Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device and storage medium for identifying foreign objects in vehicle bottom pictures based on sliding window

A technology of sliding window and recognition method, which is applied in the field of foreign object recognition, can solve the problems of small proportion of vehicle bottom images, low accuracy of foreign object recognition, and large calculation overhead, so as to achieve the effect of improving efficiency and accuracy

Active Publication Date: 2021-08-13
南京索安电子有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This leads to a large computational overhead and a long time-consuming process of image recognition. It often takes tens of seconds to get the recognition result after directly inputting high-resolution images into the target recognition network; Base image scale is small
This makes the usual object recognition methods less accurate in identifying foreign objects

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and storage medium for identifying foreign objects in vehicle bottom pictures based on sliding window
  • Method, device and storage medium for identifying foreign objects in vehicle bottom pictures based on sliding window
  • Method, device and storage medium for identifying foreign objects in vehicle bottom pictures based on sliding window

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 As shown, the car bottom picture foreign object recognition method of the present invention, the car bottom includes but not limited to the truck bottom, the train bottom and other vehicle bottoms, and the recognition method includes the following steps:

[0036] Step 1, training the foreign object recognition network model M to obtain the parameters of the foreign object recognition network.

[0037] Step 2, the prediction of the under-vehicle image, and the result of foreign object recognition in the under-vehicle image.

[0038] Step 1 includes: the construction and division of the data set, the preprocessing of the vehicle bottom image, the forward propagation of the foreign object recognition network, and the parameter update of the foreign object recognition network.

[0039] Step 1-1, collect the under-vehicle image data containing foreign objects, including the under-vehicle image and the corresponding foreign object label bounding box and cate...

Embodiment 2

[0076] The present invention also provides a sliding window-based foreign matter recognition device for vehicle bottom pictures, including a processor and a memory; programs or instructions are stored in the memory, and the programs or instructions are loaded and executed by the processor to realize the vehicle according to Embodiment 1. Method for identifying foreign matter in the bottom image.

Embodiment 3

[0078] The present invention also provides a computer-readable storage medium. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium may also be a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium, and when the instructions are run on the computer, the computer is made to execute the method for identifying foreign objects in the vehicle bottom image in Embodiment 1.

[0079] Those skilled in the art can clearly understand that the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of software products, and the computer software products Stored in a storage medium, including several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of...

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

No PUM Login to View More

Abstract

The invention discloses a sliding window-based method, device and storage medium for identifying foreign objects in vehicle bottom pictures. The method for identifying foreign objects in vehicle bottom pictures includes the following steps: Step 1, training a foreign object recognition network model M to obtain parameters of the foreign object recognition network; 2. Use the sliding window to divide the car bottom image into multiple window images, load the image data of each window in multiple processes, preprocess the window images and input them into the foreign object recognition network M to obtain the foreign object recognition results. The present invention processes the undercarriage images after sliding window segmentation through multi-processes, and combines the method based on the anchor frame which is more stable for medium target recognition and the method based on feature points which is more flexible for small target recognition, effectively improving the high resolution. The efficiency and accuracy of foreign object recognition under the vehicle.

Description

technical field [0001] The invention relates to an efficient small target foreign matter recognition method based on a sliding window high-resolution vehicle bottom picture, and belongs to the technical field of foreign matter recognition. Background technique [0002] In order to prevent criminals from hiding guns, explosives, drugs and other dangerous items in the vehicle chassis, the foreign object recognition of the vehicle chassis is an important part of the safety inspection. The existing methods for identifying foreign objects on the bottom of the vehicle include taking high-definition pictures of the bottom of the vehicle and manually checking the pictures, but this method has defects such as low efficiency and a decrease in the accuracy of judgment after the security personnel monitor the pictures for a long time. A more efficient way of security inspection is to analyze the pictures of the bottom of the car through the deep learning-based target recognition technol...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/44G06F18/241G06F18/253
Inventor 赵荣成晓龙赵智玉徐梅娟
Owner 南京索安电子有限公司