Automatic target recognition method for low-resolution ground surveillance radar based on 1D-CNN

Xie, Renhong; Dong, Bohao; Rui, Yun; Wang, Xing; Wei, Junfeng

doi:10.1117/12.2581319

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, these exceptional outcomes were realized by employing cutting-edge deep learning-based classifier architectures, such as Convolutional Neural Networks (CNN) and SqueezeNet. A similar scenario can be seen in the case of [36][37][38][39][40], where the accuracy of the detection technique falls as the environment becomes cluttered. This comparison serves to underscore the significance of our newly proposed methodology, as it not only competes favorably with these highly advanced approaches but, importantly, showcases its own merits, particularly in scenarios characterized by varying levels of foliage density.…”

Section: Comparison With Similar Techniquesmentioning

confidence: 63%

Enhancing Outdoor Moving Target Detection: Integrating Classical DSP with mmWave FMCW Radars in Dynamic Environments

Chowdhury,

Melige,

Pal

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper introduces a computationally inexpensive technique for moving target detection in challenging outdoor environments using millimeter-wave (mmWave) frequency-modulated continuous-wave (FMCW) radars leveraging traditional signal processing methodologies. Conventional learning-based techniques for moving target detection suffer when there are variations in environmental conditions. Hence, the work described here leverages robust digital signal processing (DSP) methods, including wavelet transform, FIR filtering, and peak detection, to efficiently address variations in reflective data. The evaluation of this method is conducted in an outdoor environment, which includes obstructions like woods and trees, producing an accuracy score of 92.0% and precision of 91.5%. Notably, this approach outperforms deep learning methods when it comes to operating in changing environments that project extreme data variations.

show abstract

Section: Comparison With Similar Techniquesmentioning

confidence: 63%

Enhancing Outdoor Moving Target Detection: Integrating Classical DSP with mmWave FMCW Radars in Dynamic Environments

Chowdhury,

Melige,

Pal

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…is the output of tanh after convolution and bias is added, j a is the output of the hidden layer, and j r is the output of the output layer. Equations ( 4) - (7) respectively calculate the error between Layer Out's output and the expected output, the error of each hidden layer, the gradient of weights, and the gradient of bias. The loss function adopts mean square error (MSE) as given in equation ( 8).…”

Section: Error Back Propagationmentioning

confidence: 99%

“…There are fewer studies using neural networks for UWB fuze signal processing. Xie et al [7] applied 1D-CNN to radar automatic target recognition, but the input channel includes power spectrum and power transform spectrum in addition to the signal time domain waveform, which is very time-consuming to perform the spectral transform on the actual hardware circuit, and does not meet the high requirements of fuze for real-time; Cai et al [8] successfully applied 1D-CNN to the diagnosis of ECG signal derangement, but its convolutional layers C1 and C2 are fully connected, such a simple network structure has poor performance when facing the fuze echo signal in the actual complex noise environment.…”

Section: Introductionmentioning

confidence: 99%

Real-time Signal Processing of UWB Fuze Based On 1D-CNN Model

Luo

Hou²,

Shi³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The main source of the burst-height error of UWB fuze is the random error related to the fuze signal processing method. Therefore, the use of reliable algorithms to reduce the error as much as possible to avoid bursting early and misfire is very important to improve the burst-height precision of fuze. In this paper, taking the output of the fuze sampling and integrating circuit as the research object, a real-time signal processing method based on the 1D-CNN model is proposed. Simulation results show that the target recognition rate of the 1D-CNN algorithm is as high as 100%, with no bursting early or misfires, and the mean absolute time error is as low as 0.0202s. The burst-height error is effectively reduced.

show abstract

“…Having said all of the above, in view of the differences in clutter distribution caused by environmental diversity, we aim to use an unsupervised deep generative model to learn robustly and model finely complex clutter distributions, find the specific distribution of interested target according to the characteristics of clutter and target difference, and then extract, amplify and detect the interested target in this paper. As a consequence, motivated by [39][40][41][42], we propose a Gaussian Mixture Variational Autoencoder with a onedimensional convolutional neural network (GM-CVAE) method considering the attractive properties of the convolutional neural network (CNN). The model takes pure clutter data as input and learns the log-likelihood as output.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Radar Target Detection under Complex Clutter Background Based on Mixture Variational Autoencoder

Liang

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The clutter background in modern radar target detection is complex and changeable. The performance of classical detectors based on parametric statistical modeling methods is often degraded due to model mismatch. Existing data-driven deep learning methods require cumbersome and expensive annotations. Furthermore, the performance of the detection network is severely degraded when the detection scene changes, since the trained network with the data from one scene is not suitable for another scene with different data distribution. To this end, it is crucial to develop an unsupervised detection method that can finely model complex and changing clutter scenes. This problem is challenging yet rewarding because it completely eliminates the cost of obtaining cumbersome annotations. In this paper, we introduce GM-CVAE, a novel unsupervised Gaussian Mixture Variational Autoencoder with a one-dimensional Convolutional neural network approach to finely model complex and changing clutter. Furthermore, we develop an unsupervised narrow-band radar target detection strategy based on reconstructed likelihood. Comprehensive experiments are carried out to show that the proposed method realizes the refined modeling of clutter and guarantees superior detection performance in the simulated complex clutter environment. Compared with baselines, the proposed method shows better performance.

show abstract

Automatic target recognition method for low-resolution ground surveillance radar based on 1D-CNN

Cited by 3 publications

References 0 publications

Enhancing Outdoor Moving Target Detection: Integrating Classical DSP with mmWave FMCW Radars in Dynamic Environments

Enhancing Outdoor Moving Target Detection: Integrating Classical DSP with mmWave FMCW Radars in Dynamic Environments

Real-time Signal Processing of UWB Fuze Based On 1D-CNN Model

Unsupervised Radar Target Detection under Complex Clutter Background Based on Mixture Variational Autoencoder

Contact Info

Product

Resources

About