changes per request

README.md

@@ -37,7 +37,7 @@ image_processing:
     roi_x_max: 0.8
     #roi_y_min: 0.4
     roi_y_max: 0.8
-    crop_roi: True
+    crop_to_roi: True
     targets:
       - target: person
       - target: vehicle
@@ -65,7 +65,7 @@ Configuration variables:
 - **roi_x_max**: (optional, default 1), range 0-1, must be more than roi_x_min
 - **roi_y_min**: (optional, default 0), range 0-1, must be less than roi_y_max
 - **roi_y_max**: (optional, default 1), range 0-1, must be more than roi_y_min
-- **crop_roi**: (oprional, default False), crops the image to the specified roi.  This reduces disk space used, and improves performance (speed and object detection) when regions-of-interest are applied. 
+- **crop_to_roi**: (optional, default False), crops the image to the specified roi.  May improve object detection accuracy when a region-of-interest is applied
 - **source**: Must be a camera.
 - **targets**: The list of target object names and/or `object_type`, default `person`. Optionally a `confidence` can be set for this target, if not the default confidence is used. Note the minimum possible confidence is 10%.
 

custom_components/deepstack_object/image_processing.py

@@ -77,7 +77,7 @@
 CONF_ROI_X_MAX = "roi_x_max"
 CONF_SCALE = "scale"
 CONF_CUSTOM_MODEL = "custom_model"
-CONF_CROP_ROI = "crop_roi"
+CONF_CROP_ROI = "crop_to_roi"
 
 DATETIME_FORMAT = "%Y-%m-%d_%H-%M-%S-%f"
 DEFAULT_API_KEY = ""

custom_components/deepstack_object/manifest.json

@@ -2,7 +2,7 @@
         "domain": "deepstack_object",
         "name": "deepstack object custom integration",
         "documentation": "https://github.com/robmarkcole/HASS-Deepstack-object",
-        "version": "4.3.1",
+        "version": "4.4.0",
         "requirements": [
                 "pillow",
                 "deepstack-python==0.8"