No abstract

Computer vision‐based displacement measurement for structural monitoring has grown popular. However, tracking natural low‐contrast targets in low‐illumination conditions is inevitable for vision sensors in the field measurement, which poses challenges for intensity‐based vision‐sensing techniques. A new edge‐enhanced‐matching (EEM) technique improved from the previous orientation‐code‐matching (OCM) technique is proposed to enable robust tracking of low‐contrast features. Besides extracting gradient orientations from images as OCM, the proposed EEM technique also utilizes gradient magnitudes to identify and enhance subtle edge features to form EEM images. A ranked‐segmentation filtering technique is also developed to post‐process EEM images to make it easier to identify edge features. The robustness and accuracy of EEM in tracking low‐contrast features are validated in comparison with OCM in the field tests conducted on a railroad bridge and the long‐span Manhattan Bridge. Frequency domain analyses are also performed to further validate the displacement accuracy.

Computer vision-based displacement measurement techniques can be affected by the optical turbulence in the field in hot weather. The optical turbulence can be observed naturally when viewing a thick layer of heated air. The nonuniform density distribution of the air due to heat creates spatial variations in refraction indexes, resulting in distortions in video images and measurement errors in displacements obtained from distorted videos. The effect of optical turbulence on vision-based displacement sensing is first illustrated in the field test conducted in hot weather. Then, the statistical characteristics of the optical-turbulence-induced measurement errors are analyzed and confirmed.And a comprehensive optical-turbulence error alleviation technique, which has two steps, is designed based on the statistical studies. A previously developed high-performance multitarget vision-based displacement measurement technique is utilized in the first step to track multiple targets. Distortions of multiple targets are estimated simultaneously continuously. Targets with the least distortions in each frame are identified and their displacements are extracted as the primary displacement. To further alleviate errors in the primary displacement, an adaptive optical-turbulence error filter is formulated in the second step based on the statistical characteristics of the optical-turbulence errors. Validations of the optical-turbulence error alleviation technique are performed in both laboratory and field tests. Field tests are conducted on the Williamsburg Bridge in the natural environment. After alleviating opticalturbulence and camera vibration errors, frequency domain analyses are conducted on vibrational displacements of the Williamsburg Bridge in response to train passing. K E Y W O R D Scomputer vision, displacement measurement, frequency domain analysis, laboratory and field validation, optical-turbulence error alleviation

In this paper, we propose simultaneous and sequential hybrid brain-computer interfaces (hBCIs) that incorporate electroencephalography (EEG) and electromyography (EMG) signals to classify drivers’ hard braking, soft braking, and normal driving intentions to better assist driving for the first time. The simultaneous hBCIs adopt a feature-level fusion strategy (hBCI-FL) and classifier-level fusion strategies (hBCIs-CL). The sequential hBCIs include the hBCI-SE1, where EEG signals are prioritized to detect hard braking, and hBCI-SE2, where EMG signals are prioritized to detect hard braking. Experimental results show that the proposed hBCI-SE1 with spectral features and the one-vs-rest classification strategy performs best with an average system accuracy of 96.37% among hBCIs. This work is valuable for developing human-centric intelligent assistant driving systems to improve driving safety and driving comfort and promote the application of BCIs.