SquintPRO · Ports and terminals
Video analytics for port gates and container yards, on the cameras already there
At a terminal gate and in the yard, trucks, handling equipment and people on foot share the same space, and the CCTV that covers them is rarely watched in full. SquintPRO turns those cameras into events a supervisor can act on: a person in a truck lane, someone too close to moving equipment, a vehicle where vehicles should not be, a missing helmet or vest. It is already deployed at a port, on container and gate operations.
Published 6 min read
The short answer
- What it watches: people, vehicles and protective equipment in the zones you define at gates, lanes and yard blocks.
- What it produces: events with the camera, time, zone and a video clip, a review step, and counts per zone and shift.
- What it does not do: run the gate or replace your gate and yard systems. It adds evidence from the cameras to the way your supervisors and HSE team already work.
- How to start: one gate or one yard block, one or two detections, and success criteria written down before go-live.
Why gates and yards are hard to supervise
Regulators' port-safety guidance stresses separation: keeping pedestrians out of areas where vehicles operate, giving them separate routes, and keeping people out of the danger zone when equipment such as a crane moves. Each terminal adds its own rules on top, for example where drivers may wait and what protective equipment is worn in operational areas.
The rules are written down. Checking them is the hard part. A gate runs around the clock, a yard covers a large area, and a supervisor sees only the part in front of them. Cameras cover far more of it, but a control room cannot watch every screen, so footage is usually opened only after something has already gone wrong.
What SquintPRO can watch for at gates and in yards
Each row is a detection the terminal sets up for its own layout: where it applies, at which times, and who is told. The third column is what to check on your cameras before relying on it.
| Situation at the gate or in the yard | What SquintPRO does | Check before relying on it |
|---|---|---|
| A person on foot in a truck lane, a stacking area or another zone closed to pedestrians | Detects entry into the restricted zone and raises an event | Mark where walking is allowed, such as walkways and driver waiting spots, so routine movement is not flagged |
| A person too close to handling equipment while it moves | Detects unsafe proximity to moving equipment | The camera must see both the person and the machine at a usable distance and angle |
| A vehicle in an area where vehicles should not be | Detects the vehicle in the restricted area | Decide which vehicles are allowed where, and at which times |
| A worker without a helmet or high-visibility vest in an operational area | Detects the missing equipment | Helmets are large and high-contrast, which makes them a good starting point. Vests are designed to be conspicuous but are harder to see when faded, dirty or covered by other layers |
| A situation specific to your terminal, such as an object in a truck lane | Lets your team define the event in text or with a reference image, without a model-retraining project | Run it on your own cameras for a period before it alerts anyone |
Finding out what happened after an incident
When something has already happened, the question changes from "alert me" to "show me". SquintPRO lets your team search the footage it analyses by typing a description, such as "red truck in the last three hours", or by supplying a reference photo of a truck. SquintPRO returns the matching clips, each with its camera and time, and a person confirms which ones matter.
Once the truck or the person has been found on one camera, cross-camera tracking, placed on a map of the terminal (GIS), helps follow where it went next across the other cameras. Search covers only the cameras connected to SquintPRO, and only footage still inside the deployment's retention period.
What the gate, yard and HSE teams receive
- An event for each detection, logged with its time, camera, zone and event type, with a video clip as evidence.
- A review step, so a person confirms or dismisses each event before it feeds a report or an investigation.
- Alerts in the tools the teams already use. Interkey connects SquintPRO to the terminal's video management, control-room and incident workflow during deployment.
- Counts per zone and shift, so supervisors can see which lane, gate or block keeps producing the same event.
Before you start: what the terminal needs to decide
- Where to start. One gate or one yard block, and the one or two detections that matter most there.
- A written rule for each detection. Where it applies, when, what counts as an event and what does not, for example a driver standing in the designated spot beside the cab.
- Camera coverage. A camera survey shows which existing cameras can be used as they are, which need adjusting, and where coverage is missing. Height, distance, night lighting, glare and dust all affect what a camera can see in a yard.
- Who receives what. Gate supervisor, yard supervisor, HSE or the control room, and what each is expected to do with an alert.
- The systems already running at the gate. List them during scoping, so it is clear what SquintPRO connects to and what stays as it is.
- Where processing runs. SquintPRO can run on the terminal's premises, where the footage does not leave the site, or in the cloud with 3, 6 or 12 months of retention chosen at setup.
- People and privacy. Drivers, contractors and staff all appear on gate and yard cameras. Decide with your legal and HSE owners who may view events and run searches, how long records are kept, and how the workforce is told. Detection records can be kept without retaining continuous footage. Teams that see monitoring as surveillance tend to work around it, so introduce it as a tool for rules everyone already follows.
How a first deployment is measured
Agree the success criteria in writing before anything is switched on, including how many false alerts per shift your supervisors can accept. Then measure over a period that covers day and night shifts:
- Confirmed events as a share of all alerts, to see how much of the alert volume is useful;
- Missed events, found by a person reviewing a sample of footage independently;
- Alerts per shift, against the number your supervisors agreed they can act on;
- What happened after each confirmed event, to check that alerts lead to action and not just to a log.
Ask for the pilot to be priced separately from a rollout, so the decision to continue rests on the results. At the end, decide in writing whether to extend, adjust or stop.
SquintPRO at ports today
SquintPRO is Interkey's own video-analytics platform. Interkey's team surveys the cameras, connects SquintPRO to the site's systems, configures the zones and detections, and tunes them after go-live.
It is deployed at a port on container and gate operations, on energy and smart-city sites, and in Interkey's own assembly facility in Riyadh. The platform includes 35 trained detection libraries across 12 core use-case categories, and 73 configurable metrics and alerts. It is priced by quote, according to the site, the number of cameras and the use cases in scope.
Questions buyers ask
Do we need new cameras?
Usually not. SquintPRO is designed to work with an existing CCTV estate. The survey shows which cameras can be used as they are, which need adjusting, and where an additional camera is needed for a particular detection.
Can the footage stay inside the terminal?
Yes. In an on-premise deployment the analysis runs on your infrastructure and the footage does not leave the site.
Does it replace our gate or yard systems?
No. SquintPRO works from the cameras and sends events into the workflow your teams already use. Which systems it connects to is settled during scoping.
Does it decide who is at fault?
No. It produces events with video evidence. A person reviews them, and decisions stay with your supervisors and HSE team.
How is it priced?
By quote, according to the site, the number of cameras and the use cases in scope. The deployment model, any camera work and the depth of integration also shape the quote.
Can we add a detection later?
Yes. A new event can be defined in text or with a reference image, then tested on your own cameras before it alerts anyone.
Next
Related
Next step
Start with one gate or yard block
Tell us which gate, lane or yard area you would start with, roughly how many cameras cover it, and the situations that concern your team most. We will come back with a first view of camera suitability and a pilot scope with written measures.
Or directly
+966-11-2180999 [email protected]Tawuniya Towers, North Tower, 7th Floor, King Fahad Highway, Olaya, P.O. Box 56835, Riyadh 11564, Saudi Arabia