Tutorial - Using 3D Object Detection

This tutorial shows how to enable the AI-based Object Detection module to detect, classify and localize objects in 3D space, with a runtime-adjustable confidence threshold. Detection and localization work with both a static and a moving camera. This module requires a stereo camera with an integrated IMU (ZED 2/2i, ZED Mini, or ZED X family); the original ZED is not supported.

Getting Started

• First, download the latest version of the ZED SDK.
• Download the Object Detection sample code in C, C++, Python or C#.

Code Overview

Open the camera

In this tutorial, we will use the Object Detection AI module of the ZED SDK. As in previous tutorials, we create, configure and open the camera.

// Create ZED objects
Camera zed;
InitParameters init_parameters;
init_parameters.camera_resolution = RESOLUTION::HD720;
init_parameters.depth_mode = DEPTH_MODE::NEURAL;
// Open the camera
ERROR_CODE zed_error = zed.open(init_parameters);
if (zed_error != ERROR_CODE::SUCCESS) {
	std::cout << "Error " << zed_error << ", exit program.\n";
	return 1; // Quit if an error occurred
}

Enable 3D Object detection

Before enabling object detection, we specify the ObjectDetectionParameters of the module. In this tutorial, we use the following settings:

// Define the Object Detection module parameters
ObjectDetectionParameters detection_parameters;
detection_parameters.enable_tracking = true;
detection_parameters.enable_segmentation = true;
// Object tracking requires camera tracking to be enabled
if (detection_parameters.enable_tracking)
	zed.enablePositionalTracking();

• enable_tracking allows objects to be tracked across frames and keep the same ID as long as possible. Positional tracking must be active in order to track objects’ movements independently from camera motion.
• enable_segmentation outputs 2D masks over detected objects. Since it requires additional processing, disable this option if not used.

Now let’s enable object detection which will load an AI model. This operation can take a few seconds. The first time the module is used, the model will be optimized for your hardware and this can take up to a few minutes. The model optimization operation is done only once.

cout << "Object Detection: Loading Module..." << endl;
zed_error = zed.enableObjectDetection(detection_parameters);
if (zed_error != ERROR_CODE::SUCCESS) {
	cout << "Error " << zed_error << ", exit program.\n";
	zed.close();
	return 1;
}

Retrieve object data

To retrieve detected objects in an image, use the retrieveObjects() function with an Objects parameter that will store objects’ data.

For each grab call, the image is fed into the AI module, which outputs the objects detected in that frame. We also set the object confidence threshold at 40: detections with a lower confidence are discarded. Raise it to keep only the most confident detections.

// Set runtime parameter confidence to 40
ObjectDetectionRuntimeParameters detection_parameters_runtime;
detection_parameters_runtime.detection_confidence_threshold = 40;
Objects objects;
// Grab new frames and detect objects
while (zed.grab() == ERROR_CODE::SUCCESS) {
	zed.retrieveObjects(objects, detection_parameters_runtime);
	if (objects.is_new && !objects.object_list.empty()) {
        // Count the number of objects detected
        cout << objects.object_list.size() << " Object(s) detected" << endl;
        // Display the 3D location of an object  
        auto &first_object = objects.object_list[0];
        cout << " 3D position: " << first_object.position;
        // Display its 3D bounding box coordinates        
        cout << " Bounding box 3D \n";
        for (auto it : first_object.bounding_box)
          cout << "    " << it;    
	}
}

Disable modules and exit

Before exiting the application, modules need to be disabled and the camera closed.

// Disable object detection and close the camera
zed.disableObjectDetection();
zed.close();

And this is it!