A method for illegal detection of overloaded luggage trailers in airports
A trailer and luggage technology, applied in the field of computer vision, can solve the problems of fast trailer travel, reduced airport work efficiency, and high labor costs, and achieve the effects of reducing calculations, improving accuracy, and saving labor costs
Active Publication Date: 2022-04-12
杭州视在科技有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The violation detection of airport luggage trailers has always been based on manual inspection methods. With the increase of airport flights, the workload of manual inspection of trailer overloads is increasing and will waste a lot of time, resulting in a significant drop in airport work efficiency. Therefore, a method based on computer vision is adopted. The need for automatic detection of trailer overload is becoming more and more urgent
[0003] The traditional method of detecting trailer overload has the following disadvantages: low efficiency; missed detection; high labor cost
There are many difficulties in detecting the overload of the trailer compartment based on computer vision. Among them, there are several main technical difficulties: the state detection of the trailer is inaccurate; the misjudgment caused by multiple vehicles appearing at the same time; the trailer travels faster and the algorithm runs slower Can not meet the actual requirements of the algorithm
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
[0030] The following clearly and completely describes the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0031] see figure 1 , the present invention provides a method for detecting overload violations of airport luggage trailers, characterized in that it includes the following steps,
[0032] S1, using the target detection network YOLOV3 to perform target detection on the image to obtain the position and type of the target, including the front and the compartment. The training process of the target detection network YOLOV3 is as follows: collect the monitoring pictures of the airport apron, mark the front and compartment, input the ma...
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 invention discloses a method for detecting overload violations of airport luggage trailers and relates to the technical field of computer vision. The method includes the following steps: performing target detection on the image to obtain the position and type of the target, the type including the front and the compartment; judging the movement state of the front according to the number of the front; matching the compartments belonging to the same trailer; using a straight line fitting method to match the matched Cars are screened; the number of cars in each trailer is counted; if the number of cars in the trailer exceeds the number of cars stipulated by the trailer, it will be judged as an overload violation. The invention greatly improves the detection efficiency and saves labor cost.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for detecting overload violations of airport luggage trailers. Background technique [0002] With the increasing business of the airport, higher requirements are put forward for the working efficiency of the airport apron. Among them, baggage checking is a more important part of the maintenance. Baggage drop-off at the airport is to transport the luggage to the corresponding aircraft seat on the airport apron through a luggage trailer, and then load it on the aircraft. The safe transportation of luggage trailers is an important part of station apron safety work. This patent has developed an algorithm for real-time detection of trailer overloading based on deep learning, which can replace the traditional manual detection method and improve the work efficiency of the airport apron. The violation detection of airport luggage trailers has always been based on manua...
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 Patents(China)
IPC IPC(8): G06V20/52G06V10/762G06V10/774G06K9/62
CPCG06V20/52G06V2201/08G06F18/23213G06F18/214
Inventor 王书平吴晓晖
Owner 杭州视在科技有限公司