ROVI-EVS · WHITE PAPER

Event Camera (EVS) White Paper

How an event camera (EVS) is built, how it sees motion, and how it differs from an ordinary RGB camera — explained with diagrams and video.

1. Summary

An ordinary camera (RGB camera) captures the whole picture at fixed intervals. An event camera (EVS, Event-based Vision Sensor) sends a signal only from pixels whose brightness changed, at the moment they changed. An EVS is therefore less a picture-taking device than a sensor that outputs motion directly.

RGB cameraEvent camera (EVS)
What it outputsEvery pixel's brightness at fixed intervals (fps) = the state of the scene(x, y, polarity, time) of pixels that changed = the change in the scene
Time resolution1/fps (33 ms at 30 fps), blurred during exposureµs time stamps, equivalent to over 10,000 fps (spec)
Dynamic rangeabout 60–70 dBover 120 dB (spec)
Data volumeConstant, whatever the sceneProportional to motion, almost zero for a still scene
Good atColour, texture, recognising still objectsFast motion, speed, backlight and low light, low latency
Not good atMoments between frames, high-speed motion, strong backlightStill objects, colour and texture

In one line: an EVS sees "when, where and how fast" something moved; an RGB camera sees "what" it is. The two sensors complement each other more than they replace each other.

2. What a frame camera misses

Like film, a frame camera shows motion by stringing still pictures together quickly. This has three built-in limits.

  1. It cannot see between frames. A 30 fps camera takes one picture every 33 ms and records nothing in between. A fast flash, collision or fall can be over between two pictures.
  2. It blurs during the exposure. If an object moves while a picture is being taken, it smears. A shorter exposure makes the picture darker and noisier.
  3. It resends what has not changed. Even when most of the scene is still, every pixel is sent and processed in every frame, and finding motion means filtering the background out of all that data again.

On top of that, one exposure holds only a narrow range of brightness, so in strong backlight the bright side turns white and the dark side black.

3. How an event camera works

Each EVS pixel keeps watching the brightness at its position as a logarithmic (log) value. When the difference between the current value and the value at its last event (the reference) exceeds a set threshold C, it sends one event at that moment.

log brightness time fast change between frames → RGB misses it, EVS records it as events no change → no events (no data) reference ± C (threshold) ON event (brighter) OFF event (darker) RGB frame — once every 33 ms (30 fps)
One pixel's brightness (white line) and its events. The grey dashed line is the reference; the arrows are the ON (orange) and OFF (blue) events sent each time the brightness moves C away from it. The grey circles are when a 30 fps RGB camera samples the same pixel — the RGB camera misses the short flash between two frames, while the EVS records it as events.

What one event contains

FieldMeaning
x, yPixel position
PolarityBrighter (ON, 1) or darker (OFF, 0)
TimestampIn µs, stamped on each event

Events are a list of "which pixel changed when, and which way", so to show them to people you collect the events over a period and draw them (accumulated frame, time surface — chapter 7).

Why log brightness

A difference of log values is a ratio of brightness. So the edge of the same object shows the same size of change in deep shade and in sunlight 400 times brighter. This is the basis of the wide dynamic range of an EVS (over 120 dB).

4. EVS sensor structure

Behind the light-sensitive part, each EVS pixel holds a circuit that decides whether something changed. Where a frame-camera pixel "collects light and waits to be read", an EVS pixel "decides for itself and reports only what changed".

PIXEL Light scene brightness Photodiode light → current Log conversion current → log value very wide range Change detector vs. the value at the last event Comparators above +C → ON below −C → OFF Event (x, y, polarity, t) µs time stamp after an event, the reference resets to the current value every pixel decides on its own, at the same time 1280 × 720 pixels (IMX636) only pixels that changed send events → one event stream asynchronous readout · time ordered · 2.5GigE
EVS pixel structure — light → photodiode → log conversion → change detector → comparators → event, with the reference reset after each event. Below: every pixel decides on its own, and only events from pixels that changed leave as one stream.
StageWhat it does
PhotodiodeTurns incoming light into current
Log conversion (photoreceptor)Turns current into a log-brightness voltage — handles everything from near darkness to direct sunlight at once
Change detectorKeeps computing the difference between the current value and the value stored at the last event
Comparators (ON / OFF)Sends an ON event above +C or an OFF event below −C, then resets the reference
Asynchronous readoutReads only pixels that fired, in order, and sends them with position, polarity and time

Stacked sensor and on-chip processing

The Sony IMX636 used in ROVI-EVS is a stacked sensor: a pixel chip that receives light is bonded onto a logic chip that decides and processes events. Moving the decision circuits to the lower chip keeps the pixels small (4.86 µm) while reaching 1280 × 720 resolution. The logic chip also has functions that tidy up the events.

On-chip functionWhat it does
Event rate control (ERC)Caps events per second so a sudden flood cannot overrun transfer or processing
Anti-flicker (AFK)Filters events caused by light that flickers at a fixed frequency, such as fluorescent or LED lighting
Noise filter (STC)Filters isolated events not connected to their neighbours (noise)
You can switch these on and off in the control window of the ROVI-EVS evaluation kit (user manual, chapter 5 "Control window").

5. Frames and events — what is different

Draw a black dot circling a bright disc five times a second in x · y · time space and the difference is plain.

Illustration (10× slower than real time). Left: a 30 fps frame camera takes a thin slice every 33 ms, with nothing in between. Right: an event camera fires at every pixel the dot's edge passes, drawing an unbroken helix — the leading edge gets darker, so OFF (blue); the trailing edge gets brighter, so ON (orange).
RGB cameraEvent camera (EVS)
How it worksAll pixels expose at the same time → read out togetherEach pixel separately, the moment a change happens
Time resolution1/fps — 33 ms at 30 fpsµs time stamps, equivalent to over 10,000 fps (spec)
LatencyExposure + waiting for frame transferPixel latency 100 µs or less @ 1000 lx (spec)
Motion blurOccurs during exposureNone — there is no exposure
Dynamic rangeabout 60–70 dB (HDR needs several exposures)over 120 dB (spec) — log response
Data volume1280 × 720 × 60 fps = about 55 million pixel values a second, whatever the sceneabout 0.33 million events/s in a near-still room, about 2 million events/s with people walking (measured)
Still sceneVisible as isNo events → looks empty
Colour and textureYesNo (brightness change only)
Sensor settingsExposure, gain, white balance (mature automation)Sensitivity and on-chip filters set to suit the scene

6. Motion blur and dynamic range

Picture fan blades turning 20 times a second, with the right half in sunlight 400 times brighter than the shade.

Synthetic illustration (40× slower than real time). Left: an RGB camera at 30 fps with a 1/60 s exposure — the blades turn a third of a revolution during one exposure and blur into a disc, and the sunlit side clips to white so the blades vanish. Right: events from the same scene (last 0.3 ms) — the blade edges stay sharp in shade and in sun, and the still wall and hub produce no events.

7. Real recordings

All of the following were recorded by FLOYD with a Triton2 EVS (6.5 mm lens).

30 fps and 10,000 fps

Drawing the events at 0.1 ms intervals lets you watch them like 10,000 fps video. Here it is next to the same scene as a 30 fps camera would capture it (33 ms exposure).

Left: as a 30 fps camera would capture it (33 ms exposure) · Right: the same moment drawn from events as 10,000 fps frames

Two ways to look at events

ViewHow it is drawnGood for
Accumulated frame (events view)Events over a short time as dots, coloured by polaritySeeing edge shapes
Time surfaceEach pixel's last event time as brightness — the more recent, the brighterSeeing direction and flow at a glance
Events view (left) and time surface (right) — only the edges of the walking person appear and the background is empty

Tracking moving targets

In an EVS, "where events gather is where something moved", so moving targets can be found directly, without a background model or an AI recognition model. ROVI-EVS gives each target an ID and works out its speed and trail — updates at 100 Hz, tracking p95 3 ms (measured).

ROVI-EVS live tracking — boxes, IDs, speed (px/s), trails and motion arrows

8. Strengths and limits

Strengths

StrengthWhyFigures
Motion = signalA still background is not output → no background removal needed—
High time resolution, low latencyEach pixel outputs the moment it changesEquivalent to over 10,000 fps · pixel latency 100 µs or less (spec)
No motion blurThere is no exposure time—
Wide dynamic rangeLog response — sees ratios of brightnessOver 120 dB · down to 0.08 lx (spec)
Less data, less computingOnly changed pixels are output, almost zero when stillAbout 0.33 million events/s in a still room (measured)
PrivacyNo colour or texture in the output, so faces are hard to recognise—

Limits

LimitDetailsWhat to do
Still objects are invisibleWhen both camera and target stop, there are no eventsTracking software remembers briefly stopped targets · use RGB to confirm a still state
No colour or textureIt knows "something is moving" but finds it hard to tell people, vehicles and objects apartPair with an RGB camera when the type matters
Low contrastChanges smaller than the threshold C produce no events — targets close to the background colour, long distancesAdjust lens, lighting and mounting distance
Event floodsFlickering lights, camera shake, or lights switching on and off make every pixel respondOn-chip anti-flicker and event rate control, fix the camera firmly
Resolution and price0.92 MP, 1/2.5" sensor — costs more than a comparable RGB cameraUse where motion and speed are what matter
Tools and experienceFewer AI models, public data and standard tools than RGB; per-scene setting experience neededFLOYD processing software and set-up support

9. Where to use it

Selection guide

◎ best · ○ possible · △ limited · ✕ unsuitable

TaskEVSRGBBothWhy
People counting, paths, passing speed◎○◎Sees only motion, no background handling
High-speed falling objects, rotating parts, vibration◎△○µs time resolution, no blur (RGB needs a high-speed camera)
Backlit entrances, tunnels, night◎△◎Over 120 dB dynamic range
Long-term monitoring with limited bandwidth or power◎△○Almost no data when nothing moves
Privacy-sensitive spaces◎△△No faces or texture in the output
Telling vehicle and person types apart△◎◎Type from RGB, motion and speed from EVS
Still objects, stock checks✕◎○An EVS cannot see what has stopped
Colour, text, appearance inspection✕◎△Colour and texture are RGB territory

Using both: the EVS reports first when and where something moved and how fast, and the RGB camera checks only that area at that moment. Each sensor covers the other's weak points, and the RGB side needs less computing.

Application examples

Application areas from the camera supplier's (LUCID) material. Figures are from the vendor material and depend on conditions.

AreaExamples
Machines and processesNon-contact vibration frequency measurement (1 Hz to kHz, pixel level), cable and yarn speed and slip monitoring, high-speed counting (over 1,000 objects a second), high-speed 3D with a line laser (over 10 kHz)
Safety and spacesPeople counting and tracking, fall detection, safety-zone intrusion, gesture recognition
TrafficTraffic counts and vehicle tracking, scenes with large brightness differences such as tunnel entrances
Drones and robotsTracking fast flying objects, obstacle avoidance, LED marker positioning
People and gazekHz-class eye tracking, driver monitoring (low light)

FLOYD is focusing first on tracking moving people and vehicles (the ROVI-EVS evaluation kit), high-speed counting of falling objects (pharmaceuticals), and tracking moving targets in backlight and low light.

10. Triton2 EVS and ROVI-EVS

LUCID Triton2 EVS

ItemDetails (spec)
ModelsTRT009S-EC (Sony IMX636, 1280 × 720, 0.9 MP) · TRT003S-EC (Sony IMX637, 640 × 512, 0.3 MP)
Pixel4.86 µm · 1/2.5" (IMX636)
Time resolutionEquivalent to over 10,000 fps
Dynamic rangeOver 120 dB
Low-light cut-off0.08 lx
InterfaceM12 2.5GigE · PoE
ProtectionIP67 (dust and water)
LensC-mount

ROVI-EVS

ROVI-EVS is an evaluation kit combining the Triton2 EVS (TRT009S-EC) with FLOYD processing software. Using only a CPU, without a GPU, it finds moving targets, shows ID, box, speed and trail in real time and saves them as CSV, and lets you replay fast moments in 10,000 fps super slow motion.

ItemDetails
Update rate100 Hz (10 ms) (measured)
Tracking processing timep95 3 ms (measured)
Live processing limit9.8 Mev/s, no loss (measured)
Super slow motion0.1 ms intervals, equivalent to 10,000 fps

Set-up and use are in the ROVI-EVS user manual; send application review requests through floyd.kr contact.

11. Glossary

TermMeaning
EVS, event cameraEvent-based Vision Sensor. Outputs only pixels whose brightness changed, at the moment they changed. Also called DVS (Dynamic Vision Sensor) or neuromorphic camera
EventOne brightness change at one pixel — (x, y, polarity, time)
PolarityBrighter (ON) / darker (OFF)
Threshold (C)The smallest log-brightness change that produces an event — smaller is more sensitive but noisier
Event rateEvents per second. ev/s, Mev/s (millions per second)
Accumulated frameEvents over a short time drawn together in one picture
Time surfaceA picture showing each pixel's last event time as brightness
Dynamic rangeRatio between the darkest and brightest parts visible in one scene at once. 20 dB = 10×, 120 dB = 1,000,000×
Equivalent fpsFrames per second you get by drawing events at that interval. Equivalent to 10,000 fps = 0.1 ms intervals
ERC, AFK, STCOn-chip event rate control, anti-flicker and noise filter (chapter 4)