# SPDX-License-Identifier: MIT # Copyright (C) Intel Corporation # # Crowd Detection: OpenVINO Runtime sample. # See README.md for prerequisites and inputs. Run: python3 openvino_sample.py import cv2 import numpy as np import openvino as ov PERSON_CLASS_ID = 0 CONF_THRESHOLD = 0.4 # Select the model: "yolo26n" (default) or "detr-resnet-50". MODEL = "yolo26n" INPUT_SIZE = 800 if MODEL.startswith("detr") else 640 core = ov.Core() model = core.read_model(f"{MODEL}_openvino_model/{MODEL}.xml") compiled = core.compile_model(model, "CPU") # or "GPU", "NPU" image = cv2.imread("test.jpg") h0, w0 = image.shape[:2] # Preprocess: letterbox-free resize for simplicity. blob = cv2.resize(image, (INPUT_SIZE, INPUT_SIZE)) blob = cv2.cvtColor(blob, cv2.COLOR_BGR2RGB).astype(np.float32) / 255.0 blob = blob.transpose(2, 0, 1)[np.newaxis, ...] # NCHW # End-to-end output: [1, N, 6] = [x1, y1, x2, y2, confidence, class_id] # (N = 300 for YOLO26, 100 for DETR) # No NMS is needed -- YOLO26 is natively end-to-end. output = compiled([blob])[compiled.output(0)][0] mask = (output[:, 4] >= CONF_THRESHOLD) & (output[:, 5].astype(int) == PERSON_CLASS_ID) dets = output[mask] sx, sy = w0 / INPUT_SIZE, h0 / INPUT_SIZE crowd_count = len(dets) print(f"Detected persons: {crowd_count}") for det in dets: x1 = int(det[0] * sx) y1 = int(det[1] * sy) x2 = int(det[2] * sx) y2 = int(det[3] * sy) cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2) cv2.putText( image, f"Crowd count: {crowd_count}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 255, 0), 2, ) cv2.imwrite("output_openvino.jpg", image)