Method and device for detecting position of container
A container and normalization technology, applied in the detection field, can solve the problems of long time, large amount of model parameters, and inability to obtain location information in real time, so as to achieve the effect of saving hardware costs and precise loading and unloading operations
Pending Publication Date: 2020-09-25
北京主线科技有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the large number of model parameters in the deep learning model, it takes a lot of time to determine the location information of the container through the deep learning model, which makes it impossible for unmanned vehicles to obtain the location information of the container in real time
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
[0028] In the port, no matter in the quayside bridge scenario, the unmanned vehicle and the spreader cooperate to complete the container loading and unloading task, or in the field bridge scenario, the unmanned vehicle and the spreader cooperate to complete the container access task, unmanned Driving a vehicle needs to obtain the status information of the spreader and the container, and then control the movement of the vehicle itself according t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the invention provides a method and device for detecting the position of a container. The method comprises the steps of acquiring an image containing the container; cutting the deeplearning model based on importance parameters in a normalization layer of the deep learning model, wherein the importance parameters are obtained by performing sparse training on channel feature parameters in the normalization layer of the deep learning model; re-training the cut deep learning model; and inputting the image into a retrained deep learning model to obtain the position of the container in the image. Thus, the deep learning model can be lightened, and the position of the container in the image can be detected more quickly. Moreover, since the deep learning model becomes lighter after being cut, excessive storage space does not need to be occupied, and the method can be well applied to an embedded graphic processor.
Description
technical field [0001] The invention relates to the technical field of detection, in particular to a method and device for detecting the position of a container. Background technique [0002] During the loading and unloading process of port containers, unmanned vehicles need to control their own actions to load and unload containers according to the status information of spreaders and containers. Specifically, the unmanned vehicle obtains the image of the sky above it through the image sensor, and then uses the deep learning model to determine whether the spreader has captured the container and the location information of the container, so as to determine the progress of the container loading and unloading operation, and then make the unmanned The vehicle can perform actions such as deceleration, alignment, and start-up. [0003] However, in the process of loading and unloading containers, unmanned vehicles need to obtain the location information of the containers in real t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/73G06K9/32G06K9/34G06K9/62G06N3/04
CPCG06T7/73G06V10/25G06V10/267G06N3/045G06F18/214
Inventor 陈建松王晓东张天雷鞠豪明
Owner 北京主线科技有限公司