorithms: YOLOv3_tiny, YOLOv5-Mobilenetv3small, and YOLOv5-Shufflenetv2, the improved model in this study shows better detection performance. It provides technical support to achieve rapid and accurate identification of multiple foxtail millet ear targets in complex environments in the field, which is important for improving foxtail millet ear yield and thus achieving intelligent detection of foxtail millet.

Sanbai Melon, a nationally recognized geographical indication product and a specialty agricultural product of Shanxi Province, is named for its distinctive white skin, white flesh, and white seeds. Primarily cultivated in Wanrong County, Yuncheng City, Shanxi Province, it is not only rich in various vitamins and amino acids but also boasts significant medicinal properties. Known for its ability to clear heat, detoxify the body, purify the lungs, moisten the intestines, reduce internal heat, and protect the liver, Sanbai Melon is highly valued for both its nutritional and health benefits. However, Sanbai melon is only available on the market from July to December each year. Due to this extended seasonal gap, fresh supply falls short of meeting daily consumer demand. To address this issue, processing Sanbai melon into freeze-dried powder has become essential. This study investigated the optimal freeze-drying parameters for Sanbai melon by examining the correlation between its dielectric properties and moisture content. Using a combination of single-factor tests and response surface methodology, a three-factor, three-level experimental design was implemented. Based on preliminary experiments, the vacuum levels were set at 35~40 Pa, 40~45 Pa, and 45~50 Pa; the heating plate temperatures were set at 60°C, 70°C, and 80°C; and the material thicknesses were set at 3 mm, 6 mm, and 9 mm. With drying time as the target variable, and moisture content, dielectric constant, and dielectric loss factor as response variables, response surface analysis determined the optimal freeze-drying conditions as follows: vacuum degree of 40~45 Pa, heating plate temperature of 73 °C, material thickness of 7 mm, and a total freeze-drying time of 6 hours. Under these conditions, the resulting Sanbai melon powder exhibited a moisture content of 2.9%, a dielectric constant of 2.195, and a dielectric loss factor of 1.525.