Adaptive target detection in forward-looking infrared imagery using the eigenspace separation transform and principal component analysis

Young, S. Susan; Kwon, Heesung; Der, Sandor Z.; Nasrabadi, Nasser M.

doi:10.1117/1.1768534

Cited by 19 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[8] A similar ANN technique for person identification was presented by Zhang et al, 2004 [9]. The application of the ANN technique for image detection has also been addressed by Young et al, 2004, where they considered the target detection problem by mapping these image gradient vectors using linear transformations [10]. Therefore, it is worth exploring the ANN technique to check the parameter clustering image of pump systems for the purpose of diagnosis.…”

Section: Introductionmentioning

confidence: 98%

Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Tsai

Wang

2009

J Mech Sci Technol

View full text Add to dashboard Cite

Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input-output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions were artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended.

show abstract

Section: Introductionmentioning

confidence: 98%

Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Tsai

Wang

2009

J Mech Sci Technol

View full text Add to dashboard Cite

show abstract

“…ARL researchers led by Chan later published a multi-stage IR target detector [2], which added an Eigenspace Multi-Layer Perceptron (EIGMLP) to separate clutter from real targets, and finally the "Evidence Integrator" which combined the output of EIGMLP with intermediate feature values from the initial detector. Young, et al, [3] proposed the use of Eigenspace Separation Transforms (EST) and Principal Components Analysis (PCA) applied to gradient vectors to detect differences in the structural information between low-contrast, short-to-medium range targets and nontargets. Mehmood and Nasrabadi [4] proposed the "wavelet-RX" algorithm, which uses two-dimensional wavelet transforms to decompose the image into a number of sub-bands, followed by the multi-variate RX Constant False Alarm Rate (CFAR) algorithm, adopted from hyperspectral image processing.…”

Section: Introductionmentioning

confidence: 99%

Training decision trees to guide feature selection for infrared image pre-screening algorithms

M.¹,

Nader²

2022

View full text Add to dashboard Cite

This research explores a fresh approach to the selection and weighting of classical image features for infrared object detection and target-like clutter rejection. Traditional statistical techniques are used to calculate individual features, while modern supervised machine learning techniques are used to rank-order the predictivevalue of each feature. This paper describes the use of Decision Trees to determine which features have the highest value in prediction of the correct binary target/non-target class. This work is unique in that it is focused on infrared imagery and exploits interpretable machine learning techniques for the selection of hand-crafted features integrated into a pre-screening algorithm.

show abstract

“…Target detection methods can be mainly divided into single image-based detection methods [4], [5], [6], [7] and sequential images-based detection methods [8], [9], [10], [11]. The former usually segments targets from the background based on the features of the infrared images such as color, texture, shape and so on.…”

Section: Introductionmentioning

confidence: 99%

Target Detection and Pedestrian Recognition in Infrared Images

Wang¹,

Zhang²,

Lu³

et al. 2013

JCP

View full text Add to dashboard Cite

By improving the local contrast between targets and background in the static infrared images, a simple and effective background model is proposed to detect targets. At the same time, a novel learning algorithm is presented for training a discriminatively trained, part-based model with only positives images, for pedestrian recognition. The background models are constructed based on the static infrared images by morphological operations. Meanwhile, the learning algorithm is based on the ramp loss function, which can filter out the false negatives from the collected negative examples. It has a great advantage on training the deformable part models with latent variables when the dataset has a large number of noisy examples. Experiments manifest that our background model can achieve a high precision in target detection and the discriminative part model trained by the proposed learning approach can recognize the targets well and truly, with the help of target detection.

show abstract

Adaptive target detection in forward-looking infrared imagery using the eigenspace separation transform and principal component analysis

Cited by 19 publications

References 18 publications

Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Training decision trees to guide feature selection for infrared image pre-screening algorithms

Target Detection and Pedestrian Recognition in Infrared Images

Contact Info

Product

Resources

About