Large-range camellia oleifera forest and fruit intelligent detection and counting method based on UAV and deep learning

Abstract

The invention belongs to the technical field of economic forest intelligent monitoring and discloses a large-range camellia oleifera forest fruit intelligent detection and counting method based on UAVand deep learning. The camellia oleifera forest fruit intelligent detection and counting method comprises the steps that firstly, creating unmanned aerial vehicle inspection, wherein the inspected unmanned aerial vehicle is used for conducting vertical shooting on a camellia oleifera forest, acquiring camellia oleifera fruit pictures, wherein the obtained camellia oleifera fruit pictures serve asa data set, and conducting frame labeling, amplification and division on the data set; simulating the training data set by using a convolutional neural framework based on image segmentation, and constructing a deep learning network for intelligent detection and counting of the camellia oleifera fruits; and counting the number of masks of the camellia oleifera fruits based on the camellia oleiferafruit photo data by using a deep learning network for intelligent detection and counting of the camellia oleifera fruits to realize intelligent detection and counting of the camellia oleifera fruits.The method can improve the detection precision and speed of the large-range camellia oleifera fruits, and provides reference for the yield estimation of the large-range camellia oleifera forest.

Description

technical field [0001] The invention belongs to the technical field of economic forest intelligent monitoring, in particular to an intelligent detection and counting method, system and unmanned aerial vehicle of camellia oleifera forest and fruit, and specifically relates to a large-scale intelligent detection and counting method of camellia oleifera forest and fruit based on UAV and deep learning. Background technique [0002] At present, camellia oleifera is a woody oil tree species with high economic value and plays an important role in regional economy. With the development of the economy, the planting area of ​​camellia oleifera forest has expanded year by year, and the output of camellia oleifera forest and the cost of manual picking have doubled. However, due to the lack of sufficient attention, Camellia oleifera fruit has long relied on traditional manual detection and counting methods, and there are few reports on large-scale intelligent detection and counting of Ca...

AI Technical Summary

Problems solved by technology

[0004] The existing detection and counting methods of Camellia oleifera forest fruit are mainly on-site manual counting, and the way of counting while marking is adopted to avoid repetition and omission of manual counting. Although this method has high accuracy of counting results, it is time-consuming, labor-intensive and inefficient. ; The second is to use picking robots to count at close range. Although this method is low in cost, it has poor flexibility, slow detection speed, and is not suitable for large-scale rapid detection. move

[0005] Through the above analysis, the problems and defects in the prior art are: (1) the existing camellia oleifera fruit counting method has poor flexibility, slow detection speed, and is not suitable for large-scale rapid detection

[0006] (2) The detection cost is high, and there is nothing that can be done for the detection of Camellia oleifera forest in inaccessible hills and mountains

[0007] (3) In order to obtain the sample data of Camellia oleifera at different stages, multiple tests are required, and the feasibility is low

[0008] The difficulty of solving the above problems and defects is: the high-definition photography and mobility of UAVs make it possible to intelligently detect a wide range of Camellia oleifera fruit, but the flying height, speed and light conditions of UAVs directly affect the clarity of photos of Camellia oleifera fruit and spatial resolution

Images