Detectable Design
Methodology

How Detectable Design scores colors

Detectable Design compares visibility colors against local street scenes, then recommends the colors that perform best most often in that city and light condition. The model is based on published research about how people notice color, contrast, brightness, and visual clutter.

Research-backed visibility guidance, translated into one quick recommendation.
Fluorescent Yellow
Chartreuse Lime
Blaze Orange
Bright White
Neon Pink
Safety Red
Local scenes Recommendations are based on the street images collected for each city and light condition.
High-visibility palette The model compares the main high-visibility colors against the same local scene pool.
Research-informed scoring Contrast, brightness, clutter, and color separation all shape the final result.

What gets scored

  • Each city and light condition creates a pool of local street scenes.
  • Each candidate color is scored against each scene on its own.
  • The color that wins the most scenes becomes the top recommendation.
  • The second-most common winner becomes the backup choice.
  • The colors that most often perform worst become the avoid colors.

Core scoring terms

  • Blend risk: estimates how much a color overlaps with the scene around it.
  • Close-region share: estimates how much of the scene is visually too similar to that color.
  • Contrast score: measures how clearly the color separates from the scene in brightness.
  • Luminance score: rewards colors whose brightness still holds up in the available light.
  • Fluorescence bonus: gives fluorescent color families a small daytime visibility boost.
  • Complexity penalty: penalizes colors that blend into busy, cluttered scenes.

Why these terms are in the model

Each term in the model is there for a reason. The goal is not to reward colors that simply look vivid on their own. It is to reward colors that stay noticeable once they are placed into a real street scene.

Blend risk / close-region share

Background contrast

High-visibility clothing can fail if it is too similar to the background and starts to act like camouflage.

Targoutzidis et al. (2021); Sayer & Mefford (2000)

Contrast score

Brightness separation

In low light especially, people notice hazards better when contrast is stronger.

Wood et al. (2005); Jones et al. (2022)

Luminance score

Low-light readability

At night, brightness often matters more than hue alone for whether a person gets noticed.

Sayer & Mefford (2000)

Fluorescence bonus

Daytime lift

Fluorescent yellow-green and similar vivid colors have a documented daytime visibility advantage, especially in peripheral vision.

Zwahlen & Schnell (1996, 1997)

Complexity penalty

Busy scenes

Colors that already blend in should be penalized more when the scene is visually busy and cluttered.

Sayer & Buonarosa (2008)

Citations

These are the main papers and reports used to shape the scoring model and the overall approach.

  1. Targoutzidis, A., et al. Selecting effective colors for high-visibility safety apparel. Safety Science, 2021. doi.org/10.1016/j.ssci.2020.104978
  2. Sayer, J., & Mefford, M. The effect of color contrast on daytime and nighttime conspicuity of roadworker vests. UMTRI, 2000. hdl.handle.net/2027.42/49418
  3. Sayer, J., & Buonarosa, M. The roles of garment design and scene complexity in the daytime conspicuity of high-visibility safety apparel. Journal of Safety Research, 2008. doi.org/10.1016/j.jsr.2007.12.004
  4. Zwahlen, H., & Schnell, T. Conspicuity Advantage of Fluorescent Color Targets in the Field. Human Factors and Ergonomics Society Annual Meeting Proceedings, 1996. doi.org/10.1177/154193129604001810
  5. Zwahlen, H., & Schnell, T. Visual Detection and Recognition of Fluorescent Color Targets Versus Nonfluorescent Color Targets as a Function of Peripheral Retinal Location, Target Size, and Luminance. Transportation Research Record, 1997. doi.org/10.3141/1605-05
  6. Wood, J., Tyrrell, R., et al. Limitations in Drivers' Ability to Recognize Pedestrians at Night. Human Factors, 2005. doi.org/10.1518/001872005774859980
  7. Babić, D., et al. Factors affecting pedestrian conspicuity at night: Analysis based on driver eye tracking. Safety Science, 2021. doi.org/10.1016/j.ssci.2021.105257
  8. Jones, P., et al. Contrast Sensitivity and Night Driving in Older People. Frontiers in Human Neuroscience, 2022. doi.org/10.3389/fnhum.2022.914459

What is still heuristic

This is not a medical, legal, or crash-risk model. It is a directional visibility tool that combines research-backed ideas with engineering choices such as color-distance thresholds, image-complexity estimates, and local scene sampling. The studies above support the structure of the model, but they do not validate every constant in the implementation.