Detection and Classification of Finer-Grained Human Activities Based on Stepped-Frequency Continuous-Wave Through-Wall Radar

Abstract

The through-wall detection and classification of human activities are critical for anti-terrorism, security, and disaster rescue operations. An effective through-wall detection and classification technology is proposed for finer-grained human activities such as piaffe, picking up an object, waving, jumping, standing with random micro-shakes, and breathing while sitting. A stepped-frequency continuous wave (SFCW) bio-radar sensor is first used to conduct through-wall detection of finer-grained human activities; Then, a comprehensive range accumulation time-frequency transform (CRATFR) based on inverse weight coefficients is proposed, which aims to strengthen the micro-Doppler features of finer activity signals. Finally, in combination with the effective eigenvalues extracted from the CRATFR spectrum, an optimal self-adaption support vector machine (OS-SVM) based on prior human position information is introduced to classify different finer-grained activities. At a fixed position (3 m) behind a wall, the classification accuracies of six activities performed by eight individuals were 98.78% and 93.23%, respectively, for the two scenarios defined in this paper. In the position-changing experiment, an average classification accuracy of 86.67% was obtained for five finer-grained activities (excluding breathing) of eight individuals within 6 m behind the wall for the most practical scenario, a significant improvement over the 79% accuracy of the current method.

Keywords: comprehensive range accumulation; finer-grained human activity; human micro-Doppler; support vector machine; through-wall.

Figure 1

Schematic diagram of the SFCW radar system.

Figure 2

(a) Through-wall detection of human activity. (b) Preprocessed SFCW radar signal of piaffe-type movement.

Figure 3

The joint time-frequency-range representation of the UWB radar signal.

Figure 4

Time-frequency spectra of SFCW radar signal for piaffe at a distance of 4 m behind the wall, based on different range accumulation methods: (a) Reference method and (b) Proposed method.

Figure 5

CRATFR spectrograms of six finer-grained human activities performed at 3 m behind a wall: (a) piaffe; (b) picking up an object; (c) waving; (d) jumping; (e) standing with random micro-shakes; and (f) breathing while sitting.

Figure 6

Some of the eight features extracted from the CRATFR spectrogram.

Figure 7

Spectrograms of the piaffe activity at different positions: (a) 3 m, (b) 4 m, (c) 5 m, and (d) 6 m.

Figure 8

Operation diagram of OS-SVM based on prior human position information.

Figure 9

Schematic diagrams of the two selection scenarios. (a) The first scenario; (b) The second scenario.

Figure 10

Classification results from four-fold cross-validation for the first scenario. (a) Parameter selection results; (b) Classification errors distribution of the four-fold cross-validation (the horizontal axis represents the actual activity class represented as the numbers 1–6, the vertical axis represents the predicted activity class represented as the numbers 1–6).

Figure 11

Classification results from four-fold cross-validation for the second scenario (a): The parameter selection results. (b) Classification errors distribution of the four-fold cross-validation.

Figure 12

Four-fold cross-validation error distribution of the reference method at changing positions.

Figure 13

Four-fold cross-validation error distributions of proposed method at different positions: (a) 3 m, (b) 4 m, (c) 5 m, and (d) 6 m.