Search

In recent years, the main grain-producing areas in the west of Jilin have gradually concentrated in the perennial irrigation areas and supplementary irrigation areas in the north, and the stress degree of grain irrigation water resources is gradually increasing. Therefore, this paper selects the arid and semiarid area in the west of Jilin Province as the research area and compares and analyzes the modeling process and simulation accuracy of the temporal and spatial distribution of food security production and total water resources. Based on the center of gravity model, this paper studies the temporal and spatial distribution of food security production and total water resources in Western Jilin. It can be seen that after 2018, rice and wheat show a fluctuating upward trend, and their values rise from 0.612 to 0.786 and 0.356 to 0.612, respectively; the rise of corn is small, showing an inverted "U" trend, which first increases from 0.693 in 2018 to 0.701 in 2019 and then decreases to 0.671 in 2021; By comparing the precipitation statistics in different years, the inverted "U" trend of corn irrigation water efficiency may be related to the sudden increase of precipitation. The center of gravity model is used to analyze the evolution trend of the center of gravity of grain production and water resources in Western Jilin from the national and regional levels, and the spatiotemporal coupling degree of the center of gravity of grain production and water resources is explored through the two-factor center of gravity coupling situation model. [ABSTRACT FROM AUTHOR]

Crop-related object recognition is of great importance in realizing intelligent agricultural machinery. Maize (Zea mays. L.) ear recognition could be a representative of crop-related object recognition, which is a critical technological premise for realizing automatic maize ear picking and maize yield prediction. In order to recognize maize ears in dough stage, this study combined deep learning and image processing, which have advantages of feature extraction and hardware flexibility, respectively. LabelImage was applied to mark and label maize plants, based on the deep learning framework TensorFlow, and this study developed multiscale hierarchical feature extraction together with quadruple-expanded convolutional kernels. To recognize the whole maize plant, 1250 images were acquired for training the recognition model, and its performance in a test set showed that the recognition accuracy was 99.47%. Subsequently, multifeatures of maize ear were determined, and the optimum binary threshold was obtained by fitting Gaussian distribution in the subblock image. Consequently, the maize ear was recognized by morphological process which was conducted by Python and OpenCV. Experiment was conducted in August 2018, and 10800 images were acquired for testing this algorithm. Experimental results showed that the average recognition accuracy was 97.02% and time consumption was 0.39 s for each image, which could meet a forward speed of 4.61 km/h for combine harvesters. [ABSTRACT FROM AUTHOR]