Product Overview
LILIN EDGECAP is an Edge AI software license for compatible LILIN smart IP cameras, enabling real-time people and vehicle counting directly on the camera. By processing analytics at the edge, it reduces server load and bandwidth use while supporting occupancy tracking, traffic analysis, retail visitor counting, and parking-area monitoring.
Key Configuration
Model: LILIN EDGECAP; product type: Edge AI software license; analytics function: human and vehicle counting; processing location: on-camera edge processing; object classes: people, cars, motorcycles, bicycles, and buses; detection setup: up to 4 polygon zones with 6 anchor points; confidence control: 0–100% adjustable; false-alarm reduction: up to 8 cold zones.
Key Features
• Counts people and vehicles directly on compatible LILIN smart IP cameras.
• Classifies humans, cars, motorcycles, bicycles, and buses for more useful analytics.
• Supports custom polygon detection zones and directional line-based flow counting.
• Adjustable confidence filtering helps tune detection accuracy for each scene.
• Edge-based AI processing reduces bandwidth demand and backend server workload.
Technical Context
EDGECAP is intended for deployments that need live counting data rather than simple motion events. The software can calculate people and vehicle statistics and send results to backend systems or LILIN NAV Recorders for storage, reporting, and business intelligence use.
Installation Notes
Install EDGECAP on a compatible LILIN smart IP camera and configure detection zones, direction rules, confidence thresholds, and cold zones according to the monitored scene. For best results, validate counting accuracy after installation and adjust the zone placement to avoid background movement, reflections, and non-relevant traffic paths.
| General | |
| Model | EDGECAP |
| Features | To manage and calculate the number of people and vehicles, and send the statistics to the backend server for storage and analysis. Data can be reset at specific times everyday. |
| Warranty | 1 Year |
| Object Support | |
| Supported Objects | Human in different postures: Stand, run, couch, move forward, crawl, climb, with hat, with umbrella, etc Vehicle Types: Bicycle, car, motorbike, airplane, bus, train, truck, tuktuk, trailer, pickup, fire engine, van, bulldozer, stacker, excavator, tanker |
| Results Display | Conditional display results according to specified objects. |
| Number of Detectable Objects | 24 objects per frame. |
| Counter Functions | |
| Counter Functions | Quantities:Up to 8 counters to count events are triggered by specified objects. Reset Value:To count from a reset value. Operand:Expressions such as +1, -1, and = can be used as the counter counting method. Intervals Reset:Intervals to reset the counter are: 1 minute, 5 minutes, 30 minutes, 1 hour, 1 day, 1 week, 1month, etc. Trigger Conditions:While running density detection, the number of objects (up to 300) can be set as the criteria to trigger events and start the counter. |
| Behaviors Detection | |
| Behaviors Detection | Density Detection Counter : Supports counting the number of specified objects in the detection area, if the number exceeds the set predefined number, the event will be triggered and counted Prohibited Zone Counter : Support triggering an event and count when specified object(s) enters restricted area Zone with Dwell / Parking Violation Counter : Support triggering an event and count when specified object(s) enters restricted area and stays for a predefined duration of time Tripwire / Traffic Flow Counter : Support triggering an event and count when specified object(s) crosses the designed line in a predefined direction Tampering Detection : Support triggering an event when the camera is blocked, redirected, or shaken All Object Detection (AND) Counter : Support triggering an event and count when all of the specified objects show up within the set detection zone at the same time (based on AND rule) Lack of any Object Detection (NAND) Counter : Support triggering an event and count when any of the specified objects is not present within the set detection zone (based on NAND rule) |
| Recognition | |
| Recognition Speed | Support object recognition speed up to 12 frames per second at 4K, 14 frames per second at 1080P, and 16 frames per second at 720P |
| Video Resolution | Supports 4K(3840 x 2160), 2MP(1920 x 1080) |
| Minimum Recognition Resolution | Vehicles: 60x60 pixels People: 60x100 pixels Motorcycles/Bicycles: 60x100 pixels Other specified objects: 120x120 pixels and above. |
| Objects Filtering | |
| Objects Filtering | Object Type:Supports recognize selected objects instead of processing all objects. Object Size:Supports 0~100% of objects’ size compared to the screen with size filter. Confidence Level:Support 0~100% adjustable confidence level. 0~100% adjustable confidence intervals. |
| Events | |
| Event Trigger | Support to set triggers by specified behaviors of certain objects. Up to 8 cold zones can be set to minimize false alarms and improve the accuracy. |
| Alarm Output | After an event is triggered by classified object, the alarm will be continually issued according to the set object dwell time (2~30 secs). |
| Heartbeat Checking | Support checking the camera AI operation status and pushing notifications every 1~30 minutes. |
| Detection Zone / Line | |
| Detection Zone / Line | Support setting 4 detection zones to trigger independent behaviors. |
| Polygon Area | The detection zone is a polygon that can be freely dragged and that the shape can be modified by 6 draggable anchor points. The detection line is a line attached to a polygon that the shape and position can be modified by 4 draggable anchor points. Also, direction of the line can be set by dragging the 4 anchor points or clicking the “Enable direction button”. |
| Pixels Calculation | To display the size of selected objects on the web UI. |
| Integration | |
| Alarm Output | Digital Output : Support triggering digital output of camera Smart Event : Support triggering up to 4 virtual inputs of camera HTTP POST : Support pushing counter values to third-party devices for integration Support displaying an alarm on LILIN IP LED Panel Support displaying an alarm on specific channel of LILIN Navigator VMS Support triggering digital outputs for LILIN I/O Box Support triggering digital outputs for LILIN NVR Support triggering HTTP POST to integrate with third-party devices Support triggering a PTZ camera to go to a preset |
| Recording System Integration | Support event search to playback or snapshot on LILIN NAV VMS and NVR. |
| Interface Language | Traditional Chinese, English, Japanese and Italian. |
| Camera supported | Z7/S7 |