Adaptive Micro-Doppler Corner Feature Extraction Method Based on Difference of Gaussian Filter and Deformable Convolution
- 18 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 860-864
Abstract
Through-the-wall radar (TWR) utilizes range and Doppler information to achieve indoor human activity recognition. However, traditional recognition methods are developed based on range-time maps (RTM) and Doppler-time maps (DTM), resulting in low accuracy and poor robustness. In order to solve these problems, this letter proposes to use micro-Doppler corner feature to achieve activity recognition and gives an adaptive corner feature extraction method based on difference of Gaussian (DoG) filter and deformable convolution. Micro-Doppler corner feature is defined as the points on the radar squared-range and squared-Doppler images where the gray scale changes sharply in different directions, reflecting the inflection, stationing, intersection, and boundaries of the motion trajectory curves of the human limb nodes. The proposed corner feature extraction method utilizes the DoG filter to extract the micro-Doppler corner supervisory labels on simulated data. The labels are then used to train the $\boldsymbol{\mu }$ D-CornerDet, which is constructed based on deformable convolution network (DCN), task-adaptive deformable convolution network (TDCN), feature pyramid network (FPN) and learnable regression global attention module (LRGA). For predictions, only $\mu$ D-CornerDet is used on measured data to obatin the corner feature maps. Both numerical simulations and experiments are conducted to verify the effectiveness and robustness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61860206012, 62101042)
- Natural Science Foundation of Chongqing Municipality (cstc2020jcyj-msxmX0768, cstc2021jcyj-msxmX0339)
- Beijing Institute of Technology Research Fund Program for Young Scholars (XSQD-202205005)
This publication has 23 references indexed in Scilit:
- A Lightweight Multiscale Neural Network for Indoor Human Activity Recognition Based on Macro and Micro-Doppler FeaturesIEEE Internet of Things Journal, 2023
- ECFRNet: Effective corner feature representations network for image corner detectionExpert Systems with Applications, 2022
- Boosting Crowd Counting via Multifaceted Attention2022
- Graph Matching Based Image Registration for Multi-View Through-the-Wall Imaging RadarIEEE Sensors Journal, 2021
- Human Motion Serialization Recognition With Through-the-Wall RadarIEEE Access, 2020
- ResNet-Based Counting Algorithm for Moving Targets in Through-the-Wall RadarIEEE Geoscience and Remote Sensing Letters, 2020
- Deformable Convolutional Neural Networks for Hyperspectral Image ClassificationIEEE Geoscience and Remote Sensing Letters, 2018
- LIFT: Learned Invariant Feature Transform2016
- Deep Residual Learning for Image Recognition2016
- Accurate Junction Detection and Characterization in Natural ImagesInternational Journal of Computer Vision, 2013