Quantification and recognition of parkinsonian gait from monocular video imaging using kernel-based principal component analysis

Abstract

Background: The computer-aided identification of specific gait patterns is an important issue in the assessment of Parkinson's disease (PD). In this study, a computer vision-based gait analysis approach is developed to assist the clinical assessments of PD with kernel-based principal component analysis (KPCA).

Method: Twelve PD patients and twelve healthy adults with no neurological history or motor disorders within the past six months were recruited and separated according to their "Non-PD", "Drug-On", and "Drug-Off" states. The participants were asked to wear light-colored clothing and perform three walking trials through a corridor decorated with a navy curtain at their natural pace. The participants' gait performance during the steady-state walking period was captured by a digital camera for gait analysis. The collected walking image frames were then transformed into binary silhouettes for noise reduction and compression. Using the developed KPCA-based method, the features within the binary silhouettes can be extracted to quantitatively determine the gait cycle time, stride length, walking velocity, and cadence.

Results and discussion: The KPCA-based method uses a feature-extraction approach, which was verified to be more effective than traditional image area and principal component analysis (PCA) approaches in classifying "Non-PD" controls and "Drug-Off/On" PD patients. Encouragingly, this method has a high accuracy rate, 80.51%, for recognizing different gaits. Quantitative gait parameters are obtained, and the power spectrums of the patients' gaits are analyzed. We show that that the slow and irregular actions of PD patients during walking tend to transfer some of the power from the main lobe frequency to a lower frequency band. Our results indicate the feasibility of using gait performance to evaluate the motor function of patients with PD.

Conclusion: This KPCA-based method requires only a digital camera and a decorated corridor setup. The ease of use and installation of the current method provides clinicians and researchers a low cost solution to monitor the progression of and the treatment to PD. In summary, the proposed method provides an alternative to perform gait analysis for patients with PD.

Figures

Figure 1

A general schematic of the experimental setup used for video recording. The participant wears a light suit to enhance the contrast between the individual and the dark background. The participant walks along the course (approximately 6 m) in front of the video camera (located approximately 4.1 m away). To ensure that the captured data reflect the gait performance during the steady-state walking period, the camera videotapes only the middle 3 m of each walking trial.

Figure 2

A flow-chart of gait analysis and recognition.

Figure 3

The trimmed 64 × 64 pixel binary walking sequence silhouettes of non-PD control (top) and Parkinson's disease (PD) patients in the "Drug-Off" (middle) and "Drug-On" (bottom) states.

Figure 4

An example of step image frames from a non-PD control subject. (a) Step image frames from a non-PD control subject. The top panel is the original sequential walking image frames with 240 × 320 pixels. The bottom panel is the trimmed 64 × 64 pixels binary silhouettes of the top image frames. (b) The magnitudes of the associated sequential primary KPCA components. For simplicity, the primary KPCA component is denoted as 1stKPC. The green dots indicate the magnitudes of the sequential 1stKPCs. (c) The power spectrum of (b) using a 2048-point DFT and rectangular window with a length, L, of 64 points.

Figure 5

The representations of 1stKPC gait feature for non-PD control subjects and PD patients, respectively. (a) The 1stKPC waveform of a selected non-PD control participant. (b) The 1stKPC waveform of a selected PD patient in the "Drug-Off" state. (c) The 1stKPC waveform of the same PD patient in the "Drug-On" state. The red circles and black squares represent the local maximums and minimums, which reflect the occurrences of mid-swings and heel strikes, respectively.

Figure 6

The gait frequency spectra of (a) PD patients in the "Drug-Off" state (red solid line) and the "Drug-On" state and (b) the non-PD controls.

Figure 7

Equipment setup used to measure gait parameters with the GAITRite® mat and its recording system, and the KPCA-based method.

Figure 8

Sequential gait image frames from a healthy subject walking on the GAITRite® walkway system. (a) Sequential gait image frames from a healthy subject walking on the GAITRite walkway system. The top panels are the original sequential walking image frames containing 240 × 320 pixels. The bottom panels are the trimmed 64 × 64 pixel binary silhouettes of the top image frames. (b) The 1stKPC waveform of a selected non-PD control volunteer participating in the preliminary experiment. The green dots indicate the magnitudes of the sequential 1stKPCs.