--- title: What Automatic Incident Detection Misses, and Why description: "What automatic incident detection misses, according to Caltrans and multi-state DOT evaluations: sensor gaps, PTZ, night, weather and false alarms." image: https://blog.goodvisionlive.com/hubfs/12_aid-blog-header-1.png --- ###### Stay in touch ### Subscribe to Newsletter Get latest updates and news about GoodVision directly to your inbox. [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) - [Free demo](https://goodvision.typeform.com/freetrial25?utm_source=gv-blog&utm_medium=menu) - [Case studies](https://casestudies.goodvisionlive.com) - [Blog](https://blog.goodvisionlive.com) - [Return to homepage](https://goodvisionlive.com/) [Contact us](https://goodvisionlive.com/contacts/) [![GoodVision - Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/TITLE-R-black.png?width=175&height=30&name=TITLE-R-black.png "GoodVision - Smart cities matter.")](https://goodvisionlive.com/) - [Case studies](https://casestudies.goodvisionlive.com) - [Blog](https://blog.goodvisionlive.com) - [Return to homepage](https://goodvisionlive.com/) - [Contact us](https://goodvisionlive.com/contacts) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) - [Solutions](https://goodvisionlive.com/solutions/) [Real-time Traffic Monitoring](https://goodvisionlive.com/solutions/real-time-traffic-monitoring/) [![refresh\_icon-1](https://blog.goodvisionlive.com/hubfs/refresh_icon-1.svg) ![refresh\_icon\_green](https://blog.goodvisionlive.com/hubfs/refresh_icon_green.svg) AID](https://goodvisionlive.com/solutions/aid/) [![money\_icon](https://blog.goodvisionlive.com/hubfs/money_icon.svg) ![money\_icon\_green](https://blog.goodvisionlive.com/hubfs/money_icon_green.svg) Tolling](https://goodvisionlive.com/solutions/tolling/) [![road\_icon](https://blog.goodvisionlive.com/hubfs/road_icon.svg) ![road\_icon\_green](https://blog.goodvisionlive.com/hubfs/road_icon_green.svg) Traffic Flow Monitor](https://goodvisionlive.com/solutions/traffic-flow-monitor/) [![warning\_icon](https://blog.goodvisionlive.com/hubfs/warning_icon.svg) ![warning\_icon\_green](https://blog.goodvisionlive.com/hubfs/warning_icon_green.svg) Traffic Violation Detection](https://goodvisionlive.com/solutions/traffic-violation-detection/) [![car\_icon\_white](https://blog.goodvisionlive.com/hubfs/car_icon_white.svg) ![car\_icon\_green-1](https://blog.goodvisionlive.com/hubfs/car_icon_green-1.svg) Parking Monitor](https://goodvisionlive.com/solutions/parking-occupancy/) [![lights\_icon](https://blog.goodvisionlive.com/hubfs/lights_icon.svg) ![lights\_icon\_green](https://blog.goodvisionlive.com/hubfs/lights_icon_green.svg) Traffic Controller](https://goodvisionlive.com/solutions/traffic-controller/) [Traffic Data Collection From Camera and Drones](https://goodvisionlive.com/solutions/traffic-data-collection/) [Traffic Data Analytics For Traffic Modelling](https://goodvisionlive.com/solutions/traffic-modelling/) [![alt](https://blog.goodvisionlive.com/hs-fs/hubfs/adad4.webp?width=300&height=96&name=adad4.webp) Go to our APP](https://my.goodvisionlive.com/en/login) - [Products](https://goodvisionlive.com/products/) - [Video Insights Platform](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) - Partners - [Global Sales Partners](https://goodvisionlive.com/partners/) - [Technology Partners](https://goodvisionlive.com/technology-partners/) - [Academy Program](https://goodvisionlive.com/goodvision-academy/) - Resources - [Case Studies](https://casestudies.goodvisionlive.com/) - [Help Portal](https://goodvisionlive.com/support/) - [Webinars](https://goodvisionlive.com/webinars/) - [Blog](https://blog.goodvisionlive.com/) - [Company](https://goodvisionlive.com/about-goodvision/) - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) - [Contact us](https://goodvisionlive.com/contacts/) [Contact us](https://goodvisionlive.com/contacts/) [![GoodVision - Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/TITLE-R-black.png?width=175&height=30&name=TITLE-R-black.png "GoodVision - Smart cities matter.")](https://goodvisionlive.com/) - [Solutions](https://goodvisionlive.com/solutions/) [Real-time Traffic Monitoring](https://goodvisionlive.com/solutions/real-time-traffic-monitoring/) [![refresh\_icon-1](https://blog.goodvisionlive.com/hubfs/refresh_icon-1.svg) ![refresh\_icon\_green](https://blog.goodvisionlive.com/hubfs/refresh_icon_green.svg) AID](https://goodvisionlive.com/solutions/aid/) [![money\_icon](https://blog.goodvisionlive.com/hubfs/money_icon.svg) ![money\_icon\_green](https://blog.goodvisionlive.com/hubfs/money_icon_green.svg) Tolling](https://goodvisionlive.com/solutions/tolling/) [![road\_icon](https://blog.goodvisionlive.com/hubfs/road_icon.svg) ![road\_icon\_green](https://blog.goodvisionlive.com/hubfs/road_icon_green.svg) Traffic Flow Monitor](https://goodvisionlive.com/solutions/traffic-flow-monitor/) [![warning\_icon](https://blog.goodvisionlive.com/hubfs/warning_icon.svg) ![warning\_icon\_green](https://blog.goodvisionlive.com/hubfs/warning_icon_green.svg) Traffic Violation Detection](https://goodvisionlive.com/solutions/traffic-violation-detection/) [![car\_icon\_white](https://blog.goodvisionlive.com/hubfs/car_icon_white.svg) ![car\_icon\_green-1](https://blog.goodvisionlive.com/hubfs/car_icon_green-1.svg) Parking Monitor](https://goodvisionlive.com/solutions/parking-occupancy/) [![lights\_icon](https://blog.goodvisionlive.com/hubfs/lights_icon.svg) ![lights\_icon\_green](https://blog.goodvisionlive.com/hubfs/lights_icon_green.svg) Traffic Controller](https://goodvisionlive.com/solutions/traffic-controller/) [Traffic Data Collection From Camera and Drones](https://goodvisionlive.com/solutions/traffic-data-collection/) [Traffic Data Analytics For Traffic Modelling](https://goodvisionlive.com/solutions/traffic-modelling/) [![alt](https://blog.goodvisionlive.com/hs-fs/hubfs/adad4.webp?width=300&height=96&name=adad4.webp) Go to our APP](https://my.goodvisionlive.com/en/login) - [Products](https://goodvisionlive.com/products/) - [Video Insights Platform](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) - Partners - [Global Sales Partners](https://goodvisionlive.com/partners/) - [Technology Partners](https://goodvisionlive.com/technology-partners/) - [Academy Program](https://goodvisionlive.com/goodvision-academy/) - Resources - [Case Studies](https://casestudies.goodvisionlive.com/) - [Help Portal](https://goodvisionlive.com/support/) - [Webinars](https://goodvisionlive.com/webinars/) - [Blog](https://blog.goodvisionlive.com/) - [Company](https://goodvisionlive.com/about-goodvision/) - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) - [Contact us](https://goodvisionlive.com/contacts/) ![automatic incident detection](https://blog.goodvisionlive.com/hubfs/12_aid-blog-header-1.png) ![automatic incident detection](https://blog.goodvisionlive.com/hubfs/12_aid-blog-header-1.png) # What Automatic Incident Detection Misses, and Why Oct 2, 2026, 2:01:52 PM Automatic incident detection misses five things most often: incidents between sensors, incidents in light traffic, anything a PTZ camera sees once it has moved off its preset, events at night or in bad weather, and real alerts buried among false ones. Public evaluations by Caltrans, a multi-state DOT pooled fund and the New England Transportation Consortium all describe the same gaps. None of these are exotic failures. They come from how AID systems are built and where they are deployed, and they show up in almost every agency review of the technology. Knowing them in advance is the difference between a pilot that proves something and one that only proves the vendor's demo. ## How is automatic incident detection measured? Three numbers describe any AID system. The [New England Transportation Consortium's review of incident detection algorithms](https://onlinepubs.trb.org/onlinepubs/trispdfs/00988875.pdf) (Parkany and Xie, 2005) defines them: - **Detection rate (DR):** detected incidents as a share of all actual incidents in a given period. - **False alarm rate (FAR):** false alarms as a share of all alarms, or as false alarms per day or per hour. Check which definition a vendor uses, because the numbers are not comparable. - **Mean time to detect (MTTD):** the time from the moment an incident occurs to the moment the system declares it. ![Chart of how detection rate, false alarms and time to detect change as an AID alarm threshold moves from strict to sensitive. Detection rate and false alarms rise together while time to detect falls. A single accuracy figure hides where on the curve a system is tuned.](https://blog.goodvisionlive.com/hs-fs/hubfs/aid-figure-1-metrics.png?width=1600&height=900&name=aid-figure-1-metrics.png) The same review states the catch plainly: the figures "clearly illustrate the tradeoffs between the three performance parameters." Tune for a higher detection rate and false alarms rise. Tune false alarms down and incidents get missed or detected later. A single headline accuracy figure hides which way a system has been tuned. ## What does automatic incident detection miss? | Blind spot | Why it happens | What the evidence says | | --- | --- | --- | | Incidents between sensors | Detection covers what a detector or camera can see, and full coverage of a network is rarely affordable | AID is "effective principally for major incidents or for incidents that occur in the immediate vicinity of a sensor" ([NETC, 2005](https://onlinepubs.trb.org/onlinepubs/trispdfs/00988875.pdf)). Full coverage is "a challenging proposition… gaps will inevitably remain" ([ENTERPRISE Pooled Fund, 2022](https://enterprise.prog.org/wp-content/uploads/ENT-Automated-Incident-Detection-FR-Jan-2022.pdf)) | | Incidents in light traffic | Flow-based algorithms look for congestion, and a blockage on a quiet road may not cause any | "Most existing algorithms cannot deal with incident detection under low volume conditions very well" (NETC, 2005) | | PTZ cameras off preset | Video analytics are calibrated to one camera position | "AID doesn't work unless the camera is in its home position" (ENTERPRISE, 2022) | | Night, shadows and weather | Vision models lose contrast in darkness, glare, rain and snow | "lighting (darkness, glare, shadows, etc.) and weather (rain, snow) degraded AVID performance, even in modern systems" ([Caltrans, 2018](https://rosap.ntl.bts.gov/view/dot/66173/dot_66173_DS1.pdf)) | | Real alerts among false ones | Operators stop trusting a system that alarms too often | "operator fatigue with high false alarm rates will invariably lead to AID systems being ignored" (Caltrans, 2018) | ## Why do incidents between sensors go undetected? Point detection sees only its own patch of road. Loop-based algorithms such as the California algorithm compare occupancy at two adjacent detector stations, because an incident "is likely to cause a significant increase in upstream occupancy while simultaneously reducing occupancy downstream," as the NETC review describes it. That logic works, but its speed depends on geometry: the review notes that the required distance between stations "is directly related to the time required to detect an incident." ![Three cameras along a corridor. CAM 01 detects a stopped vehicle in view. Between CAM 02 and CAM 03 there is no camera view, so the incident is inferred from the queue upstream and the falling flow downstream.](https://blog.goodvisionlive.com/hs-fs/hubfs/02-between-cameras.png?width=1600&height=900&name=02-between-cameras.png) The same review records what traffic management centers reported about the California algorithm in practice: difficult calibration, a detection rate below 50%, a high false alarm rate and long times to detection. Some centers dropped earlier algorithms altogether for those reasons. We covered how corridor-level correlation handles the gap between cameras in [Automatic Incident Detection Beyond a Single Camera View](https://blog.goodvisionlive.com/automatic-incident-detection-beyond-single-camera-view). ## Why do PTZ cameras break video detection? Operators move PTZ cameras constantly, which is the point of having them. Most video AID is calibrated to one fixed view. The [ENTERPRISE pooled fund study](https://enterprise.prog.org/wp-content/uploads/ENT-Automated-Incident-Detection-FR-Jan-2022.pdf) reports that with many products, detection stops until the camera returns home. MnDOT reported that detection continues off preset but with more false positives. A Caltrans pilot review traced false alarms "primarily" to environmental conditions and to "the camera being moved out of the preset position for which calibration was performed." The practical effect is that detection is weakest exactly when an operator is looking at something, which is often when an incident is under way. ## Why does detection get worse at night and in bad weather? The [Caltrans report](https://rosap.ntl.bts.gov/view/dot/66173/dot_66173_DS1.pdf), summarizing earlier research, describes a tunnel monitoring system whose false alarm rate ranged from 48% to 80% depending on the camera, caused in roughly equal parts by static shadows, snow and rain, glare and other causes. Iowa DOT told the ENTERPRISE study that its false positives "typically" occur at night with low visibility, and the same study notes that vision-based systems will not detect anything if it is completely dark. A system evaluated on daytime footage in clear weather has only been tested on its easiest hours. Ask for results by condition. ## Why does detection time matter so much? Detection is the first stage of traffic incident management. The [FHWA Freeway Management and Operations Handbook](https://ops.fhwa.dot.gov/freewaymgmt/publications/frwy_mgmt_handbook/chapter10.htm) lists it ahead of verification, motorist information, response, site management, traffic management, clearance and recovery. Every later stage waits on it. FHWA has estimated that [traffic incidents cause about a quarter of all congestion](https://ops.fhwa.dot.gov/program_areas/reduce-non-cong.htm), a figure that dates from the mid-2000s. Research on secondary crashes points the same way. A 2025 analysis for [The Eastern Transportation Coalition](https://tetcoalition.org/wp-content/uploads/2026/01/Secondary-Crash-Factors_Final.pdf) found that incident duration has its strongest effect on secondary crash odds in the first ten minutes, which is the window where faster detection counts most. ## How should you test an AID system before you buy it? Ask for detection rate, false alarm rate and time to detect, measured on your cameras, with the FAR definition stated. Then test each blind spot directly: 1. Move a PTZ camera during the pilot and watch what detection does while it's away and after it returns. 2. Run through nights, rain and low sun, and report results by condition rather than as one average. 3. Include quiet overnight periods, when a stopped vehicle causes no queue. 4. Count the alerts operators dismissed, not only the incidents caught. ## ![Four tests for an AID pilot: move a PTZ camera, run through night, rain and low sun, include quiet overnight periods, and count dismissed alerts. Ask for DR, FAR and MTTD on your own cameras.](https://blog.goodvisionlive.com/hs-fs/hubfs/03-pilot-checklist.png?width=1600&height=900&name=03-pilot-checklist.png) ## How does GoodVision handle these gaps? GoodVision Live Traffic runs on the cameras an agency already owns. When an operator moves a PTZ camera, it pauses analytics while the camera is off position and recalibrates automatically when the camera returns to its preset, with no manual reset. It detects wrong-way driving, stopped vehicles in the travel lane and on the shoulder, and congestion as it builds and propagates along a corridor. Between cameras, it infers flow-affecting incidents from how traffic behaves at the neighboring monitoring points. That works where the points are close enough that a change at one shows up at the next. Where they sit further apart, the inference tells you a segment is affected rather than pinpointing a location, and in-view detection is what gives you a classified event with visual evidence. We size this per corridor during the pilot. Every event is cross-checked against surrounding traffic conditions before it reaches an operator, so transient anomalies are filtered out and only verified, prioritized events surface. Events route into the agency's existing ATMS and dashboards rather than another screen. More detail is on the [automatic incident detection solution page](https://goodvisionlive.com/solutions/aid/). Want to see how detection holds up on your own cameras, including at night and with PTZ in use? [Request a demo](https://goodvisionlive.com/request-demo/). [![Request a demo of GoodVision Live Traffic to see how automatic incident detection holds up on your own cameras, including at night and with PTZ in use.](https://blog.goodvisionlive.com/hs-fs/hubfs/04-request-demo-banner-1.png?width=759&height=213&name=04-request-demo-banner-1.png)](https://goodvisionlive.com/request-demo/)   [Back to Blog](https://blog.goodvisionlive.com) ## Related Articles ## [In-Camera, Edge or Server: Where Should Your Traffic Analytics Actually Run](https://blog.goodvisionlive.com/in-camera-edge-or-server-where-should-your-traffic-analytics) Summary Traffic analytics deployment options fall into three topologies: in-camera processing on... [Read More](https://blog.goodvisionlive.com/in-camera-edge-or-server-where-should-your-traffic-analytics) ## [Automatic Incident Detection Beyond a Single Camera View](https://blog.goodvisionlive.com/automatic-incident-detection-beyond-single-camera-view) TL;DR Per-camera detection has converged. Every camera-based incident detection system shares one... [Read More](https://blog.goodvisionlive.com/automatic-incident-detection-beyond-single-camera-view) ## [6 Cities That Got Traffic Control Right, and What Made the Difference](https://blog.goodvisionlive.com/6-smart-cities-that-get-traffic-control-right) London, Stockholm, Singapore, Pittsburgh, San Francisco and Los Angeles all reduced congestion... [Read More](https://blog.goodvisionlive.com/6-smart-cities-that-get-traffic-control-right) ##### Subscribe to our Newsletter Get latest updates and news about GoodVision directly to your inbox Subscribe [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/LOGO-WITH-TITLE_R.png?width=284&height=48&name=LOGO-WITH-TITLE_R.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) ###### Products - [GoodVision Video Insights](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) ###### Company - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) ###### Resources - [Blog](https://blog.goodvisionlive.com/) - [Case Studies](https://casestudies.goodvisionlive.com/) - [Webinars](https://goodvisionlive.com/webinars/) Copyright © 2026 GoodVision Ltd. All rights reserved [Privacy Policy](https://goodvisionlive.com/privacy-policy) [Terms of Service](https://goodvisionlive.com/terms-of-service) - - - - ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Tomas Bui", "url" : "https://blog.goodvisionlive.com/author/tomas-bui" }, "dateModified" : "2026-10-02T12:01:52.650Z", "datePublished" : "2026-10-02T12:01:52.000Z", "headline" : "What Automatic Incident Detection Misses, and Why", "image" : [ "https://blog.goodvisionlive.com/hubfs/12_aid-blog-header-1.png" ], "mainEntityOfPage" : { "@id" : "https://blog.goodvisionlive.com/what-automatic-incident-detection-misses", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://blog.goodvisionlive.com/hubfs/aas-1.png" }, "name" : "GoodVision Ltd" } } ``` ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Organization", "name" : "GoodVision", "url" : "https://www.goodvisionlive.com" }, "dateModified" : "2026-10-01T08:00:00Z", "datePublished" : "2026-10-01T08:00:00Z", "description" : "What automatic incident detection misses, according to Caltrans and multi-state DOT evaluations: sensor gaps, PTZ, night, weather and false alarms.", "headline" : "What Automatic Incident Detection Misses, and Why", "image" : "https://20473359.fs1.hubspotusercontent-na1.net/hubfs/20473359/GoodVision_logo_full_GREEN.png", "mainEntityOfPage" : { "@id" : "https://blog.goodvisionlive.com/what-automatic-incident-detection-misses", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://20473359.fs1.hubspotusercontent-na1.net/hubfs/20473359/GoodVision_logo_full_GREEN.png" }, "name" : "GoodVision", "url" : "https://www.goodvisionlive.com" }, "url" : "https://blog.goodvisionlive.com/what-automatic-incident-detection-misses" } ```