administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-08-03 17:43:59 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
3,919 Commits 87 Branches 159 Tags
b18d1fb9709a3d2585c3c3a7c47496bf37d29ca2
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Nicolas MowenandGitHub b18d1fb970 Refactor face recognition (#17368) 
* Refactor face recognition to allow for running lbph or embedding

* Cleanup

* Use weighted average for faces

* Set correct url

* Cleanup

* Update docs

* Update docs

* Use scipy trimmed mean

* Normalize

* Handle color and gray landmark detection

* Upgrade to new arcface model

* Implement sigmoid function

* Rename

* Rename to arcface

* Fix

* Add face recognition model size to ui config

* Update toast
 2025-03-25 19:59:03 -05:00
Nicolas MowenandGitHub 7e8b3c389d Update face_recognition.md (#17349) 2025-03-24 18:31:32 -05:00
Nicolas MowenandGitHub eabc316c7b Various fixes (#17342) 
* Remove imutils

* Ensure that state is maintained when setting search params

* Change script for version of setuptools

* Fix

* Fix
 2025-03-24 12:25:36 -05:00
Nicolas MowenandGitHub c239721021 Ensure thumb camera directory exists before saving (#17339) 2025-03-24 09:39:51 -05:00
Nicolas MowenandGitHub a8fa77c6b9 Classification fixes (#17337) 
* Cleanup classification settings behavior

* Cleanup response

* restore
 2025-03-24 09:12:42 -05:00
Nicolas MowenandGitHub 18af06237c Support RF-DETR models with OpenVINO (#17321) 
* Add support for openvino to run rf-detr models

* Add more inference time examples

* organize

* Add example to docs

* Add support for yolo generic
 2025-03-23 14:02:16 -06:00
Nicolas MowenandGitHub 17e14cefd9 Various fixes & tweaks (#17308) 
* Catch case where returned face box is invalid

* Update detector docs

* Add note for customizing rfdetr resolution
 2025-03-22 13:58:27 -05:00
Nicolas MowenandGitHub 48e4c44b32 Add support for RF-DETR models (#17298) 
* Add support for rf-detr models

* Add docs for rf-detr model

* Cleanup
 2025-03-21 19:55:46 -05:00
Nicolas MowenandGitHub 4e83237d47 Sub label snapshot (#17296) 
* Publish sub label for logos

* Cleanup check
 2025-03-21 17:37:09 -05:00
Nicolas MowenandGitHub 08cf0def6e Face tweaks (#17290) 
* Ensure doesn't fail due to missing dir

* Remove redundant settings from tabs

* Adjust selection method for mobile

* Fix button descendent error

* Ensure train is option on mobile

* Cleanup face images

* Cleanup
 2025-03-21 12:47:32 -05:00
Nicolas MowenandGitHub 060659044e Quick fixes (#17278) 
* Fix check

* Fix default loading state
 2025-03-20 15:09:57 -05:00
Nicolas MowenandGitHub e396043f79 Don't log go2rtc failure when camera is disabled (#17277) 2025-03-20 13:38:18 -05:00
Nicolas MowenandGitHub 0308a88111 Add MQTT topic to expose current camera review status (#17276) 
* Add MQTT topic to expose current camera review status

* Formatting
 2025-03-20 10:51:08 -06:00
Nicolas MowenandGitHub d4d5c4aac8 Disabled cameras fixing (#17273) 
* Fix case where objects are returned as null

* Fix enabled status not being persisted

* Use config as source of truth when refreshed

* Ensure camera always have config object updated

* Cleanup typing
 2025-03-20 11:20:44 -05:00
Nicolas MowenandGitHub d84fd324b2 Actually set the configured face and lpr settings (#17272) 2025-03-20 07:48:50 -06:00
Nicolas MowenandGitHub e7c6b2d571 Fix per camera config (#17263) 
* Fix per camera config

* fix
 2025-03-19 21:52:55 -05:00
Nicolas MowenandGitHub a7704a369d Update reviews state when sub label is set (#17262) 2025-03-19 20:55:57 -05:00
Nicolas MowenandGitHub f4284023fd Remove leadingn / (#17258) 2025-03-19 14:19:17 -06:00
Nicolas MowenandGitHub ce43b7b3d9 Add per-camera face and lpr configs (#17235) 
* Add per-camera face and lpr configs

* Formatting

* Cleanup
 2025-03-19 09:02:40 -06:00
Nicolas MowenandGitHub e33fa96599 Face recognize api (#17233) 
* Add api to run face recognition on image

* Rework save attempts option

* Cleanup mobile object pane buttons

* Adjust api signature

* Remove param

* Cleanup
 2025-03-19 09:02:25 -06:00
Nicolas MowenandGitHub 5514fc11b9 Face tweaks (#17225) 
* Always use white text

* Add right click as well

* Add face details dialog

* Clenaup
 2025-03-18 09:32:15 -05:00
Nicolas MowenandGitHub bf22d89f67 Improve Face Library Management (#17213) 
* Set maximum number of face images to be kept

* Fix vertical camera scaling

* adjust wording

* Add attributes to search data

* Add button to train face from event

* Handle event id saving in API
 2025-03-17 16:57:46 -05:00
Nicolas MowenandGitHub ff8e145b90 Face setup wizard (#17203) 
* Fix login page

* Increase face image size and add time ago

* Add component for indicating steps in a wizard

* Split out form inputs from dialog

* Add wizard for adding new face to library

* Simplify dialog

* Translations

* Fix scaling bug

* Fix key missing

* Improve multi select

* Adjust wording and spacing

* Add tip for face training

* Fix padding

* Remove text for buttons on mobile
 2025-03-17 13:50:13 -06:00
Nicolas MowenandGitHub 95e141ed15 Improve face detection (#17202) 2025-03-17 08:05:53 -06:00
Nicolas MowenandGitHub db541abed4 Fix model errors (#17171) 2025-03-16 06:01:15 -05:00
Nicolas MowenandGitHub 19342c8768 Fix face library menu item (#17155) 2025-03-14 14:39:48 -05:00
Nicolas MowenGitHubJosh Hawkins
 		a995872d1c Add face recognition and license plate recognition to settings UI (#17152) 
* Refactor explore settings to classification settings

* Cleanup

* Add face config section

* Add license plate recognition to settings

* Update face recognition docs

* Fix variable usage

* Fix typo

* Update docs/docs/configuration/face_recognition.md

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>

* Improve spacing and add face library to mobile

* Clarify docs

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
 2025-03-14 11:23:37 -05:00
Nicolas MowenandGitHub 2313b8ea05 Fix bug where safari and firefox cache image for too long (#17148) 2025-03-14 08:48:16 -05:00
Nicolas MowenandGitHub fbd22c8124 Cleanup bird classification (#17146) 
* Cleanup bird classification

* Cleanup
 2025-03-14 07:21:50 -06:00
Nicolas MowenandGitHub 759d963a04 Cleanup typing (#17145) 2025-03-14 08:10:47 -05:00
Nicolas MowenandGitHub 8d05e7c5b9 Make detection threhsold configurable (#17136) 2025-03-13 12:22:14 -05:00
Nicolas MowenandGitHub b8f2d8fb0c Fix rtsp config access (#17129) 2025-03-12 21:23:06 -05:00
Nicolas MowenandGitHub b7333557a1 Enable audio by default (#17125) 
* Remove mp4 query, allowing go2rtc to send any audio

* Add audio transcoding by default
 2025-03-12 16:54:28 -05:00
Nicolas MowenandGitHub 9e70bddc9d Update go2rtc version (#17119) 2025-03-12 13:54:20 -05:00
Nicolas MowenandGitHub f305ff3a5a Update hardware recommendation (#17111) 
* Update hardware recommendation

* re-organize information

* Broaden introduction

* Update index.md

* Update hardware.md

* Update hardware.md

* Update hardware.md

* Update index.md

* Update index.md

* Update hardware.md
 2025-03-12 08:58:07 -05:00
Nicolas MowenandGitHub b3d5cd9e4b Refactor manual event api to use ZMQ (#17105) 
* Don't wait for topic

* Refactor object processing and camera state

* Move manual event handling to camera state / tracked object

* Cleanup

* Refactor audio to use internal zmq

* Cleanup

* Clenaup

* Cleanup

* Quick label fix

* Fix tests

* Cleanup
 2025-03-11 22:31:05 -05:00
Nicolas MowenandGitHub 300f85720c Face blur factor (#17099) 
* Add option to apply factor to face blurring

* Adjust blur factors

* Add debug log
 2025-03-11 14:18:43 -05:00
Nicolas MowenandGitHub c43092da9a Add self return for pydantic (#17091) 2025-03-11 07:57:00 -05:00
Nicolas MowenandGitHub 0cc5d66e5b Refactor sub label api (#17079) 
* Use event metadata updater to handle sub label operations

* Use event metadata publisher for sub label setting

* Formatting

* fix tests

* Cleanup
 2025-03-10 16:29:29 -06:00
Nicolas MowenandGitHub 7d44970f78 Face multi select (#17068) 
* Implement multi select for face library

* Clear list of selected

* Add keyboard shortcut
 2025-03-10 10:01:52 -05:00
Nicolas MowenandGitHub 6f9d9cd5a8 Fix yolov9 link (#17007) 2025-03-07 08:50:04 -06:00
Nicolas MowenandGitHub 09705fd1b4 Update python deps (#17006) 2025-03-07 06:54:53 -07:00
Nicolas MowenandGitHub 433da8ffce Update web deps (#16983) 
* Update vite

* Update LuIcons

* Update radix packages

* Fix other icons

* Use correct node version

* Remove superfluous web build on python tests

* Move web build to test
 2025-03-06 10:50:37 -06:00
Nicolas MowenandGitHub 30acd26898 Disable detection by default (#16980) 
* Enable detection by default

* Migrate config to have detect enabled if it is not
 2025-03-06 08:00:29 -06:00
Nicolas MowenandGitHub 66d5f4f3b8 Refactor enabled camera listeners (#16979) 
* Monitor if camera is disabled for review items

* Simplify multi camera disabled check

* Cleanup birdseye config handling

* Cleanup

* Remove old listeners
 2025-03-06 07:59:35 -06:00
Nicolas MowenandGitHub 73c2c34127 Fix previews failing when disabled (#16962) 
* Fix previews failing when offline

* Simplify frame cache handling
 2025-03-05 08:07:48 -06:00
Nicolas MowenandGitHub 56079d080d Quick fix (#16926) 
* fix

* Fix

* Fix incorrect default websocket value

* Cleanup value setting
 2025-03-03 17:28:34 -06:00
Nicolas MowenandGitHub 2946c935ee Disabled camera output (#16920) 
* Fix live cameras not showing on refresh

* Fix live dashboard when birdseye is added

* Handle cameras that are offline / disabled

* Use black instead of green frame

* Fix missing mqtt topics
 2025-03-03 15:05:49 -06:00
Nicolas MowenandGitHub 71e6e04d77 Remove rocm detector (#16913) 
* Remove rocm detector plugin

* Update docs to recommend using onnx for rocm

* Formatting
 2025-03-03 08:16:14 -06:00
Nicolas MowenandGitHub 0128ec2ba6 Upgrade RocM to 6.3.3 (#16900) 
* Simplify rocm install and update to 6.3.1

* Build out more necessary packages

* Update to 6.3.3

* Set bake version

* Fix typo

* Ensure NHWC is used

* Reset dev changes

* Write to cache
 2025-03-02 21:46:46 -06:00
Nicolas MowenandGitHub b8f4cb5435 Fix docs (#16889) 2025-03-02 09:30:18 -07:00
Nicolas MowenandGitHub 4e03efaba9 Disable hailort log (#16888) 2025-03-02 09:26:59 -06:00
Nicolas MowenandGitHub f56668e467 Update d-fine documentation (#16881) 2025-03-01 17:09:41 -06:00
Nicolas MowenandGitHub 06d6e21de8 Fix cuda targetarch (#16869) 2025-02-28 14:48:08 -06:00
Nicolas MowenandGitHub db4152c4ca Fix jetson (#16854) 
* Fix jetson build

* Update ci.yml

* Update Dockerfile.base

* Update Dockerfile.base

* Update Dockerfile.base

* Fix

* Update ci.yml
 2025-02-27 17:24:03 -06:00
Nicolas MowenandGitHub 4f855f82ea Simplify tensorrt (#16835) 
* Remove unneccessary trt wheels build

* Cleanup

* Try without local cuda

* Keep specific cuda libs only

* Cleanup

* Add newer libcufft

* remove target

* Include more
 2025-02-26 14:39:19 -06:00
Nicolas MowenandGitHub 7eb3c87fa0 UI tweaks (#16813) 
* Add escape to close review details

* Refresh review page automatically if there are currently no items to review
 2025-02-25 19:17:39 -06:00
Nicolas MowenandGitHub 7ce1b354cc Use native arm runner for arm docker builds (#16804) 
* Try building jetpack on latest ubuntu version

* Update ci.yml

* run natively on arm

* Run all arm builds using arm runner

* Update ci.yml
 2025-02-25 11:02:56 -06:00
Nicolas MowenandGitHub 844ee089d8 Fix preview fetch (#16741) 2025-02-22 09:04:09 -06:00
Nicolas MowenandGitHub 6e8e88692c Fix coral dep (#16713) 2025-02-20 17:50:50 -07:00
Nicolas MowenandGitHub 391ac70e60 Fix nullable thumbnail (#16706) 2025-02-20 12:19:16 -06:00
Nicolas MowenandGitHub c736b1dae5 Refactor ONNX embedding class to use a base class and type-specific classes (#16703) 
* Move onnx runner

* Build out base embedding

* Convert text embedding to separate class

* Move image embedding to separate

* Move LPR to separate class

* Remove mono embedding

* Simplify model downloading

* Reorganize jina v1 embeddings

* Cleanup

* Cleanup for review
 2025-02-20 10:17:07 -06:00
Nicolas MowenandGitHub 649e5cfda5 Fix rockchip docker build (#16705) 2025-02-20 10:04:29 -06:00
Nicolas MowenandGitHub c7db0f479d Only match on exact config name in some cases (#16704) 
* Only match on exact config name in some cases

* Cleanup
 2025-02-20 10:04:06 -06:00
Nicolas MowenandGitHub 0f481546cd Fix build (#16683) 
* Add necessary tensorrt bindings

* Include both versions of cudnn

* Update Dockerfile
 2025-02-19 05:54:02 -07:00
Nicolas MowenandGitHub ab797c95af Remove jp4 build and add notes for jp6 (#16670) 2025-02-18 12:20:35 -06:00
Nicolas MowenandGitHub c819961cc8 Update pull request template to suggest creating a discussion (#16669) 
* Update pull request template to suggest creating a discussion for large changes

* Update template

* Ignore github changes
 2025-02-18 10:17:18 -06:00
Nicolas MowenandGitHub 81b873dead Quick fixes (#16668) 
* Write thumbnails to disk on shutdown

* Update text on face library page
 2025-02-18 10:13:28 -06:00
Nicolas MowenandGitHub f49a8009ec Remove thumb from database field (#16647) 
* Remove thumbnail from dict

* Create thumbnail diectory

* Cleanup handling of tracked object images

* Make thumbnail optional

* Handle cases where thumbnail is used

* Expand options for thumbnail api

* Fix up the does not exist condition

* Remove absolute usages of thumbnails

* Write thumbnails for external events

* Reduce webp quality

* Use webp everywhere in frontend

* Formatting

* Always consider all events when re-indexing

* Add thumbnail deletion and cleanup path management

* Cleanup imports

* Rename def

* Don't save thumbnail for every object

* Correct event count

* Use correct function

* Include thumbnail in query

* Remove unused

* Fix requiring exception
 2025-02-18 07:46:29 -07:00
Nicolas MowenandGitHub 1e709f5b3f Update coral deps and remove unused pycoral (#16630) 2025-02-17 06:57:05 -07:00
Nicolas MowenandGitHub 7b7387a68c Update info for face recognition (#16629) 2025-02-17 07:38:29 -06:00
Nicolas MowenandGitHub 761c5109dc Update nvidia driver req (#16560) 2025-02-13 17:18:38 -06:00
Nicolas MowenandGitHub f7199f205f Update docs for pcie coral driver (#16548) 2025-02-13 11:00:34 -06:00
Nicolas MowenandGitHub 73fee6372b Remove obsolete event clip logic (#16504) 
* Remove obsolete event clip logic

* Formatting
 2025-02-11 15:16:10 -06:00
Nicolas MowenandGitHub 0f0b2687af Add support for YoloV9 to OpenVINO (#16495) 
* Add support for yolov9 to OpenVINO

* Cleanup detector docs

* Fix link
 2025-02-11 11:23:19 -07:00
Nicolas MowenandGitHub b594f198a9 Consolidate HailoRT into the main Docker Image (#16487) 
* Simplify main build to include hailo

* Update docs

* Remove hailo docker build
 2025-02-11 09:08:13 -07:00
Nicolas MowenandGitHub ac3dfbc30d Set stop event first (#16466) 2025-02-10 21:22:33 -06:00
Nicolas MowenandGitHub 198d067e25 Implement support for YOLOv9 via ONNX (#16459) 
* WIP yolov9

* Implement post processing for yolov9

* Cleanup detection

* Update docs to make note of supported yolov9

* Move post processing to separate utility

* Add note about other models
 2025-02-10 15:00:12 -06:00
Nicolas MowenandGitHub 81bd956ae8 Fix sanitized api causing issues (#16433) 2025-02-09 14:50:12 -07:00
Nicolas MowenandGitHub 81a56549da Face recognition UI improvements (#16422) 
* Rework face recognition APIs

* Fix error message on cancel

* Add ability to create new face library
 2025-02-09 13:22:25 -06:00
Nicolas MowenGitHubMitch Ross
 		c58d2add37 Fix missing prometheus commit (#16415) 
* Add prometheus metrics

* add docs for metrics

* sidebar

* lint

* lint

---------

Co-authored-by: Mitch Ross <mitchross@users.noreply.github.com>
 2025-02-09 10:04:39 -07:00
Nicolas MowenandGitHub a42ad7ead9 UI fixes (#16406) 
* Fix new review item banner blocking third chip

* Fix custom export mode
 2025-02-09 07:36:55 -06:00
Nicolas MowenandGitHub 973d3aed9a Disable jetson builds (#16396) 2025-02-08 17:20:58 -06:00
Nicolas MowenandGitHub fa300742ea Fix build (#16393) 
* Fix rpi build

* Attempt to fix jetson builds
 2025-02-08 14:51:42 -06:00
Nicolas MowenandBlake Blackshear 15472274ee Update docs sidebar name (#16370) 
* Clarify classification

* Fix face hierarchy as well
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear f3485bfc13 Sanitize provided name 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 060ad34e1d Update cudnn and onnxruntime (#16332) 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear fb316874ef Quick fix for face rec (#16226) 
* Check both

* Fix api order
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 9236898a9d Sub label sensors (#16218) 
* Support mqtt sensors for logo attributes

* Expose in api
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 1c3527f5c4 Face recognition reprocess (#16212) 
* Implement update topic

* Add API for reprocessing face

* Get reprocess working

* Fix crash when no faces exist

* Simplify
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 6f4002a56f Add training face library information to docs (#16169) 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 3f99ff65ed Face recognition improvements (#16034) 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear c7c8575c9b Bird classification (#15966) 
* Start working on bird processor

* Initial setup for bird processing

* Improvements to handling

* Get classification working

* Cleanup classification

* Add classification config

* Update sort
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 63dbcd79e2 Update hailo deps (#15958) 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 9dc85d4a76 Processing refactor (#15935) 
* Refactor post processor to be real time processor

* Build out generic API for post processing

* Cleanup

* Fix
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 88686c44fe Generalize postprocessing (#15931) 
* Actually send result to face registration

* Define postprocessing api and move face processing to fit

* Standardize request handling

* Standardize handling of processors

* Rename processing metrics

* Cleanup

* Standardize object end

* Update to newer formatting

* One more

* One more
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 3f1d85e189 Fix onvif packages (#15906) 
* Don't replace packages

* Formatting
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear ab8f9e5412 Upgrade onvif-zeep dependency to use onvif-zeep-async (#15894) 
* Upgrade to new dependency

* Start onvif work

* Update for async calls
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear 4f85b18b08 Improvements to face recognition (#15854) 
* Do not add margin to face images

* remove margin

* Correctly clear
 2025-02-08 12:47:01 -06:00
Nicolas MowenandBlake Blackshear a6ae208fe7 Add metrics page for embeddings and face / license plate processing times (#15818) 
* Get stats for embeddings inferences

* cleanup embeddings inferences

* Enable UI for feature metrics

* Change threshold

* Fix check

* Update python for actions

* Set python version

* Ignore type for now
 2025-02-08 12:47:01 -06:00