SHIP target image recognition based on FAST detector and faster-RCNN

2021 ◽  
Author(s):  
Leyuan Zhao ◽  
Bihui Liu ◽  
Chuanhui Liu
Keyword(s):  
Image Recognition ◽  
Target Image ◽  
Fast Detector

scholarly journals Image recognition in online monitoring of power equipment

2020 ◽  
Vol 17 (1) ◽  
pp. 172988141990083
Author(s):  
Guifeng Wu ◽  
Miao Yu ◽  
Wangwang Shi ◽  
Shengquan Li ◽  
Jiatong Bao
Keyword(s):  
Image Recognition ◽  
Template Matching ◽  
Online Monitoring ◽  
Source Image ◽  
Power Equipment ◽  
Target Image ◽  
Matching Algorithm ◽  
Matching Process ◽  
Abnormal State ◽  
Fast Recognition

The application of remote digital video surveillance and image recognition technology in online monitoring of power equipment is conducive to timely equipment maintenance and troubleshooting. In order to solve the problem of slow speed and large amount of computation of traditional template matching algorithm for power image recognition, a second template matching algorithm for fast recognition of target image is proposed in this article. Firstly, a quarter of the template data is taken and matched within a quarter of the source image, and a reasonable error threshold is given in the matching process. Then, the neighborhood of the minimum error point in rough matching is matched to get the final result. Finally, the algorithm is applied to identify the power equipment and detect the abnormal state of the power equipment. The experimental results show that the matching algorithm can not only accurately locate and identify power equipment and detect equipment faults, but also greatly improve the matching speed compared with other commonly used template matching algorithms.

An Image Recognition Method Based on Ant Colony Optimization Neural Network Using in Imaging Fuze

2011 ◽  
Vol 121-126 ◽  
pp. 1886-1890
Author(s):  
Ke Yong Wang ◽  
Shi Kai Xing
Keyword(s):  
Neural Network ◽  
Ant Colony Optimization ◽  
Image Recognition ◽  
Recognition Algorithm ◽  
Bp Algorithm ◽  
Ant Colony ◽  
Target Image ◽  
Recognition Method ◽  
Simulation Experiments ◽  
Training Time

Target image recognition is an important issue in the information processing of imaging fuse system. In the paper, the main frame is proposed which can solve the problem of target image recognition and many computer simulation experiments are carried out. A recognition algorithm based on ant colony optimization and neural network is proposed. It overcomes the shortcomings of traditional BP algorithm and converges fast. The results of experiments prove that the presented algorithm can shorten the training time effectively and increase the accuracy of recognition, so it is very useful in improving the effective destroying ability of the missile.

The Application of Image Stitching in the Robot Target Recognition

2011 ◽  
Vol 327 ◽  
pp. 149-152
Author(s):  
Lan Shen Guo ◽  
Nai Qiang Dong ◽  
Wei Tian ◽  
Cai Xiao Li ◽  
Fang Zhong Zhang
Keyword(s):  
Image Recognition ◽  
Target Recognition ◽  
Scientific Research ◽  
Identification Problem ◽  
Image Stitching ◽  
Target Image ◽  
The Core ◽  
Engineering Work ◽  
Traditional Production ◽  
Image Definition

Images are widely used in engineering work and scientific research, therefore, it is necessary to identify the image. The image recognition technology is one of the core technologies in traditional production and life, but the identify limitations can not meet the needs of many aspects of the identification problem. Use image stitching technology can increase the angle range of the target image and enhance the image definition, to achieve the identification of target image accurately.

An analysis of deep neural network models for image recognition applications

2021 ◽  
pp. 1-8
Author(s):  
Lin Wang ◽  
Xingfu Wang ◽  
Ammar Hawbani ◽  
Yan Xiong ◽  
Xu Zhang
Keyword(s):  
Neural Network ◽  
Image Recognition ◽  
Target Recognition ◽  
Network Models ◽  
Data Sets ◽  
Target Image ◽  
Neural Network Models ◽  
The Neural Network ◽  
Simulation Results ◽  
Classification Tool

The development of hardware technology and information technology has promoted the development of image recognition technology. Today, image recognition technology has been applied to many national defense technologies; especially target image recognition technology is widely used in the field of air threat prevention. However, nowadays, the air target recognition technology has the disadvantage of high misjudgment rate. The main reason is that the sky is too large and the distance gap makes it difficult to distinguish the target image from other noise images. This paper takes the neural network as the classification tool, through image preprocessing and contour extraction, establishes the recognition model of the target image. The simulation results of 10 data sets show that the method used in this paper is more than 85% accurate, but the error rate is only 0.7%. The simulation results show that the model designed in this paper can achieve air target recognition very well.

New Traffic Lights Identification Algorithms Based on Image Recognition

2011 ◽  
Vol 105-107 ◽  
pp. 1856-1859
Author(s):  
You Lin Shao ◽  
Dao Jiong Chen ◽  
Long Chen ◽  
Wei Yu Ni
Keyword(s):  
Image Recognition ◽  
Color Space ◽  
Target Area ◽  
Identification Algorithm ◽  
Target Image ◽  
Traffic Lights ◽  
Automatic Driving ◽  
Remote Control System ◽  
Hsi Space ◽  
Rgb Color Space

The traffic lights identification algorithms is an important part of the platform for automatic driving technology and it is also applied in the remote control system. As the absolute standard of behavior instruction, lights are the most firsthand object to judge. Image recognition technology has been applied in the Gray Spaces and HSI space, but Comparing with RGB color space, the latter is easier to understand and realize. This paper puts forward a kind of identification algorithm for single or multiple lights. According to the target image numerical characteristics in the RGB color space and judging from the target area needed and the related parameters extracted, The feasibility of this algorithm is proved in theory and application and the experimental results are satisfactory in the Matlab environment.

Sign in / Sign up

Export Citation Format

Share Document