The Research of the ATR System Based on Infrared Images and L-M BP Neural Network

Mu, Chengpo; Wang, Jiyuan; Yuan, Zhijie; Zhang, Xianlei; Han, Chao

doi:10.1109/icig.2013.162

Cited by 5 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can approach the boundary infinitely in the form of multiple harmonics and has the advantages of scale transformation, rotation transformation, and invariance of starting point transformation [21][22][23]. is paper first uses the method in [32][33][34][35] to obtain the outline point set of the target. For a closed boundary C, it can be expressed as a vector form v(t) � [x(t) y(t)] T , where t ∈ [0, 2π).…”

Section: Outline Descriptorsmentioning

confidence: 99%

Selection of Outline Descriptors Based on LightGBM with Application to Infrared Image Target Recognition

Yao

2021

Scientific Programming

View full text Add to dashboard Cite

Infrared sensing technology can be well used for night observation, which is becoming an important measure for battlefield reconnaissance. It is a powerful way to implement precision strikes and situational awareness by improving the ability of target recognition based on infrared images. For the problem of infrared image recognition, the Light Gradient Boosting Machine (LightGBM) is employed to select the outline descriptors extracted based on the elliptic Fourier series (EFS), which is combined with sparse representation-based classification (SRC) to achieve target recognition. First, based on the target outlines in the infrared image, the multi-order outline descriptors are extracted to characterize the essential characteristics of the target to be recognized. Then, the LightGBM feature selection algorithm is used to screen the multi-order outline descriptors to reduce redundancy and improve the pertinence of features. Finally, the selected outline descriptors are classified based on SRC. The method effectively improves the effectiveness of the final features through the feature selection of LightGBM and reduces the computational complexity of classification at the same time, which is beneficial to improve the overall recognition performance. The mid-wave infrared (MWIR) dataset of various targets is employed to carry out verification experiments for the proposed method under three different conditions of original samples, noisy samples, and partially occluded samples. By comparing the proposed method with several types of existing infrared target recognition methods, the results show that the proposed method can achieve better performance.

show abstract

Section: Outline Descriptorsmentioning

confidence: 99%

Selection of Outline Descriptors Based on LightGBM with Application to Infrared Image Target Recognition

Yao

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…The activation function of each node is shown by (17); its weight update method is shown by (18); and its estimation method of hidden layer number is shown by (19). When training the BPNN, the Levenberg–Marquardt method [29] is employed. The network error and the maximum iteration number are used to terminate the network computation

f false(x false) = \frac{1}{1 + {normale}^{- x}}

w_{q r} false(n + 1 false) = w_{q r} false(n false) + φ \sum_{p = 1}^{P} δ_{q}^{p} σ_{r}^{p} + κ normalΔ w_{q r} false(n false)

r = \sqrt{u + q} + D

where f ( x ) is the Sigmoid function; w qr ( n ) is the connection weight in the n th computation; q ( q = 1, 2,…, Q ) is the node number of the output layer; r ( r = 1, 2,…, R ) is the node number of the hidden layer; u ( u = 1, 2,…, U ) is the node number of the input layer; p ( p = 1, 2,…, P ) is the symbol of the training data;

δ_{q}^{p}

is the propagation error;

δ_{r}^{p}

is the output of each layer; κ is the momentum coefficient; ϕ is the learning rate; Δ w qr ( n ) = w qr ( n )− w qr ( n −1); D ∈Z + and D ∈[1, 10].…”

Section: Adaptive Processing Of Iq_learning Computationmentioning

confidence: 99%

Image enhancement for outdoor long‐range surveillance using IQ‐learning multiscale Retinex

Liu

2017

IET Image Processing

View full text Add to dashboard Cite

“…However, the design process has some uncertainties, so the discrimination is often limited. In terms of the classifiers, the infrared image recognition, like other pattern recognition problems, mainly employs classical and robust classifiers [10][11][12], such as support vector machines (SVMs), neural networks, and sparse representation-based classification (SRC). With the development of deep learning theory [13][14][15][16], different types of deep learning models have also been applied in the field of infrared image target recognition, and their effectiveness has also been verified [17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

A Target Recognition Method Based on Multiview Infrared Images

Zhang

Rao

2022

Scientific Programming

View full text Add to dashboard Cite

Infrared image target recognition provides an important means of night traffic management and battlefield environment monitoring. With the improvement of the performance of infrared sensors and the popularization of applications, it becomes possible to obtain multiview infrared images of the same target in the same scene. A target recognition method combining multiview infrared images is proposed. At first, the internal correlation analysis of multiview infrared images is performed based on the nonlinear correlation information entropy (NCIE). The view subset from all the multiview images with the largest NCIE is selected as candidate samples for the subsequent target recognition. The joint sparse representation (JSR) is used to classify all infrared images in the candidate view subset. JSR can effectively investigate the internal correlation of multiple related sparse representation problems and improve the reconstruction accuracy and classification capabilities. In the experiments, the tests are performed on the collected infrared images of multiple types of traffic vehicles, under the conditions of original, noisy, and occluded samples. The effectiveness and robustness of the proposed method can be verified by comparative analysis.

show abstract

The Research of the ATR System Based on Infrared Images and L-M BP Neural Network

Cited by 5 publications

References 2 publications

Selection of Outline Descriptors Based on LightGBM with Application to Infrared Image Target Recognition

Selection of Outline Descriptors Based on LightGBM with Application to Infrared Image Target Recognition

Image enhancement for outdoor long‐range surveillance using IQ‐learning multiscale Retinex

A Target Recognition Method Based on Multiview Infrared Images

Contact Info

Product

Resources

About