Method and system for identifying different vehicle models in complex environment
A vehicle type identification and complex environment technology, applied in the field of vehicle type identification, can solve problems such as vehicle type identification and inability to apply to disaster relief sites, and achieve the effect of improving recognition accuracy
Active Publication Date: 2019-11-15
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing identification methods, such as face recognition, cannot be applied to vehicle identification at disaster relief sites due to the complexity of the environment. It can be seen that how to realize the identification of different vehicle types in complex environments has become a technical problem that needs to be solved urgently
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
[0048] The purpose of the present invention is to provide a method and system for identifying different vehicle models in a complex environment, so as to realize the identification of different vehicle models in a complex environment.
[0049] In order to make the above objects, features and advantages of the present invention more comprehensible, the invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0050] Convolutional neural network (CNN) is a kind of artificial neural network. Its artificial neurons can respond to surrounding units in a part of the coverage area, and it performs well in a large number of image processing. The convolutional neural network automatically learns the features of images at various scales through convolution and pooling layers. Through a series of methods, the image recognition problem with a huge amount of data is continuously reduced in dimension, so that it can be train...
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 provides a method and a system for identifying different vehicle models in a complex environment. The method for identifying different vehicle models in a complex environment Includes: utilizing a WGAN network model to generate a first generation training sample set under each environment, generating a second generation training sample set compounded by different environments by using a CycleGAN network model. The number of training samples is increased; so that the data volume required by convolutional neural network training is achieved, meanwhile, various environment-compounded training samples in various complex environments can be generated, the convolutional neural network is trained by adopting the training samples, different vehicle types in the complex environments can be recognized, and the recognition accuracy of the different vehicle types in the complex environments is improved.
Description
technical field [0001] The invention relates to the field of vehicle identification, in particular to a method and system for identifying different vehicle types in a complex environment. Background technique [0002] When natural disasters and man-made disasters come, the state will carry out disaster relief work such as organizing manpower and material resources to rescue, transfer or evacuate trapped people, rescue and transport important materials, protect the safety of important targets, and carry out post-disaster reconstruction work. According to different rescue contents, personnel dispatching is carried out. When the vehicles carrying rescue materials or rescue personnel arrive at the disaster relief scene, they are quickly identified and the rescue is carried out according to the identified vehicle type. For the rescue scene where time is life has important meaning. However, the existing identification methods, such as face recognition, cannot be applied to vehicl...
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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/10G06V2201/08G06N3/045G06F18/24133G06F18/214
Inventor 雷添杰黄锦涛吕娟贾金生郑璀莹王嘉宝张亚珍李曙光李世灿宋宏权张炬慎利宫阿都岳建伟汪洋李爱丽杨会臣宋文龙万金红刘中伟周磊陈强娄和震程子懿路京选李杨程慧李翔宇陈文晋李明宇赵林洪史婉丽徐瑞瑞张鹏鹏
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES