Cepstrum-based analysis of radar Doppler signals

Andrić, Milenko; Bujaković, Dimitrije; Bondžulić, Boban; Zrnic, B.

doi:10.1109/telsks.2011.6143180

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Description of the database. Computational experiment is based on radar signal database described in [6]. The sensor that is used to generate data -land-based pulse Doppler radar, operating at Ku band at a frequency of 16.8 GHz.…”

Section: Computational Experimentsmentioning

confidence: 99%

Classification of the Signatures for Doppler Radar from the Standpoint of Active Perception Theory

Gai

Bogdan

2016

KEM

View full text Add to dashboard Cite

show abstract

Section: Computational Experimentsmentioning

confidence: 99%

Classification of the Signatures for Doppler Radar from the Standpoint of Active Perception Theory

Gai

Bogdan

2016

KEM

View full text Add to dashboard Cite

show abstract

“…Therefore, the selection of features largely determines the accuracy of radar classification. Radar target classification and recognition can be roughly divided into radar micro-Doppler classification [1][2][3][4][5] , target classification based on time-frequency joint analysis 6 , and radar target classification based on fuzzy logic 7 . etc., most of which are based on target feature micro-Doppler classification.…”

Section: Introductionmentioning

confidence: 99%

Ground surveillance radar targets classification based on 2D multichannel adaptive weighted CNN

Xu,

Rui,

Wang

et al. 2024

Fifteenth International Conference on Signal Processing Systems (ICSPS 2023)

View full text Add to dashboard Cite

In this paper, a new 2D convolutional neural network (CNN) model is proposed for the classification of people, cars, and UAVs detected by low-resolution ground surveillance radars. Process the signals of people, cars, and UAVs in different domains to obtain the unique characteristics of the target signal, which can be used for target classification and recognition.Using the newly designed model to classify radar targets is divided into three steps. First, the Toeplitz matrix is used to reconstruct the 1D radar signal into 2D signals, and then a multi-channel adaptive attention module is constructed to classify radar targets. In the first step, since 2D radar signals are required for training, the 2D data is reconstructed using the Toeplitz matrix. In the second step, a channel attention module and a coordinate attention module weighted with adaptive coefficients are constructed, and the two are combined to form a multi-channel adaptive attention module. This module extracts features from the input through receptive fields of different sizes on different channels, and performs feature fusion. Since the overall network introduces a residual structure, the possible gradient disappearance/explosion problem in backpropagation is effectively solved. Tested on the actual human, car and UAV data sets, the accuracy rate reached 98.7% on the original time domain test set, 96.9% accuracy rate was achieved on the original frequency domain test set.

show abstract

“…Most proposed ATR approaches are based on conventional handcrafted features extracted from echo signals. Examples of handcrafted features include the central Doppler frequency and the width of the spectral band [7], cepstrum coefficients [9], [10], cadence frequency [11], cadencevelocity diagrams (CVDs) [12], and time-velocity diagrams [13]. For the last method, [14], Perisco et al proposed a computationally efficient variant by using Krawtchouk moments.…”

Section: Introductionmentioning

confidence: 99%

Learned Micro-Doppler Representations for Targets Classification Based on Spectrogram Images

Alhadhrami¹,

Al-Mufti²,

Taha

et al. 2019

IEEE Access

View full text Add to dashboard Cite

This paper proposes a new approach for classifying ground moving targets captured by pulsed Doppler radar. Radar echo signals express the Doppler effect that moving targets produce. A learned feature representation extracted from spectrogram images using a transfer learning paradigm is proposed. A discrimination power analysis that derives highly discriminative features used to train a robust classifier was conducted. The extensive experiments performed on the public RadEch dataset show that the proposed method produces a significant boost in performance when compared to other state-of-the-art methods.INDEX TERMS Target detection, micro-Doppler signatures, spectrograms, learned features representation, convolutional neural networks, transfer learning.

show abstract

Cepstrum-based analysis of radar Doppler signals

Cited by 7 publications

References 10 publications

Classification of the Signatures for Doppler Radar from the Standpoint of Active Perception Theory

Classification of the Signatures for Doppler Radar from the Standpoint of Active Perception Theory

Ground surveillance radar targets classification based on 2D multichannel adaptive weighted CNN

Learned Micro-Doppler Representations for Targets Classification Based on Spectrogram Images

Contact Info

Product

Resources

About