# AI use cases for Lotvulture (lotvulture/lotvulture)

Repo: [lotvulture/lotvulture](https://github.com/lotvulture/lotvulture) | Use cases: 4 | Page: https://dedupedai.com/use-cases/lotvulture-lotvulture/

Lot Vulture is a source-available app that runs computer vision on existing IP or RTSP camera feeds to show live parking space occupancy.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Show live space-by-space occupancy from existing cameras: https://dedupedai.com/use-cases/lotvulture-lotvulture/live-lot-occupancy-dashboard/
- Push lot availability to road signs and Home Assistant: https://dedupedai.com/use-cases/lotvulture-lotvulture/push-availability-to-signs-and-home-assistant/
- Audit past lot use with the scrubbing timeline: https://dedupedai.com/use-cases/lotvulture-lotvulture/review-lot-utilization-history/
- Detect parking spaces in one image through the cloud API: https://dedupedai.com/use-cases/lotvulture-lotvulture/detect-spaces-in-one-image-via-cloud-api/

## How to show live space-by-space occupancy from existing cameras with Lotvulture

Repo: [lotvulture/lotvulture](https://github.com/lotvulture/lotvulture) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Turn existing lot cameras into a live occupancy map with per-space status updates.

**Who it is for:** A facilities manager or lot operator who needs to see which spaces are free right now and has cameras already covering the lot.

**The problem:** Attendants give delayed estimates, and in-ground sensors are costly to install and maintain.

**The outcome:** A browser dashboard at localhost:8000 that shows each drawn parking space as occupied or free, updating over WebSockets.

### Steps

1. Install Lot Vulture: on Windows, run the LotVulture_Setup_*.exe from the Releases page; on Linux, run `docker run -d --name lotvulture --restart unless-stopped -p 8000:8000 -v lotvulture-data:/var/lib/lotvulture ghcr.io/lotvulture/lotvulture:latest`. (inferred, check the README)
2. Open `http://localhost:8000` in a browser.
3. In the Cameras view, add each RTSP stream URL or snapshot endpoint.
4. Use the visual canvas editor to map the four corners of each parking space.
5. Open the live dashboard and confirm each mapped space shows a state.

### Prompt to paste into your agent

```text
Using the repo lotvulture/lotvulture, set up Lot Vulture with the Docker command from its README on a Linux host, then add the camera stream <camera_rtsp_url> in the Cameras view. Report the occupancy state of each mapped space shown on the live dashboard at http://localhost:8000, and verify that the states change when a vehicle enters or leaves a mapped space.
```

### Caveat

The Community Edition runs a bundled standard model on optimized CPU, and GPU acceleration and the high-accuracy model require a Commercial license.

Risk, credentials: Camera RTSP URLs often embed usernames and passwords, so store them only in the app and avoid pasting them into shared logs or agent chats.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lotvulture-lotvulture/live-lot-occupancy-dashboard/

## How to push lot availability to road signs and Home Assistant with Lotvulture

Repo: [lotvulture/lotvulture](https://github.com/lotvulture/lotvulture) | Difficulty: Intermediate | Time: 1.5 hours | Basis: From the README

Send capacity and space changes over MQTT to LED signage or Home Assistant automations.

**Who it is for:** A lot operator or smart-building integrator who has LED road signs or a Home Assistant setup and needs live availability to drive them.

**The problem:** Signs and automations cannot show lot availability without a live data source that reports capacity changes.

**The outcome:** MQTT messages fire on capacity thresholds or single-space transitions, and staff get notified when capacity hits a set level such as 95%.

### Steps

1. Complete the dashboard setup and confirm occupancy states appear on the live dashboard.
2. Open the alerting subsystem in the dashboard and create an MQTT alert.
3. Set the trigger to a lot capacity threshold, such as 95%, or to single space transitions.
4. Point the MQTT alert at your broker and topic that the sign or Home Assistant reads.
5. Trigger a test change by occupying or freeing a mapped space and confirm the message arrives.

### Prompt to paste into your agent

```text
For the repo lotvulture/lotvulture, configure an MQTT alert in the Lot Vulture dashboard that fires when lot capacity reaches 95 percent, targeting the broker at <mqtt_broker_address> and topic <topic_name>. Report the alert configuration you created and the message payload received, and verify that a test occupancy change produces exactly one message on the topic.
```

### Caveat

The README does not document the exact MQTT payload format or the alert setup menu, so check the dashboard and the Developer Guide before wiring it to a sign.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lotvulture-lotvulture/push-availability-to-signs-and-home-assistant/

## How to audit past lot use with the scrubbing timeline with Lotvulture

Repo: [lotvulture/lotvulture](https://github.com/lotvulture/lotvulture) | Difficulty: Beginner | Time: 1 hour | Basis: From the README

Replay past occupancy by second and open snapshots of each state change.

**Who it is for:** A parking manager reviewing a past incident, peak hours, or a dispute about how long a space was occupied.

**The problem:** Periodic manual audits give only estimates, so past utilization is hard to verify.

**The outcome:** A replayable record of space states across the day, with snapshots showing the exact frames of each transition.

### Steps

1. Open the dashboard at `http://localhost:8000` and go to the historical timeline view.
2. Scrub to the time window you need to review.
3. Click a parking space to see its state transitions.
4. Open the visual snapshot for each transition you need to verify.
5. Export or note the transition times you need for your audit record.

### Prompt to paste into your agent

```text
For the repo lotvulture/lotvulture running at http://localhost:8000, use the Visual Scrubbing History Timeline to list the occupancy transitions for space <space_name> between <start_time> and <end_time>. Return the transition times and states, and verify that each listed transition has a matching snapshot.
```

### Caveat

The README does not state how long history is retained or whether it can be exported, so confirm retention in the Developer Guide before relying on it for records.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lotvulture-lotvulture/review-lot-utilization-history/

## How to detect parking spaces in one image through the cloud API with Lotvulture

Repo: [lotvulture/lotvulture](https://github.com/lotvulture/lotvulture) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Send one lot photo to the Developer Cloud API and get space detections back.

**Who it is for:** A developer building a parking feature into their own app who does not want to run on-prem infrastructure.

**The problem:** Running the on-prem engine adds infrastructure work when only occasional detection is needed.

**The outcome:** Parking space detection results for a single image, billed per image.

### Steps

1. Get an API key from the Lot Vulture Developer Cloud API page at https://www.lotvulture.com/developer.html.
2. Prepare a lot image file, such as parking_lot.jpg, and the space polygon coordinates for each region.
3. Run `curl -X POST "https://api.lotvulture.com/v1/detect" -H "Authorization: Bearer YOUR_API_KEY" -F "image=@parking_lot.jpg" -F 'rois=[[[120,340],[250,340],[260,490],[110,490]]]'` and replace YOUR_API_KEY and the file name. (inferred, check the README)
4. Read the response and match each detection to its region.

### Prompt to paste into your agent

```text
Using the Lot Vulture Developer Cloud API described in the repo lotvulture/lotvulture README, send the image <image_path> with the region coordinates <rois_json> to https://api.lotvulture.com/v1/detect using the API key in the environment variable <api_key_env>. Report the detection result for each region and verify that the number of results equals the number of regions sent.
```

### Caveat

The README documents the API call and its per-image price but not its response format, so check the response shape against the live endpoint before parsing it.

Risk, credentials: The API key is billed per image at $0.02 each, so keep it in an environment variable or secret store and never commit it to a repo.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lotvulture-lotvulture/detect-spaces-in-one-image-via-cloud-api/