{"id":15650762,"url":"https://github.com/robmarkcole/hass-sighthound","last_synced_at":"2026-03-10T05:31:45.546Z","repository":{"id":42216509,"uuid":"137716691","full_name":"robmarkcole/HASS-Sighthound","owner":"robmarkcole","description":"Beta features for Home Assistant Sighthound integration","archived":false,"fork":false,"pushed_at":"2022-07-05T04:19:14.000Z","size":3242,"stargazers_count":36,"open_issues_count":6,"forks_count":10,"subscribers_count":5,"default_branch":"master","last_synced_at":"2026-02-26T23:54:04.097Z","etag":null,"topics":["computer-vision","home-assistant"],"latest_commit_sha":null,"homepage":"https://www.home-assistant.io/integrations/sighthound/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/robmarkcole.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"github":"robmarkcole"}},"created_at":"2018-06-18T06:21:32.000Z","updated_at":"2025-06-10T10:03:05.000Z","dependencies_parsed_at":"2022-08-12T09:50:39.630Z","dependency_job_id":null,"html_url":"https://github.com/robmarkcole/HASS-Sighthound","commit_stats":null,"previous_names":[],"tags_count":14,"template":false,"template_full_name":null,"purl":"pkg:github/robmarkcole/HASS-Sighthound","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2FHASS-Sighthound","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2FHASS-Sighthound/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2FHASS-Sighthound/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2FHASS-Sighthound/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/robmarkcole","download_url":"https://codeload.github.com/robmarkcole/HASS-Sighthound/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/robmarkcole%2FHASS-Sighthound/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30326068,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","home-assistant"],"created_at":"2024-10-03T12:35:46.661Z","updated_at":"2026-03-10T05:31:45.514Z","avatar_url":"https://github.com/robmarkcole.png","language":"Python","funding_links":["https://github.com/sponsors/robmarkcole"],"categories":[],"sub_categories":[],"readme":"This repo contains beta features there are destined for the [official integration for Sighthound](https://www.home-assistant.io/integrations/sighthound/).\n\n# HASS-Sighthound\n[Home Assistant](https://www.home-assistant.io/) custom integration for people \u0026 vehicle detection (with numberplate) using [Sighthound Cloud](https://www.sighthound.com/products/cloud). To use Sighthound Cloud you must register with Sighthound to get an api key. The Sighthound Developer tier (free for non-commercial use) allows 5000 requests per month. If you need more requests per month you will need to sign up for a production account (i.e. Basic or Pro account).\n\nThis component adds a pair of image processing entities - one for person detection and one for vehicle detection. The state of the entity is the number of people/vehicles detected in an image.\n\nIf `save_file_folder` is configured, on each new detection an annotated image with the name `sighthound_latest.jpg` is saved in the configured folder if it doesn't already exist, and over-written if it does exist. The `sighthound_latest.jpg` image shows the bounding box around detected people/vehicles and can be displayed on the Home Assistant front end using a local_file camera, and used in notifications. Additionally, if `save_timestamped_file` is configured as `True` then an image file is created of the processed image, where the file name includes the time of detection.\n\nFor each person detected, an `sighthound.person_detected` event is fired. The event data includes the `entity_id` of the image processing entity firing the event, and the bounding box around the detected person. For each vehicle detected, an `sighthound.vehicle_detected` event is fired, with example data below:\n\n```\n{\n\"event_type\": \"sighthound.vehicle_detected\",\n\"data\": {\n    \"entity_id\": \"image_processing.sighthound_vehicle_local_file_1\",\n    \"plate\": \"CV67CBU\",\n    \"vehicle_type\": \"car\",\n    \"make\": \"Ford\",\n    \"model\": \"Ranger\",\n    \"color\": \"black\",\n    \"region\": \"UK\"\n}\n```\n\n**Note** that in order to prevent accidentally using up your requests to Sighthound, by default the component will **not** automatically scan images, but requires you to call the `image_processing.scan` service e.g. using an automation triggered by motion.\n\nPlace the `custom_components` folder in your configuration directory (or add its contents to an existing `custom_components` folder). Add to your Home-Assistant config:\n\n```yaml\nimage_processing:\n  - platform: sighthound\n    api_key: your_api_key\n    save_file_folder: /config/www/\n    save_timestamped_file: True\n    always_save_latest_jpg: True\n    source:\n      - entity_id: camera.local_file\n```\n\nConfiguration variables:\n- **api_key**: Your developer api key.\n- **account_type**: (Optional, default `dev` for Developer) If you have a paid account, used `prod`.\n- **save_file_folder**: (Optional) The folder to save processed images to. Note that folder path should be added to [whitelist_external_dirs](https://www.home-assistant.io/docs/configuration/basic/)\n- **save_timestamped_file**: (Optional, default `False`, requires `save_file_folder` to be configured) Save the processed image with the time of detection in the filename.\n- **always_save_latest_jpg**: (Optional, default `False`, requires `save_file_folder` to be configured) Always save the last processed image, no matter there were detections or not.\n- **source**: Must be a camera.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://github.com/robmarkcole/HASS-Sighthound/blob/master/images/usage.png\" width=\"500\"\u003e\n\u003c/p\u003e\n\n## Displaying the `sighthound_latest.jpg` image\nIt is easy to display the `sighthound_latest.jpg` image with a [local_file](https://www.home-assistant.io/integrations/local_file) camera. An example configuration is:\n\n```yaml\ncamera:\n  - platform: local_file\n    file_path: /config/www/sighthound_latest.jpg\n    name: sighthound\n```\n\n## Count people using the `sighthound.person_detected` event\nUsing a [counter](https://www.home-assistant.io/integrations/counter) an automation can be used to count the number of people seen. In `configuration.yaml`:\n\n```yaml\ncounter:\n  people_counter:\n    name: People\n    icon: mdi:alert\n```\n\nIn `automations.yaml`:\n```yaml\n- id: 'peoplecounterautomation'\n  alias: People Counting Automation\n  trigger:\n    platform: event\n    event_type: sighthound.person_detected\n    event_data:\n      entity_id: image_processing.sighthound_local_file\n  action:\n    service: counter.increment\n    entity_id: counter.people_counter\n```\n\nThe counter is incremented each time a person is detected. The bounding box can in principle be used to include/exclude people based on their location in the image. TODO: add example of using bounding box.\n\n## Info on the bounding box\nThe bounding boxes are formatted to be consumed by the `image_processing.draw_box()` function. The formatting convention is [identical](https://www.tensorflow.org/api_docs/python/tf/image/draw_bounding_boxes) to that used by Tensorflow, where the bounding box is defined by the tuple `(y_min, x_min, y_max, x_max)` where the coordinates are floats in the range `[0.0, 1.0]` and relative to the width and height of the image.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fhass-sighthound","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frobmarkcole%2Fhass-sighthound","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fhass-sighthound/lists"}