Port grab bucket detection method based on improved YOLOv3-tiny algorithm

Abstract

The invention provides a port grab bucket detection method based on an improved YOLOv3-tiny algorithm, and the method comprises the steps: an image extraction device being just opposite to a grab bucket, and setting the image extraction device to be in a working mode of following the grab bucket; collecting image data of a port grab bucket, and obtaining a network training sample and a test sample; jointly determining unique position information of the grab bucket by large arm rotation angle information of a horizontal plane and a vertical plane measured by a distance measuring sensor and an angle sensor and three-dimensional information of the grab bucket; training the network model by using an improved YOLOv3-tiny algorithm to obtain a grab bucket detection model; and testing the pictures of the test set and the port operation video by using the trained grab bucket detection model weight, and obtaining a test result. In the grab bucket operation process, the operation speed is increased, the cycle period is shortened, real-time detection of the position of the grab bucket is automatically achieved, labor capital is saved while the operation efficiency is improved, and great valueand significance are achieved in the port operation aspect.

Description

technical field [0001] The invention relates to a port grab detection method, in particular to a port grab detection method based on the improved YOLOv3-tiny algorithm. Background technique [0002] In recent years, with the vigorous development of the port industry, the port throughput has continued to increase. In 2018, China's ports completed a cargo throughput of 14.351 billion tons, which is enough to show that the port terminals have a large demand for loading and unloading dry bulk cargo. With the development of science and technology, how to automate port bulk cargo handling equipment will be the future development trend. [0003] Most of the methods currently used are controlled by humans, that is, the driver sits in the cab of the door operator and observes with the naked eye whether the grab has reached the appropriate position to grab or release the dry bulk cargo, and it is up to the human to judge when to release or Raise the wire rope on the grab bucket. The...

AI Technical Summary

Problems solved by technology

Then there will be the following problems: First, because the human eye is far away from the goods, it is easy to over-release the grab when releasing the grab, a few seconds are wasted in one operation cycle, and a lot of time is wasted in adding up multiple cycle operations, resulting in a large amount of waste. Useless work

Second, the long-term work of the driver will cause human eye fatigue, which will lead to misjudgment and over-discharge problems. This is not good for the development of the company, because it will increase the input cost of the company in addition to time-consuming and labor-intensive.

But it has the following two problems: first, the location is fixed, there is no flexibility, and the fixed area is limited. If it is too large, the opening and closing of the bucket needs to be controlled manually, which does not save human capital.

Second: During the movement of the grab bucket, the speed is extremely slow, otherwise the fixed-point opening and closing of the bucket cannot be realized, which leads to not only no savings in time cost, but an increase in

Images