ConductVision Enterprise
ConductVision times the queues at entrances and screening lanes and, in a pilot, flags carried items on the venue's screening list for staff to review.
25 detectionsConductVision detections on this photo. Photo: Tony Webster, CC BY 2.0, cropped.
Weapon Detection identifies firearms, knives, and other threat objects in video feeds to support security operations. The system is designed with full transparency about its capabilities and limitations: detection rates vary by weapon type, concealment level, and environmental conditions. It is intended as a supplementary layer for trained security personnel, not a replacement. All detection thresholds are configurable, and false positive rates are reported openly so operators can tune sensitivity to their specific risk tolerance. The system is built for environments subject to security screening requirements.
Outcomes
Entrance screening slows at peak times, and queues spill out of the building.
Long waits frustrate visitors and pull staff from the lanes to manage the line.
Visitors with bags can reach the inside through side doors, staff entrances or a lane left open.
Each one is a gap in the screening the venue promised its visitors.
A camera flag helps only if a screener can check it in seconds.
Flags that take long to review hold up the lane or get waved through.
What the model sees
ConductVision detections on this photo. Photo: Edward Russell, CC BY 2.0, cropped.
ConductVision detections on this photo. Photo: Project Kei, CC BY-SA 4.0, cropped.
Endpoints
Each endpoint is defined before the pilot starts, with what is counted, its unit and how the results are broken down.
| Endpoint | How it is counted | Unit | Broken down by |
|---|---|---|---|
| PrimaryTime to staff review | Seconds from a flag reaching the screening team to a reviewer marking it cleared or sent for a bag check. | Unit:seconds (median) | By:Entrance, shift |
| SecondaryScreening wait | Minutes from a person joining a lane's queue zone to reaching the screening point. | Unit:minutes (median) | By:Lane, hour |
| Unscreened entries | People with bags who reach the inside without passing a screening lane, counted once per person. | Unit:entries per day | By:Door, hour |
| Flag rate | Screening flags raised per 1,000 people entering, counted before and after staff review. | Unit:flags per 1,000 entries | By:Entrance, item class |
Each pilot measures ConductVision on your own footage against a sample checked by hand, before anyone relies on its numbers.
Flag precision
Share of screening flags that a reviewer confirms as an item on the venue's list, in a hand-checked sample of clips.
% · by camera, item class
Test-pass detection
Share of planned test walk-throughs, with staff carrying sample items from the list, that ConductVision flagged.
% · by lane, item class, how the item is carried
False flags
Flags a reviewer rejects, such as umbrellas, tripods or phones, per lane per day.
flags per lane-day · by lane, item class
How it works
Connect
Position cameras at entry points, hallways, and open areas where weapons might be visible. The system works with existing surveillance infrastructure, no specialized cameras required.
Analyze
Detection models identify weapon-like objects and classify them by type (handgun, rifle, knife, blunt weapon). Confidence scores reflect the model's certainty, and detections below a configurable threshold are suppressed.
Act
Detections above the confidence threshold trigger alerts to security operations centers with a snapshot, camera location, and classification. Security personnel make all response decisions, the system never initiates autonomous actions.
What it detects
Person
Each person in the entrance view, tracked from the door to the lane
Backpack
Carried on the back or in hand, linked to the person carrying it
Handbag
Bags carried by hand or on the shoulder, linked to their carrier
Suitcase
Wheeled and hand-carried cases in the lane and the queue
Screening classes
Items on the venue's screening list, trained on its own footage in a pilot
Features
Use cases
Schools need additional security layers beyond access control. Weapon Detection can provide an alert to security staff when a firearm is visibly present, supplementing existing security measures.
educationgovernment
Large campuses with multiple entry points cannot station security personnel everywhere. Camera-based detection can extend the coverage area that a security team effectively monitors.
corporate
Concert venues and stadiums use metal detectors at entry. Camera-based detection can add a visual screening layer at perimeters and common areas beyond the entry checkpoint.
eventshospitality
Transit agencies monitor thousands of cameras across stations and vehicles. Automated detection can highlight feeds that require immediate security attention, reducing operator fatigue.
transportationsmart city
Retail locations in high-risk areas benefit from an additional alert layer. Detection of weapons during robbery attempts can trigger silent alerts to law enforcement.
retail
Technical overview
Accuracy and speed are measured on your footage and cameras during the pilot, and reported with the conditions they were measured under.
Industries
Related
Counts and tracks people in each camera view, by zone and hour.
Tracks posture, waiting and movement from pose keypoints in public spaces.
Checks hard hats, vests, goggles, gloves and masks against each zone's rules.
Pilot
A pilot takes one prioritized outcome, runs on your cameras, reports the endpoints above and ends with a results review and a decision.
.jpg){kind=link}
