Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2024-11-21 19:07:46 +01:00
Code Issues Projects Releases Wiki Activity

track and report all detected object types

Browse Source
This commit is contained in:
Blake Blackshear 2019-12-14 15:18:21 -06:00
parent 5c01720567
commit e1c4aa94f4
7 changed files with 160 additions and 131 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -55,20 +55,22 @@ Example docker-compose:
A `config.yml` file must exist in the `config` directory. See example [here](config/config.example.yml) and device specific info can be found [here](docs/DEVICES.md).
Access the mjpeg stream at `http://localhost:5000/<camera_name>` and the best person snapshot at `http://localhost:5000/<camera_name>/best_person.jpg`
Access the mjpeg stream at `http://localhost:5000/<camera_name>` and the best snapshot for any object type with at `http://localhost:5000/<camera_name>/<object_name>/best.jpg`
## Integration with HomeAssistant
```
camera:
- name: Camera Last Person
platform: mqtt
topic: frigate/<camera_name>/snapshot
topic: frigate/<camera_name>/person/snapshot
- name: Camera Last Car
platform: mqtt
topic: frigate/<camera_name>/car/snapshot
binary_sensor:
- name: Camera Person
platform: mqtt
state_topic: "frigate/<camera_name>/objects"
value_template: '{{ value_json.person }}'
state_topic: "frigate/<camera_name>/person"
device_class: motion
availability_topic: "frigate/available"
@ -89,7 +91,7 @@ automation:
message: "A person was detected."
data:
photo:
- url: http://<ip>:5000/<camera_name>/best_person.jpg
- url: http://<ip>:5000/<camera_name>/person/best.jpg
caption: A person was detected.
```

38
config/config.example.yml
View File

@ -45,7 +45,19 @@ mqtt:
# - rawvideo
# - -pix_fmt
# - rgb24
####################
# Global object configuration. Applies to all cameras and regions
# unless overridden at the camera/region levels.
# Keys must be valid labels. By default, the model uses coco (https://dl.google.com/coral/canned_models/coco_labels.txt).
# All labels from the model are reported over MQTT. These values are used to filter out false positives.
####################
objects:
person:
min_area: 5000
max_area: 100000
threshold: 0.5
cameras:
back:
ffmpeg:
@ -78,6 +90,12 @@ cameras:
# 3 every 3rd frame, etc.
################
take_frame: 1
objects:
person:
min_area: 5000
max_area: 100000
threshold: 0.5
################
# size: size of the region in pixels
@ -93,18 +111,18 @@ cameras:
- size: 350
x_offset: 0
y_offset: 300
min_person_area: 5000
max_person_area: 100000
threshold: 0.5
objects:
car:
threshold: 0.2
- size: 400
x_offset: 350
y_offset: 250
min_person_area: 2000
max_person_area: 100000
threshold: 0.5
objects:
person:
min_area: 2000
- size: 400
x_offset: 750
y_offset: 250
min_person_area: 2000
max_person_area: 100000
threshold: 0.5
objects:
person:
min_area: 2000

16
detect_objects.py
View File

@ -42,6 +42,8 @@ FFMPEG_DEFAULT_CONFIG = {
'-pix_fmt', 'rgb24'])
}
GLOBAL_OBJECT_CONFIG = CONFIG.get('objects', {})
WEB_PORT = CONFIG.get('web_port', 5000)
DEBUG = (CONFIG.get('debug', '0') == '1')
@ -74,7 +76,7 @@ def main():
cameras = {}
for name, config in CONFIG['cameras'].items():
cameras[name] = Camera(name, FFMPEG_DEFAULT_CONFIG, config, prepped_frame_queue, client, MQTT_TOPIC_PREFIX)
cameras[name] = Camera(name, FFMPEG_DEFAULT_CONFIG, GLOBAL_OBJECT_CONFIG, config, prepped_frame_queue, client, MQTT_TOPIC_PREFIX)
prepped_queue_processor = PreppedQueueProcessor(
cameras,
@ -94,13 +96,13 @@ def main():
# return a healh
return "Frigate is running. Alive and healthy!"
@app.route('/<camera_name>/best_person.jpg')
def best_person(camera_name):
@app.route('/<camera_name>/<label>/best.jpg')
def best(camera_name, label):
if camera_name in cameras:
best_person_frame = cameras[camera_name].get_best_person()
if best_person_frame is None:
best_person_frame = np.zeros((720,1280,3), np.uint8)
ret, jpg = cv2.imencode('.jpg', best_person_frame)
best_frame = cameras[camera_name].get_best(label)
if best_frame is None:
best_frame = np.zeros((720,1280,3), np.uint8)
ret, jpg = cv2.imencode('.jpg', best_frame)
response = make_response(jpg.tobytes())
response.headers['Content-Type'] = 'image/jpg'
return response

49
frigate/mqtt.py
View File

@ -1,41 +1,46 @@
import json
import cv2
import threading
from collections import Counter, defaultdict
class MqttObjectPublisher(threading.Thread):
def __init__(self, client, topic_prefix, objects_parsed, detected_objects, best_person_frame):
def __init__(self, client, topic_prefix, objects_parsed, detected_objects, best_frames):
threading.Thread.__init__(self)
self.client = client
self.topic_prefix = topic_prefix
self.objects_parsed = objects_parsed
self._detected_objects = detected_objects
self.best_person_frame = best_person_frame
self.best_frames = best_frames
def run(self):
last_sent_payload = ""
current_object_status = defaultdict(lambda: 'OFF')
while True:
# initialize the payload
payload = {}
# wait until objects have been parsed
with self.objects_parsed:
self.objects_parsed.wait()
# add all the person scores in detected objects
# make a copy of detected objects
detected_objects = self._detected_objects.copy()
person_score = sum([obj['score'] for obj in detected_objects if obj['name'] == 'person'])
# if the person score is more than 100, set person to ON
payload['person'] = 'ON' if int(person_score*100) > 100 else 'OFF'
# send message for objects if different
new_payload = json.dumps(payload, sort_keys=True)
if new_payload != last_sent_payload:
last_sent_payload = new_payload
self.client.publish(self.topic_prefix+'/objects', new_payload, retain=False)
# send the snapshot over mqtt as well
if not self.best_person_frame.best_frame is None:
ret, jpg = cv2.imencode('.jpg', self.best_person_frame.best_frame)
if ret:
jpg_bytes = jpg.tobytes()
self.client.publish(self.topic_prefix+'/snapshot', jpg_bytes, retain=True)
# total up all scores by object type
obj_counter = Counter()
for obj in detected_objects:
obj_counter[obj['name']] += obj['score']
# report on detected objects
for obj_name, total_score in obj_counter.items():
new_status = 'ON' if int(total_score*100) > 100 else 'OFF'
if new_status != current_object_status[obj_name]:
current_object_status[obj_name] = new_status
self.client.publish(self.topic_prefix+'/'+obj_name, new_status, retain=False)
# send the snapshot over mqtt as well
if not self.best_frames.best_frames[obj_name] is None:
ret, jpg = cv2.imencode('.jpg', self.best_frames.best_frames[obj_name])
if ret:
jpg_bytes = jpg.tobytes()
self.client.publish(self.topic_prefix+'/'+obj_name+'/snapshot', jpg_bytes, retain=True)
# expire any objects that are ON and no longer detected
expired_objects = [obj_name for obj_name, status in current_object_status.items() if status == 'ON' and not obj_name in obj_counter]
for obj_name in expired_objects:
self.client.publish(self.topic_prefix+'/'+obj_name, 'OFF', retain=False)

15
frigate/object_detection.py
View File

@ -38,21 +38,18 @@ class PreppedQueueProcessor(threading.Thread):
frame = self.prepped_frame_queue.get()
# Actual detection.
objects = self.engine.DetectWithInputTensor(frame['frame'], threshold=frame['region_threshold'], top_k=3)
objects = self.engine.DetectWithInputTensor(frame['frame'], threshold=0.5, top_k=5)
# print(self.engine.get_inference_time())
# parse and pass detected objects back to the camera
parsed_objects = []
for obj in objects:
box = obj.bounding_box.flatten().tolist()
parsed_objects.append({
'region_id': frame['region_id'],
'frame_time': frame['frame_time'],
'name': str(self.labels[obj.label_id]),
'score': float(obj.score),
'xmin': int((box[0] * frame['region_size']) + frame['region_x_offset']),
'ymin': int((box[1] * frame['region_size']) + frame['region_y_offset']),
'xmax': int((box[2] * frame['region_size']) + frame['region_x_offset']),
'ymax': int((box[3] * frame['region_size']) + frame['region_y_offset'])
'box': obj.bounding_box.flatten().tolist()
})
self.cameras[frame['camera_name']].add_objects(parsed_objects)
@ -61,7 +58,7 @@ class PreppedQueueProcessor(threading.Thread):
class FramePrepper(threading.Thread):
def __init__(self, camera_name, shared_frame, frame_time, frame_ready,
frame_lock,
region_size, region_x_offset, region_y_offset, region_threshold,
region_size, region_x_offset, region_y_offset, region_id,
prepped_frame_queue):
threading.Thread.__init__(self)
@ -73,7 +70,7 @@ class FramePrepper(threading.Thread):
self.region_size = region_size
self.region_x_offset = region_x_offset
self.region_y_offset = region_y_offset
self.region_threshold = region_threshold
self.region_id = region_id
self.prepped_frame_queue = prepped_frame_queue
def run(self):
@ -104,7 +101,7 @@ class FramePrepper(threading.Thread):
'frame_time': frame_time,
'frame': frame_expanded.flatten().copy(),
'region_size': self.region_size,
'region_threshold': self.region_threshold,
'region_id': self.region_id,
'region_x_offset': self.region_x_offset,
'region_y_offset': self.region_y_offset
})

62
frigate/objects.py
View File

@ -2,6 +2,7 @@ import time
import datetime
import threading
import cv2
import numpy as np
from . util import draw_box_with_label
class ObjectCleaner(threading.Thread):
@ -35,16 +36,15 @@ class ObjectCleaner(threading.Thread):
self._objects_parsed.notify_all()
# Maintains the frame and person with the highest score from the most recent
# motion event
class BestPersonFrame(threading.Thread):
# Maintains the frame and object with the highest score
class BestFrames(threading.Thread):
def __init__(self, objects_parsed, recent_frames, detected_objects):
threading.Thread.__init__(self)
self.objects_parsed = objects_parsed
self.recent_frames = recent_frames
self.detected_objects = detected_objects
self.best_person = None
self.best_frame = None
self.best_objects = {}
self.best_frames = {}
def run(self):
while True:
@ -55,38 +55,30 @@ class BestPersonFrame(threading.Thread):
# make a copy of detected objects
detected_objects = self.detected_objects.copy()
detected_people = [obj for obj in detected_objects if obj['name'] == 'person']
# get the highest scoring person
new_best_person = max(detected_people, key=lambda x:x['score'], default=self.best_person)
# if there isnt a person, continue
if new_best_person is None:
continue
# if there is no current best_person
if self.best_person is None:
self.best_person = new_best_person
# if there is already a best_person
else:
now = datetime.datetime.now().timestamp()
# if the new best person is a higher score than the current best person
# or the current person is more than 1 minute old, use the new best person
if new_best_person['score'] > self.best_person['score'] or (now - self.best_person['frame_time']) > 60:
self.best_person = new_best_person
for obj in detected_objects:
if obj['name'] in self.best_objects:
now = datetime.datetime.now().timestamp()
# if the object is a higher score than the current best score
# or the current object is more than 1 minute old, use the new object
if obj['score'] > self.best_objects[obj['name']]['score'] or (now - self.best_objects[obj['name']]['frame_time']) > 60:
self.best_objects[obj['name']] = obj
else:
self.best_objects[obj['name']] = obj
# make a copy of the recent frames
recent_frames = self.recent_frames.copy()
if not self.best_person is None and self.best_person['frame_time'] in recent_frames:
best_frame = recent_frames[self.best_person['frame_time']]
label = "{}: {}% {}".format(self.best_person['name'],int(self.best_person['score']*100),int(self.best_person['area']))
draw_box_with_label(best_frame, self.best_person['xmin'], self.best_person['ymin'],
self.best_person['xmax'], self.best_person['ymax'], label)
# print a timestamp
time_to_show = datetime.datetime.fromtimestamp(self.best_person['frame_time']).strftime("%m/%d/%Y %H:%M:%S")
cv2.putText(best_frame, time_to_show, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=.8, color=(255, 255, 255), thickness=2)
self.best_frame = cv2.cvtColor(best_frame, cv2.COLOR_RGB2BGR)
for name, obj in self.best_objects.items():
if obj['frame_time'] in recent_frames:
best_frame = recent_frames[obj['frame_time']] #, np.zeros((720,1280,3), np.uint8))
label = "{}: {}% {}".format(name,int(obj['score']*100),int(obj['area']))
draw_box_with_label(best_frame, obj['xmin'], obj['ymin'],
obj['xmax'], obj['ymax'], label)
# print a timestamp
time_to_show = datetime.datetime.fromtimestamp(obj['frame_time']).strftime("%m/%d/%Y %H:%M:%S")
cv2.putText(best_frame, time_to_show, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=.8, color=(255, 255, 255), thickness=2)
self.best_frames[name] = cv2.cvtColor(best_frame, cv2.COLOR_RGB2BGR)

99
frigate/video.py
View File

@ -7,9 +7,10 @@ import ctypes
import multiprocessing as mp
import subprocess as sp
import numpy as np
from collections import defaultdict
from . util import tonumpyarray, draw_box_with_label
from . object_detection import FramePrepper
from . objects import ObjectCleaner, BestPersonFrame
from . objects import ObjectCleaner, BestFrames
from . mqtt import MqttObjectPublisher
# Stores 2 seconds worth of frames when motion is detected so they can be used for other threads
@ -70,8 +71,8 @@ class CameraWatchdog(threading.Thread):
# wait a bit before checking
time.sleep(10)
if (datetime.datetime.now().timestamp() - self.camera.frame_time.value) > 10:
print("last frame is more than 10 seconds old, restarting camera capture...")
if (datetime.datetime.now().timestamp() - self.camera.frame_time.value) > 300:
print("last frame is more than 5 minutes old, restarting camera capture...")
self.camera.start_or_restart_capture()
time.sleep(5)
@ -111,7 +112,7 @@ class CameraCapture(threading.Thread):
self.camera.frame_ready.notify_all()
class Camera:
def __init__(self, name, ffmpeg_config, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
def __init__(self, name, ffmpeg_config, global_objects_config, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
self.name = name
self.config = config
self.detected_objects = []
@ -124,6 +125,8 @@ class Camera:
self.ffmpeg_input_args = self.ffmpeg.get('input_args', ffmpeg_config['input_args'])
self.ffmpeg_output_args = self.ffmpeg.get('output_args', ffmpeg_config['output_args'])
camera_objects_config = config.get('objects', {})
self.take_frame = self.config.get('take_frame', 1)
self.regions = self.config['regions']
self.frame_shape = get_frame_shape(self.ffmpeg_input)
@ -147,20 +150,23 @@ class Camera:
# for each region, create a separate thread to resize the region and prep for detection
self.detection_prep_threads = []
for region in self.config['regions']:
# set a default threshold of 0.5 if not defined
if not 'threshold' in region:
region['threshold'] = 0.5
if not isinstance(region['threshold'], float):
print('Threshold is not a float. Setting to 0.5 default.')
region['threshold'] = 0.5
for index, region in enumerate(self.config['regions']):
region_objects = region.get('objects', {})
# build objects config for region
objects_with_config = set().union(global_objects_config.keys(), camera_objects_config.keys(), region_objects.keys())
merged_objects_config = defaultdict(lambda: {})
for obj in objects_with_config:
merged_objects_config[obj] = {**global_objects_config.get(obj,{}), **camera_objects_config.get(obj, {}), **region_objects.get(obj, {})}
region['objects'] = merged_objects_config
self.detection_prep_threads.append(FramePrepper(
self.name,
self.current_frame,
self.frame_time,
self.frame_ready,
self.frame_lock,
region['size'], region['x_offset'], region['y_offset'], region['threshold'],
region['size'], region['x_offset'], region['y_offset'], index,
prepped_frame_queue
))
@ -169,22 +175,22 @@ class Camera:
self.frame_ready, self.frame_lock, self.recent_frames)
self.frame_tracker.start()
# start a thread to store the highest scoring recent person frame
self.best_person_frame = BestPersonFrame(self.objects_parsed, self.recent_frames, self.detected_objects)
self.best_person_frame.start()
# start a thread to store the highest scoring recent frames for monitored object types
self.best_frames = BestFrames(self.objects_parsed, self.recent_frames, self.detected_objects)
self.best_frames.start()
# start a thread to expire objects from the detected objects list
self.object_cleaner = ObjectCleaner(self.objects_parsed, self.detected_objects)
self.object_cleaner.start()
# start a thread to publish object scores (currently only person)
mqtt_publisher = MqttObjectPublisher(self.mqtt_client, self.mqtt_topic_prefix, self.objects_parsed, self.detected_objects, self.best_person_frame)
# start a thread to publish object scores
mqtt_publisher = MqttObjectPublisher(self.mqtt_client, self.mqtt_topic_prefix, self.objects_parsed, self.detected_objects, self.best_frames)
mqtt_publisher.start()
# create a watchdog thread for capture process
self.watchdog = CameraWatchdog(self)
# load in the mask for person detection
# load in the mask for object detection
if 'mask' in self.config:
self.mask = cv2.imread("/config/{}".format(self.config['mask']), cv2.IMREAD_GRAYSCALE)
else:
@ -252,38 +258,45 @@ class Camera:
return
for obj in objects:
# Store object area to use in bounding box labels
# find the matching region
region = self.regions[obj['region_id']]
# Compute some extra properties
obj.update({
'xmin': int((obj['box'][0] * region['size']) + region['x_offset']),
'ymin': int((obj['box'][1] * region['size']) + region['y_offset']),
'xmax': int((obj['box'][2] * region['size']) + region['x_offset']),
'ymax': int((obj['box'][3] * region['size']) + region['y_offset'])
})
# Compute the area
obj['area'] = (obj['xmax']-obj['xmin'])*(obj['ymax']-obj['ymin'])
if obj['name'] == 'person':
# find the matching region
region = None
for r in self.regions:
if (
obj['xmin'] >= r['x_offset'] and
obj['ymin'] >= r['y_offset'] and
obj['xmax'] <= r['x_offset']+r['size'] and
obj['ymax'] <= r['y_offset']+r['size']
):
region = r
break
# if the min person area is larger than the
# detected person, don't add it to detected objects
if region and 'min_person_area' in region and region['min_person_area'] > obj['area']:
object_name = obj['name']
if object_name in region['objects']:
obj_settings = region['objects'][object_name]
# if the min area is larger than the
# detected object, don't add it to detected objects
if obj_settings.get('min_area',-1) > obj['area']:
continue
# if the detected person is larger than the
# max person area, don't add it to detected objects
if region and 'max_person_area' in region and region['max_person_area'] < obj['area']:
# if the detected object is larger than the
# max area, don't add it to detected objects
if obj_settings.get('max_area', region['size']**2) < obj['area']:
continue
# if the score is lower than the threshold, skip
if obj_settings.get('threshold', 0) > obj['score']:
continue
# compute the coordinates of the person and make sure
# compute the coordinates of the object and make sure
# the location isnt outside the bounds of the image (can happen from rounding)
y_location = min(int(obj['ymax']), len(self.mask)-1)
x_location = min(int((obj['xmax']-obj['xmin'])/2.0)+obj['xmin'], len(self.mask[0])-1)
# if the person is in a masked location, continue
# if the object is in a masked location, don't add it to detected objects
if self.mask[y_location][x_location] == [0]:
continue
@ -291,9 +304,9 @@ class Camera:
with self.objects_parsed:
self.objects_parsed.notify_all()
def get_best_person(self):
return self.best_person_frame.best_frame
def get_best(self, label):
return self.best_frames.best_frames.get(label)
def get_current_frame_with_objects(self):
# make a copy of the current detected objects