Face, Body and Object Detection

In this section you will learn how to integrate Face Detector, Human Body Detector and Object Detector to your C++ or Python project.

Face Detection (С++/Python)

Types of Detection Blocks for the Key "unit_type"

• FACE_DETECTOR
• HUMAN_BODY_DETECTOR
• OBJECT_DETECTOR

1. Create a Face Detector

1.1 To create a Face Detector, follow steps 1-3 described in Creating a Processing Block and specify the value of the block you are interested in for the "unit_type" key :

C++

configCtx["unit_type"] = "FACE_DETECTOR";

// optional, default value is "ssyv"
configCtx["modification"] = "ssyv";

// optional, default value is 1l
configCtx["version"] = 1l;

// optional, default value is 0.5
configCtx["confidence_threshold"] = 0.5;

// optional, default value is 0.5
configCtx["iou_threshold"] = 0.5;

Python

configCtx = {
    "unit_type": "FACE_DETECTOR",
    # optional, default values are specified after ":"
    "modification": "ssyv",
    "version": 1,
    "confidence_threshold": 0.5,
    "iou_threshold": 0.5
}

Flutter

Map<String, dynamic> configCtx = {
    "unit_type": "FACE_DETECTOR",
    // optional, default values are specified after ":"
    "confidence_threshold": 0.5,
    "iou_threshold": 0.5
};

1.2 Create a Face Detector processing block:

C++

pbio::ProcessingBlock faceDetector = service->createProcessingBlock(configCtx);

Python

faceDetector = service.create_processing_block(configCtx)

Flutter

ProcessingBlock blockDetector = service.createProcessingBlock(configCtx);

2. Face Detection

2.1 Create a Context container ioData for input-output data using the createContext() method:

C++

auto ioData = service->createContext();

Python

ioData = service.create_context({})

Flutter

Context ioData = service.createContext({});

2.2 Create a Context container imgCtx with RGB-image following the steps described on Creating a Context container with RGB-image.

C++

// putting an image into the container
auto imgCtx = ioData["image"];
pbio::context_utils::putImage(imgCtx, input_rawimg);

Python

# copying an image to binary format
input_rawimg = image.tobytes()
# putting an image into the container
imageCtx = {
    "blob": input_rawimg,
    "dtype": "uint8_t",
    "format": "NDARRAY",
    "shape": [dim for dim in image.shape]
}

Flutter

Map<String, dynamic> imageContext = {
    "blob": <byte array with an image in RGB format>,
    "dtype": "uint8_t",
    "format": "NDARRAY",
    "shape": [<image height in pixels>, <image width in pixels>, 3]
};

2.3 Put an image to the input-output data container:

C++

ioData["image"] = imgCtx;

Python

ioData["image"] = imageCtx

Flutter

ioData["image"].placeValues(imageContext);

2.4 Call the faceDetector and pass the Context-container ioData that contains an image:

C++

blockDetector(ioData);

Python

blockDetector(ioData)

Flutter

Context ioData = blockDetector.process(ioData);

The blockDetector() method will add the result of processing samples (images) to the ioData container.

The output format is a list of objects, accessible by the "objects" key.

Each list object has a "class" key with a value corresponding to the class of the detected object.

The "bbox" (bounding box) key contains an array of 4 double numbers {x1, y1, x2, y2} which are the relative coordinates of the source image.

The "confidence" key contains a double number in the range [0,1].

/*
{
"objects": [{ "id": {"type": "long", "minimum": 0},
               "class": "face",
               "confidence": {"double",  "minimum": 0,  "maximum": 1},
               "bbox": [x1, y2, x2, y2] }]
}
*/