Title:
CONVOLUTIONAL NEURAL NETWORK-BASED IMPAIRMENT DETECTION METHOD
Document Type and Number:
WIPO Patent Application WO/2022/047736
Kind Code:
A1
Abstract:
A convolutional neural network-based impairment detection method. An input image can be received, and convolutional multi-feature mappings of different scales are generated; the generated convolutional feature mappings are processed by means of a dual/multi-region proposal network, a dual/multi-impairment proposal is generated for each candidate impairment in the image, and a dual/multi-region proposal bounding box is created; the dual/multi-region proposal bounding box is projected back to the feature mappings of respective convolutional layers to obtain a group of dual/multi-regions of interest; the dual/multi-regions of interest are compared, and a confidence score is created to indicate the likelihood that a desired impairment is detected in the bounding box, so that the desired impairment can be detected only by one step. The beneficial effects of the present application are: less time is spent, the precision and the recall rate are high, the size of a data set is increased, and the convolutional layer can increase the speed of a model and improve the precision to an average precision mean of up to 98% to 99%.
Inventors:
ALTABEY WAEL ABDELMONEM ABDELMONEM (CN)
NOORI MOHAMMAD N (CN)
HONG WILSON (CN)
NOORI MOHAMMAD N (CN)
HONG WILSON (CN)
Application Number:
PCT/CN2020/113533
Publication Date:
March 10, 2022
Filing Date:
September 04, 2020
Export Citation:
Assignee:
JIANGSU ADVANCED TRANSP RESEARCH INSTITUTE CO LTD (CN)
NANJING ZHIXING INFORMATION TECH CO LTD (CN)
NANJING ZHIXING INFORMATION TECH CO LTD (CN)
International Classes:
G06K9/00
Foreign References:
| CN107194323A | 2017-09-22 | |||
| CN106599939A | 2017-04-26 | |||
| CN110287768A | 2019-09-27 | |||
| US10373262B1 | 2019-08-06 |
Attorney, Agent or Firm:
SUNRAY INTELLECTUAL PROPERTY ATTORNEYS (CN)
Download PDF: