The following code sample explains how to leverage scale resolution to compute distances between objects given by their bounding boxes:

import numpy as np

def compute_pixel_distance(box1, box2):

    """Compute Euclidean distance between the centers of two bounding boxes"""

    x1_center = (box1[0] + box1[2]) / 2

    y1_center = (box1[1] + box1[3]) / 2

    x2_center = (box2[0] + box2[2]) / 2

    y2_center = (box2[1] + box2[3]) / 2

    return np.sqrt((x2_center - x1_center)**2 + (y2_center - y1_center)**2)

def estimate_scale(reference_box, vehicle_type):

    """Estimate feet per pixel using a reference vehicle box"""

    vehicle_lengths = {

        'motorcycle': 5,

        'car': 20,

        'truck': 40

    }

    pixel_length = reference_box[2] - reference_box[0] # width in pixels

    return vehicle_lengths[vehicle_type.lower()] / pixel_length

def estimate_actual_distance(landmark_box1, landmark_box2, reference_box, vehicle_type):

    pixel_dist = compute_pixel_distance(landmark_box1, landmark_box2)

    scale = estimate_scale(reference_box, vehicle_type)

    return pixel_dist * scale

# Example inputs:

landmark_box1 = (100, 200, 180, 280)

landmark_box2 = (400, 450, 480, 530)

reference_vehicle_box = (300, 300, 340, 340) # e.g., a car seen from side view

vehicle_type = 'car'

actual_distance_feet = estimate_actual_distance(landmark_box1, landmark_box2, reference_vehicle_box, vehicle_type)

print(f"Estimated actual distance between landmarks: {actual_distance_feet:.2f} feet")

This is a continuation of previous article on agentic retrieval on the analysis side of the aerial drone image processing pipeline using modular functions for specific insights into a scene.