Search

Human activity classification based on micro-Doppler (m-D) signatures finds applications in surveillance, search and rescue operations, and healthcare. In this article, we propose a new approach for human activity classification. This approach deals with the situations of reduced limb movements that could be due to the presence of injury or an individual carrying objects. It applies a preprocessing step to separate human m-D signals of the limbs from the Doppler signal corresponding to the torso. The separated m-D signal is input to a two-layer convolutional principal component analysis network (CPCAN) for feature extraction and motion classification. The CPCAN comprises a simple network architecture for efficient training and implementation, and it automatically learns the highly discriminative features. Experiments involving multiple human subjects performing different activities show a high classification accuracy associated with small arm motions.

In considering human-machine interface (HMI) for smart environment, a simple but effective method is proposed for automatic arm motion recognition with a Doppler radar sensor. Arms, in lieu of hands, have stronger radar cross-section and can be recognized from relatively longer distances. An energy-based thresholding algorithm is applied to the spectrograms to extract the micro-Doppler (MD) signature envelopes. The positive and negative frequency envelopes are concatenated to form a feature vector. The nearest neighbor (NN) classifier with Manhattan distance (L1) is then used to recognize the arm motions. It is shown that this simple method yields classification accuracy above 97 percent for six classes of arm motions. Despite its simplicity, the proposed method is superior to those of handcrafted featurebased classifications and low-dimension representation techniques based on principal component analysis (PCA), and is comparable to convolutional neural network (CNN)., Comment: 9 pages, 11 figures

Many effective solutions have been proposed to reduce the redundancy of models for inference acceleration. Nevertheless, common approaches mostly focus on eliminating less important filters or constructing efficient operations, while ignoring the pattern redundancy in feature maps. We reveal that many feature maps within a layer share similar but not identical patterns. However, it is difficult to identify if features with similar patterns are redundant or contain essential details. Therefore, instead of directly removing uncertain redundant features, we propose a \textbf{sp}lit based \textbf{conv}olutional operation, namely SPConv, to tolerate features with similar patterns but require less computation. Specifically, we split input feature maps into the representative part and the uncertain redundant part, where intrinsic information is extracted from the representative part through relatively heavy computation while tiny hidden details in the uncertain redundant part are processed with some light-weight operation. To recalibrate and fuse these two groups of processed features, we propose a parameters-free feature fusion module. Moreover, our SPConv is formulated to replace the vanilla convolution in a plug-and-play way. Without any bells and whistles, experimental results on benchmarks demonstrate SPConv-equipped networks consistently outperform state-of-the-art baselines in both accuracy and inference time on GPU, with FLOPs and parameters dropped sharply., Preprint version. The final version has been accepted to appear at IJCAI20

Radar has been recently employed for automatic hand gesture recognition for touchless interactive intelligent devices. Compared to hand gesture, arm gesture recognition can be more suitable for contact-less man-machine interaction with longer range separation. The larger radar cross-section of the arms, vis-a-vis hands, permits more remote interactive positions in an indoor setting. Further, the ability of using hand gestures for device control can sometimes be limited by cognitive impairments such the Parkinson disease. In this case, arm motions can be more robust to strong hand tremor and shaking. In this paper, we discriminate between dynamic arm motions using a Doppler radar sensor. The method considered is motivated by the clear contiguity of the arm signal back-scattering in the time-frequency domain. We use information gleaned from the arm micro-Doppler (MD) signature as the sole features and proceed to classify arm motions using the Nearest Neighbor (NN) classifier. In particular, we analyze the role of the maximum instantaneous Doppler frequencies and their distribution on classification performance. The proposed classification method favorably compares with other methods based on principal component analysis (PCA) and convolutional neural networks (CNN).

Hand and arm gesture recognition using radio frequency (RF) sensing modality proves valuable in man–machine interfaces and smart environments. In this paper, we use the time-series analysis method to accurately measure the similarity of the micro-Doppler (MD) signatures between the training and test data, thus providing improved gesture classification. We characterize the MD signatures by the maximum instantaneous Doppler frequencies depicted in the spectrograms. In particular, we apply two machine learning (ML) techniques, namely, the dynamic time warping (DTW) method and the long short-term memory (LSTM) network. Both methods take into account the values as well as the temporal evolution and characteristics of the time-series data. It is shown that the DTW method achieves high gesture classification rates and is robust to time misalignment.

Spatial attention mechanism is widely used to extract local feature in person re-identification. However, some existing multi-stage spatial attention structures lack flexibility and require complicated training process. In this paper, a plug-and-play LSTM-based Attention Module(LAM) is proposed to enhance flexibility of the multi-attention mechanism. First, we employ the single-stage multi-attention structure to replace the traditional multi-stage multi-attention structure. Our structure encapsulates multiple attention machines in single module and thus the module can be added to any backbone networks without any modification directly. Then, correlation is introduced to spatial attention machines through LSTM. Correlation between different attention machines preserves diversity of the local feature and exploit the capacity of multi-attention mechanism. Moreover, the LAM is added to the backbone network in the form of residual, which enables the LAM to be trained with the backbone network synchronously. Therefore, the training process is simplified effectively. Experiments on CUHK03, Market-1501 and DukeMTMC-ReID datasets demonstrate the advantage of the proposed method.

Hand and arm gesture recognition using the radio frequency (RF) sensing modality proves valuable in manmachine interface and smart environment. In this paper, we use curve matching techniques for measuring the similarity of the maximum instantaneous Doppler frequencies corresponding to different arm gestures. In particular, we apply both Frechet and dynamic time warping (DTW) distances that, unlike the Euclidean (L2) and Manhattan (L1) distances, take into account both the location and the order of the points for rendering two curves similar or dissimilar. It is shown that improved arm gesture classification can be achieved by using the DTW method, in lieu of L2 and L1 distances, under the nearest neighbor (NN) classifier., 6 pages, 7 figures, 2020 IEEE radar conference. arXiv admin note: substantial text overlap with arXiv:1910.11176

We introduce a simple but effective technique in automatic hand gesture recognition using radar. The proposed technique classifies hand gestures based on the envelopes of their micro-Doppler signatures. These envelopes capture the distinctions among different hand movements and their corresponding positive and negative Doppler frequencies which are generated during each gesture act. We detect the positive and negative envelopes separately, and form a feature vector of their augmentation. We use the $k$-nearest neighbor ($k$NN) classifier and Manhattan distance (L1) measure, in lieu of Euclidean distance (L2), so as not to diminish small but critical envelope values. It is shown that this method outperforms both low-dimension representation techniques based on principal component analysis (PCA) and sparse reconstruction using Gaussian-windowed Fourier dictionary, and can achieve very high classification rates., Comment: 6 pages, 7 figures, 2019 radar conference