objectconfig.ini

root@30656f8d7a9e:/etc/zm# cat objectconfig.ini
# Configuration file for object detection

# NOTE: ALL parameters here can be overriden
# on a per monitor basis if you want. Just
# duplicate it inside the correct [monitor-<num>] section

# You can create your own custom attributes in the [custom] section

[general]

# Please don't change this. It is used by the config upgrade script
version=1.2

# You can now limit the # of detection process
# per target processor. If not specified, default is 1
# Other detection processes will wait to acquire lock

cpu_max_processes=3
tpu_max_processes=1
gpu_max_processes=1

# Time to wait in seconds per processor to be free, before
# erroring out. Default is 120 (2 mins)
cpu_max_lock_wait=100
tpu_max_lock_wait=100
gpu_max_lock_wait=100


#pyzm_overrides={'conf_path':'/etc/zm','log_level_debug':0}
pyzm_overrides={'log_level_debug':5}

# This is an optional file
# If specified, you can specify tokens with secret values in that file
# and onlt refer to the tokens in your main config file
secrets = /etc/zm/secrets.ini

# portal/user/password are needed if you plan on using ZM's legacy
# auth mechanism to get images
portal=!ZM_PORTAL
user=!ZM_USER
password=!ZM_PASSWORD

# api portal is needed if you plan to use tokens to get images
# requires ZM 1.33 or above
api_portal=!ZM_API_PORTAL

allow_self_signed=yes
# if yes, last detection will be stored for monitors
# and bounding boxes that match, along with labels
# will be discarded for new detections. This may be helpful
# in getting rid of static objects that get detected
# due to some motion.
match_past_detections=no
# The max difference in area between the objects if match_past_detection is on
# can also be specified in px like 300px. Default is 5%. Basically, bounding boxes of the same
# object can slightly differ ever so slightly between detection. Contributor @neillbell put in this PR
# to calculate the difference in areas and based on his tests, 5% worked well. YMMV. Change it if needed.
# Note: You can specify label/object specific max_diff_areas as well. If present, they override this value
# example:
# person_past_det_max_diff_area=5%
# car_past_det_max_diff_area=5000px
past_det_max_diff_area=5%

# this is the maximum size a detected object can have. You can specify it in px or % just like past_det_max_diff_area
# This is pretty useful to eliminate bogus detection. In my case, depending on shadows and other lighting conditions,
# I sometimes see "car" or "person" detected that covers most of my driveway view. That is practically impossible
# and therefore I set mine to 70% because I know any valid detected objected cannot be larger than that area

max_detection_size=90%

# sequence of models to run for detection
detection_sequence=object,face,alpr
# if all, then we will loop through all models
# if first then the first success will break out
detection_mode=all

# If you need basic auth to access ZM
#basic_user=user
#basic_password=password

# base data path for various files the ES+OD needs
# we support in config variable substitution as well
base_data_path=/var/lib/zmeventnotification

# global settings for
# bestmatch, alarm, snapshot OR a specific frame ID
frame_id=bestmatch

# this is the to resize the image before analysis is done
resize=800
# set to yes, if you want to remove images after analysis
# setting to yes is recommended to avoid filling up space
# keep to no while debugging/inspecting masks
# Note this does NOT delete debug images later
delete_after_analyze=yes

# If yes, will write an image called <filename>-bbox.jpg as well
# which contains the bounding boxes. This has NO relation to
# write_image_to_zm
# Typically, if you enable delete_after_analyze you may
# also want to set  write_debug_image to no.
write_debug_image=no

# if yes, will write an image with bounding boxes
# this needs to be yes to be able to write a bounding box
# image to ZoneMinder that is visible from its console
write_image_to_zm=yes


# Adds percentage to detections
# hog/face shows 100% always
show_percent=yes

# color to be used to draw the polygons you specified
poly_color=(255,255,255)
poly_thickness=2
#import_zm_zones=yes
only_triggered_zm_zones=no

# This section gives you an option to get brief animations
# of the event, delivered as part of the push notification to mobile devices
# Animations are created only if an object is detected
#
# NOTE: This will DELAY the time taken to send you push notifications
# It will try to first creat the animation, which may take upto a minute
# depending on how soon it gets access to frames. See notes below

[animation]

# If yes, object detection will attempt to create
# a short GIF file around the object detection frame
# that can be sent via push notifications for instant playback
# Note this required additional software support. Default:no
create_animation=no

# Format of animation burst
# valid options are "mp4", "gif", "mp4,gif"
# Note that gifs will be of a shorter duration
# as they take up much more disk space than mp4
animation_types='mp4,gif'

# default width of animation image. Be cautious when you increase this
# most mobile platforms give a very brief amount of time (in seconds)
# to download the image.
# Given your ZM instance will be serving the image, it will anyway be slow
# Making the total animation size bigger resulted in the notification not
# getting an image at all (timed out)
animation_width=640

# When an event is detected, ZM it writes frames a little late
# On top of that, it looks like with caching enabled, the API layer doesn't
# get access to DB records for much longer (around 30 seconds), at least on my
# system. animation_retry_sleep refers to how long to wait before trying to grab
# frame information if it failed. animation_max_tries defines how many times it
# will try and retrieve frames before it gives up
animation_retry_sleep=15
animation_max_tries=4

# if animation_types is gif then when can generate a fast preview gif
# every second frame is skipped and the frame rate doubled
# to give quick preview, Default (no)
fast_gif=no

[remote]
# You can now run the machine learning code on a different server
# This frees up your ZM server for other things
# To do this, you need to setup https://github.com/pliablepixels/mlapi
# on your desired server and confiure it with a user. See its instructions
# once set up, you can choose to do object/face recognition via that
# external serer

# URL that will be used
#ml_gateway=http://192.168.1.183:5000/api/v1
#ml_gateway=http://10.6.1.13:5000/api/v1
#ml_gateway=http://192.168.1.21:5000/api/v1
#ml_gateway=http://10.9.0.2:5000/api/v1
#ml_fallback_local=yes
# API/password for remote gateway
ml_user=!ML_USER
ml_password=!ML_PASSWORD


# config for object
[object]

# If you are using legacy format (use_sequence=no) then these parameters will
# be used during ML inferencing
object_detection_pattern=(person|car|motorbike|bus|truck|boat)
object_min_confidence=0.3
object_framework=coral_edgetpu
object_processor=tpu
object_weights={{base_data_path}}/models/coral_edgetpu/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite
object_labels={{base_data_path}}/models/coral_edgetpu/coco_indexed.names

# If you are using the new ml_sequence format (use_sequence=yes) then
# you can fiddle with these parameters and look at ml_sequence later
# Note that these can be named anything. You can add custom variables, ad-infinitum

# Google Coral
# The mobiledet model came out in Nov 2020 and is supposed to be faster and more accurate but YMMV
tpu_object_weights_mobiledet={{base_data_path}}/models/coral_edgetpu/ssdlite_mobiledet_coco_qat_postprocess_edgetpu.tflite
tpu_object_weights_mobilenet={{base_data_path}}/models/coral_edgetpu/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite
tpu_object_labels={{base_data_path}}/models/coral_edgetpu/coco_indexed.names
tpu_object_framework=coral_edgetpu
tpu_object_processor=tpu
tpu_min_confidence=0.6

# Yolo v4 on GPU (falls back to CPU if no GPU)
yolo4_object_weights={{base_data_path}}/models/yolov4/yolov4.weights
yolo4_object_labels={{base_data_path}}/models/yolov4/coco.names
yolo4_object_config={{base_data_path}}/models/yolov4/yolov4.cfg
yolo4_object_framework=opencv
yolo4_object_processor=gpu

# Yolo v3 on GPU (falls back to CPU if no GPU)
yolo3_object_weights={{base_data_path}}/models/yolov3/yolov3.weights
yolo3_object_labels={{base_data_path}}/models/yolov3/coco.names
yolo3_object_config={{base_data_path}}/models/yolov3/yolov3.cfg
yolo3_object_framework=opencv
yolo3_object_processor=gpu

# Tiny Yolo V4 on GPU (falls back to CPU if no GPU)
tinyyolo_object_config={{base_data_path}}/models/tinyyolov4/yolov4-tiny.cfg
tinyyolo_object_weights={{base_data_path}}/models/tinyyolov4/yolov4-tiny.weights
tinyyolo_object_labels={{base_data_path}}/models/tinyyolov4/coco.names
tinyyolo_object_framework=opencv
tinyyolo_object_processor=gpu


[face]
face_detection_pattern=.*
known_images_path={{base_data_path}}/known_faces
unknown_images_path={{base_data_path}}/unknown_faces
save_unknown_faces=yes
save_unknown_faces_leeway_pixels=100
face_detection_framework=dlib

# read https://github.com/ageitgey/face_recognition/wiki/Face-Recognition-Accuracy-Problems
# read https://github.com/ageitgey/face_recognition#automatically-find-all-the-faces-in-an-image
# and play around

# quick overview:
# num_jitters is how many times to distort images
# upsample_times is how many times to upsample input images (for small faces, for example)
# model can be hog or cnn. cnn may be more accurate, but I haven't found it to be

face_num_jitters=1
face_model=cnn
face_upsample_times=1

# This is maximum distance of the face under test to the closest matched
# face cluster. The larger this distance, larger the chances of misclassification.
#
face_recog_dist_threshold=0.6
# When we are first training the face recognition model with known faces,
# by default we use hog because we assume you will supply well lit, front facing faces
# However, if you are planning to train with profile photos or hard to see faces, you
# may want to change this to cnn. Note that this increases training time, but training only
# happens once, unless you retrain again by removing the training model
face_train_model=cnn
#if a face doesn't match known names, we will detect it as 'unknown face'
# you can change that to something that suits your personality better ;-)
#unknown_face_name=invader

[alpr]
alpr_detection_pattern=.*
alpr_use_after_detection_only=yes
# Many of the ALPR providers offer both a cloud version
# and local SDK version. Sometimes local SDK format differs from
# the cloud instance. Set this to local or cloud. Default cloud
alpr_api_type=cloud

# -----| If you are using plate recognizer | ------
alpr_service=plate_recognizer
#alpr_service=open_alpr_cmdline

# If you want to host a local SDK https://app.platerecognizer.com/sdk/
#alpr_url=http://192.168.1.21:8080/alpr
# Plate recog replace with your api key
alpr_key=!PLATEREC_ALPR_KEY
# if yes, then it will log usage statistics of the ALPR service
platerec_stats=yes
# If you want to specify regions. See http://docs.platerecognizer.com/#regions-supported
#platerec_regions=['us','cn','kr']
# minimal confidence for actually detecting a plate
platerec_min_dscore=0.1
# minimal confidence for the translated text
platerec_min_score=0.2


# ----| If you are using openALPR |-----
#alpr_service=open_alpr
#alpr_key=!OPENALPR_ALPR_KEY

# For an explanation of params, see http://doc.openalpr.com/api/?api=cloudapi
#openalpr_recognize_vehicle=1
#openalpr_country=us
#openalpr_state=ca
# openalpr returns percents, but we convert to between 0 and 1
#openalpr_min_confidence=0.3

# ----| If you are using openALPR command line |-----

openalpr_cmdline_binary=alpr

# Do an alpr -help to see options, plug them in here
# like say '-j -p ca -c US' etc.
# keep the -j because its JSON

# Note that alpr_pattern is honored
# For the rest, just stuff them in the cmd line options

openalpr_cmdline_params=-j -d
openalpr_cmdline_min_confidence=0.3


## Monitor specific settings


# Examples:
# Let's assume your monitor ID is 999
[monitor-999]
# my driveway
match_past_detections=no
wait=5
object_detection_pattern=(person)

# Advanced example - here we want anything except potted plant
# exclusion in regular expressions is not
# as straightforward as you may think, so
# follow this pattern
# object_detection_pattern = ^(?!object1|object2|objectN)
# the characters in front implement what is
# called a negative look ahead

# object_detection_pattern=^(?!potted plant|pottedplant|bench|broccoli)
#alpr_detection_pattern=^(.*x11)
#delete_after_analyze=no
#detection_pattern=.*
#import_zm_zones=yes

# polygon areas where object detection will be done.
# You can name them anything except the keywords defined in the optional
# params below. You can put as many polygons as you want per [monitor-<mid>]
# (see examples).

my_driveway=306,356 1003,341 1074,683 154,715

# You are now allowed to specify detection pattern per zone
# the format is <polygonname>_zone_detection_pattern=<regexp>
# So if your polygon is called my_driveway, its associated
# detection pattern will be my_driveway_zone_detection_pattern
# If none is specified, the value in object_detection_pattern
# will be used
# This also applies to ZM zones. Let's assume you have
# import_zm_zones=yes and let's suppose you have a zone in ZM
# called Front_Door. In that case, all you need to do is put in a
# front_door_zone_detection_pattern=(person|car) here
#
# NOTE: ZM Zones are converted to lowercase, and spaces are replaced
# with underscores@3

my_driveway_zone_detection_pattern=(person)
some_other_area=0,0 200,300 700,900
# use license plate recognition for my driveway
# see alpr section later for more data needed
resize=no
detection_sequence=object,alpr


[ml]
# When enabled, you can specify complex ML inferencing logic in ml_sequence
# Anything specified in ml_sequence will override any other ml attributes

# Also, when enabled, stream_sequence will override any other frame related
# attributes
use_sequence = yes

# if enabled, will not grab exclusive locks before running inferencing
# locking seems to cause issues on some unique file systems
disable_locks= no

# Chain of frames
# See https://zmeventnotification.readthedocs.io/en/latest/guides/hooks.html#understanding-detection-configuration
# Also see https://pyzm.readthedocs.io/en/latest/source/pyzm.html#pyzm.ml.detect_sequence.DetectSequence.detect_stream
# Very important: Make sure final ending brace is indented
stream_sequence = {
        'frame_strategy': 'most_models',
        'frame_set': 'snapshot,alarm',
        'contig_frames_before_error': 5,
        'max_attempts': 3,
        'sleep_between_attempts': 4,
        'resize':800

    }

# Chain of ML models to use
# See https://zmeventnotification.readthedocs.io/en/latest/guides/hooks.html#understanding-detection-configuration
# Also see https://pyzm.readthedocs.io/en/latest/source/pyzm.html#pyzm.ml.detect_sequence.DetectSequence
# Very important: Make sure final ending brace is indented
ml_sequence= {
        'general': {
            'model_sequence': 'object,face,alpr',
            'disable_locks': '{{disable_locks}}',
            'match_past_detections': '{{match_past_detections}}',
            'past_det_max_diff_area': '5%',
            'car_past_det_max_diff_area': '10%',
            #'ignore_past_detection_labels': ['dog', 'cat']

        },
        'object': {
            'general':{
                'pattern':'{{object_detection_pattern}}',
                'same_model_sequence_strategy': 'first' # also 'most', 'most_unique's
            },
            'sequence': [{
                #First run on TPU with higher confidence
                'name': 'TPU object detection',
                'enabled': 'no',
                'object_weights':'{{tpu_object_weights_mobiledet}}',
                'object_labels': '{{tpu_object_labels}}',
                'object_min_confidence': {{tpu_min_confidence}},
                'object_framework':'{{tpu_object_framework}}',
                'tpu_max_processes': {{tpu_max_processes}},
                'tpu_max_lock_wait': {{tpu_max_lock_wait}},
                'max_detection_size':'{{max_detection_size}}'


            },
            {
                # YoloV4 on GPU if TPU fails (because sequence strategy is 'first')
                'name': 'YoloV4 GPU/CPU',
                'enabled': 'yes', # don't really need to say this explictly
                'object_config':'{{yolo4_object_config}}',
                'object_weights':'{{yolo4_object_weights}}',
                'object_labels': '{{yolo4_object_labels}}',
                'object_min_confidence': {{object_min_confidence}},
                'object_framework':'{{yolo4_object_framework}}',
                'object_processor': '{{yolo4_object_processor}}',
                'gpu_max_processes': {{gpu_max_processes}},
                'gpu_max_lock_wait': {{gpu_max_lock_wait}},
                'cpu_max_processes': {{cpu_max_processes}},
                'cpu_max_lock_wait': {{cpu_max_lock_wait}},
                'max_detection_size':'{{max_detection_size}}'

            }]
        },
        'face': {
            'general':{
                'pattern': '{{face_detection_pattern}}',
                'same_model_sequence_strategy': 'union' # combines all outputs of this sequence
            },
            'sequence': [
            {
                'name': 'TPU face detection',
                'enabled': 'no',
                'face_detection_framework': 'tpu',
                'face_weights':'/var/lib/zmeventnotification/models/coral_edgetpu/ssd_mobilenet_v2_face_quant_postprocess_edgetpu.tflite',
                'face_min_confidence': 0.3,

            },
            {
                'name': 'DLIB based face recognition',
                'enabled': 'yes',
                #'pre_existing_labels': ['face'], # If you use TPU detection first, we can run this ONLY if TPU detects a face first
                'save_unknown_faces':'{{save_unknown_faces}}',
                'save_unknown_faces_leeway_pixels':{{save_unknown_faces_leeway_pixels}},
                'face_detection_framework': '{{face_detection_framework}}',
                'known_images_path': '{{known_images_path}}',
                'unknown_images_path': '{{unknown_images_path}}',
                'face_model': '{{face_model}}',
                'face_train_model': '{{face_train_model}}',
                'face_recog_dist_threshold': '{{face_recog_dist_threshold}}',
                'face_num_jitters': '{{face_num_jitters}}',
                'face_upsample_times':'{{face_upsample_times}}',
                'gpu_max_processes': {{gpu_max_processes}},
                'gpu_max_lock_wait': {{gpu_max_lock_wait}},
                'cpu_max_processes': {{cpu_max_processes}},
                'cpu_max_lock_wait': {{cpu_max_lock_wait}},
                'max_size':800
            }]
        },

        'alpr': {
            'general':{
                'same_model_sequence_strategy': 'first',
                'pre_existing_labels':['car', 'motorbike', 'bus', 'truck', 'boat'],
                'pattern': '{{alpr_detection_pattern}}'

            },
            'sequence': [{
                'name': 'Platerecognizer cloud',
                'enabled': 'yes',
                'alpr_api_type': '{{alpr_api_type}}',
                'alpr_service': '{{alpr_service}}',
                'alpr_key': '{{alpr_key}}',
                'platrec_stats': '{{platerec_stats}}',
                'platerec_min_dscore': {{platerec_min_dscore}},
                'platerec_min_score': {{platerec_min_score}},
                'max_size':1600,
                #'platerec_payload': {
                #'regions':['us'],
                #'camera_id':12,
                #},
                #'platerec_config': {
                #    'region':'strict',
                #    'mode': 'fast'
                #}
            }]
        }
    }