One of the main challenges in through-the-wall radar imaging (TWRI) is the strong exterior wall returns, which tend to obscure indoor stationary targets, rendering target detection and classification difficult, if not impossible. In this paper, an effective wall clutter mitigation approach is proposed for TWRI that does not require knowledge of the background scene nor does it rely on accurate modeling and estimation of wall parameters. The proposed approach is based on the relative strength of the exterior wall returns compared to behind-wall targets. It applies singular value decomposition to the data matrix constructed from the space-frequency measurements to identify the wall subspace. Orthogonal subspace projection is performed to remove the wall electromagnetic signature from the radar signals. Furthermore, this paper provides an analysis of the wall and target subspace characteristics, demonstrating that both wall and target subspaces can be multidimensional. While the wall subspace depends on the wall type and building material, the target subspace depends on the location of the target, the number of targets in the scene, and the size of the target. Experimental results using simulated and real data demonstrate the effectiveness of the subspace projection method in mitigating wall clutter while preserving the target image. It is shown that the performance of the proposed approach, in terms of the improvement factor of the target-to-clutter ratio, is better than existing approaches and is comparable to that of background subtraction, which requires knowledge of a reference background scene.

In this paper, we mitigate wall EM returns in through-the-wall radar imaging (TWRI) using singular value decomposition (SVD). To suppress wall reflections, the SVD is applied to the B-scan matrix of the received signals. The signal space is decomposed into three subspaces: the clutter subspace, the target subspace, and the noise subspace. Then, a set of normalized and smoothed eigen-components are combined to produce the target signal. Finally, delay-and-sum beamforming is applied to the reconstructed B-scan matrix to form the image. Experimental results demonstrate that the proposed method is effective in removing background, reducing clutter, and high lighting the targets.

This article presents some efficient training algorithms, based on first-order, second-order, and conjugate gradient optimization methods, for a class of convolutional neural networks (CoNNs), known as shunting inhibitory convolution neural networks. Furthermore, a new hybrid method is proposed, which is derived from the principles of Quickprop, Rprop, SuperSAB, and least squares (LS). Experimental results show that the new hybrid method can perform as well as the Levenberg-Marquardt (LM) algorithm, but at a much lower computational cost and less memory storage. For comparison sake, the visual pattern recognition task of face/nonface discrimination is chosen as a classification problem to evaluate the performance of the training algorithms. Sixteen training algorithms are implemented for the three different variants of the proposed CoNN architecture: binary-, Toeplitz- and fully connected architectures. All implemented algorithms can train the three network architectures successfully, but their convergence speed vary markedly. In particular, the combination of LS with the new hybrid method and LS with the LM method achieve the best convergence rates in terms of number of training epochs. In addition, the classification accuracies of all three architectures are assessed using ten-fold cross validation. The results show that the binary- and Toeplitz-connected architectures outperform slightly the fully connected architecture: the lowest error rates across all training algorithms are 1.95% for Toeplitz-connected, 2.10% for the binary-connected, and 2.20% for the fully connected network. In general, the modified Broyden-Fletcher-Goldfarb-Shanno (BFGS) methods, the three variants of LM algorithm, and the new hybrid/LS method perform consistently well, achieving error rates of less than 3% averaged across all three architectures.

An image classification technique, which has recently been introduced for visual pattern recognition, is successfully applied for human gait classification based on radar Doppler signatures depicted in the time-frequency domain. The proposed method has three processing stages. The first two stages are designed to extract Doppler features that can effectively characterize human motion based on the nature of arm swings, and the third stage performs classification. Three types of arm motion are considered: free-arm swings, one-arm confined swings, and no-arm swings. The last two arm motions can be indicative of a human carrying objects or a person in stressed situations. The paper discusses the different steps of the proposed method for extracting distinctive Doppler features and demonstrates their contributions to the final and desirable classification rates.

In recent years, Doppler radar has been used as a sensing modality for human gait recognition, due to its ability to operate in adverse weather and penetrate opaque obstacles. Doppler radar captures not only the speed of the target, but also the micro‐motions of its moving parts. These micro‐motions induce frequency modulations that can be used to characterise the target movements. However, a major challenge in Doppler signal processing is to extract discriminative features from the radar returns for target classification. This study presents a feature extraction method for classification of human motions from the micro‐Doppler radar signal. The proposed method applies the log‐Gabor filters at multiple spatial frequencies and orientations on a joint time–frequency representation. To achieve invariance to the target speed, features are extracted from local patches along the torso Doppler shift. Then, the (2D) ² PCA (two‐directional two‐dimensional principal component analysis) method is applied to create a compact feature vector. Experimental results based on real radar data obtained from multiple human subjects demonstrate the effectiveness of the proposed approach in classifying arm motions.

This paper presents an effective approach for mitigating the wall EM returns in through-the-wall radar imaging. The wall returns tend to obscure indoor targets, rendering target detection and classification difficult, if not impossible. The proposed approach recognizes the relative strength of the front wall returns compared to behind-the-wall targets, and uses eigen-structure methods to identify, and then remove the wall subspace that is typically associated with the dominant eigenvalues. The paper provides analyses of wall and target subspace characteristics, dwelling on the underlying property that the wall and target subspaces are, in most cases, spanned by complex sinusoidal components. It is shown that both the wall and the target subspaces can be of multiple dimensions. The paper demonstrates, using simulated and real data, the effectiveness of the proposed approach and compares its performance to that of background subtraction.