Computer Vision with YOLO v8

Applications of Object Detection

Retail: Inventory counting, shelf analysis

Security: Perimeter monitoring, crowd detection

Manufacturing: Defect detection, quality control

Healthcare: Medical image analysis

Autonomous vehicles: Scene understanding

Getting Started with YOLO v8

python
from ultralytics import YOLO
import cv2
Load pre-trained model
model = YOLO("yolov8n.pt")  # n=nano, s=small, m=medium, l=large, x=xlarge
Run inference on image
results = model("image.jpg")
Process results
for result in results:
    boxes = result.boxes  # Bounding boxes
    for box in boxes:
        x1, y1, x2, y2 = box.xyxy[0].tolist()
        confidence = box.conf[0].item()
        class_id = int(box.cls[0])
        class_name = model.names[class_id]
        print(f"{class_name}: {confidence:.2f} at [{x1:.0f}, {y1:.0f}, {x2:.0f}, {y2:.0f}]")

Real-Time Video Detection

python
def process_video_stream(source: str = 0):  # 0 = webcam
    cap = cv2.VideoCapture(source)
    model = YOLO("yolov8n.pt")
    
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        
        results = model(frame, verbose=False)
        annotated_frame = results[0].plot()
        
        cv2.imshow("Detection", annotated_frame)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
    
    cap.release()
    cv2.destroyAllWindows()

Fine-Tuning for Custom Objects

python
Prepare dataset in YOLO format
dataset/
  images/train/  images/val/
  labels/train/  labels/val/
  data.yaml
data.yaml
yaml_content = """
train: ./images/train
val: ./images/val
nc: 3  # number of classes
names: ['product', 'defect', 'barcode']
"""
Train custom model
model = YOLO("yolov8m.pt")  # Start from pretrained
results = model.train(
    data="data.yaml",
    epochs=100,
    imgsz=640,
    batch=16,
    device=0  # GPU index
)

Instance Segmentation

Get pixel-precise masks, not just boxes:

python
seg_model = YOLO("yolov8n-seg.pt")
results = seg_model("image.jpg")
masks = results[0].masks.data  # Segmentation masks

Deployment for Production

Export to ONNX for cross-platform deployment

TensorRT optimization for NVIDIA GPUs (10x speedup)

Edge deployment with Coral TPU or NVIDIA Jetson