Using Image-Based Metrics to Model Pedestrian Detection Performance With Night-Vision Systems

Bi, Luzheng; Tsimhoni, Omer; Liu, Yili

doi:10.1109/tits.2008.2011719

Cited by 24 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We designed experimental paradigms for target detection under five levels of weak hidden conditions, with half-and-half from the benchmark condition (pure white with R: 255, G: 255, and B: 255) based on RGB color space. The reasons for quantifying the levels using RGB color space rather than other metrics were as follows: (1) RGB color space is considered to be the base color space for various applications [33], and it is the most widely used color model [34] and is closest to a nature scene [35]; (2) although the RGB color space can be transformed into a grey color space [36], the focal point of this study was not to investigate the grey stimuli and different RGB colors that can be transformed into the same grey color space; and (3) a comprehensive metric, e.g., root mean square clutter metric or probability-of-edge metric [37], was not adopted because similar metric values can be obtained by different stimuli, which may lead to different recognition performance. All five experimental paradigms were the same, except for the RGB of the stimuli number with a pure black background (R: 0, G: 0, B: 0).…”

Section: Experiments Paradigmmentioning

confidence: 99%

EEG-Based Target Detection Using an RSVP Paradigm under Five Levels of Weak Hidden Conditions

Lian,

Qiao,

Zhao

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Although target detection based on electroencephalogram (EEG) signals has been extensively investigated recently, EEG-based target detection under weak hidden conditions remains a problem. In this paper, we proposed a rapid serial visual presentation (RSVP) paradigm for target detection corresponding to five levels of weak hidden conditions quantitively based on the RGB color space. Eighteen subjects participated in the experiment, and the neural signatures, including P300 amplitude and latency, were investigated. Detection performance was evaluated under five levels of weak hidden conditions using the linear discrimination analysis and support vector machine classifiers on different channel sets. The experimental results showed that, compared with the benchmark condition, (1) the P300 amplitude significantly decreased (8.92 ± 1.24 μV versus 7.84 ± 1.40 μV, p = 0.021) and latency was significantly prolonged (582.39 ± 25.02 ms versus 643.83 ± 26.16 ms, p = 0.028) only under the weakest hidden condition, and (2) the detection accuracy decreased by less than 2% (75.04 ± 3.24% versus 73.35 ± 3.15%, p = 0.029) with a more than 90% reduction in channel number (62 channels versus 6 channels), determined using the proposed channel selection method under the weakest hidden condition. Our study can provide new insights into target detection under weak hidden conditions based on EEG signals with a rapid serial visual presentation paradigm. In addition, it may expand the application of brain–computer interfaces in EEG-based target detection areas.

show abstract