Object Detection

SDK.detect_objects(self: tfsdk.SDK, tf_image: tfsdk.TFImage) → List[tfsdk.BoundingBox]

Detect people and objects in the image.

Parameters

tf_image - the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image(). :Returns:

The ERRORCODE and a list of tfsdk.BoundingBox representing the detected objects, in that order.

static SDK.get_object_label_string(object_label: tfsdk.OBJECTLABEL) → str

Converts an object label to a string.

Parameters

object_label – the tfsdk.BounxingBox.label.

Returns

The string representation of the tfsdk.BoundingBox.label.

class tfsdk.BoundingBox

property height

The height of the bounding box.

property label

The object class as a label.

property probability

The detection’s confidence probability.

to_dict(self: tfsdk.BoundingBox) → dict

property top_left

The top left corner Point of the bounding box.

property width

The width of the bounding box.

class tfsdk.OBJECTLABEL

Members:

background

aeroplane

bicycle

bird

boat

bottle

bus

car

cat

chair

cow

diningtable

dog

horse

motorbike

person

pottedplant

sheep

sofa

train

tvmonitor