Dense stacking target detection method based on automatic labeling and transfer learning

Abstract

The invention discloses a dense stacking target detection method based on automatic labeling and transfer learning. The dense stacking target detection method comprises the following steps: establishing a labeled training image set by high-resolution image segmentation; inputting the labeled training image set into a pre-trained target detection model YOLOv3, optimizing a priori frame size and a loss function of the YOLOv3 model, and performing fine adjustment on the model by using the training image set; and finally, inputting a to-be-detected image into the fine-tuned YOLOv3 model, outputting the classification of the target sub-regions and the positions of the sub-regions, splicing output result images to recover the output result images into an original image, and counting a total counting result. The dense stacking target detection method provided by the invention has strong anti-interference performance and robustness, and has low requirements on an image photographer and a photographing illumination condition; through an unsupervised learning method, quasi-automatic annotation of the image is realized, and the workload of manual annotation is greatly reduced, and the model training efficiency is improved; and the dense stacking target detection method can be used for image recognition of a large number of densely stacked targets which are mutually shielded, and is suitable for automatic counting scenes of various densely stacked targets.

Description

technical field [0001] The invention belongs to the technical field of machine vision and relates to a target detection method, in particular to a dense stacking target detection method based on automatic labeling and transfer learning. Background technique [0002] The practice of the construction industry involves counting the stacking of standardized objects such as steel and wood. The size of the target objects for stacking usually ranges from hundreds to thousands, and the entire manual counting process is time-consuming, inefficient, and error-prone. Although the number of target objects in the stacking of construction materials is huge, due to the high degree of normalization, the differences in shape and size between individuals are small, which is conducive to the study of target detection technology in the field of machine vision, and the detection of individual objects in dense stacking. Automatically detect and count. The research results can reduce the labor i...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the existing dense stacking target detection method has high r

Images