Computer Vision Pipeline

Need real-time (>30 FPS)? → YOLOv8
Need highest accuracy? → Detectron2 Mask R-CNN
Need mobile deployment? → YOLOv8-nano or EfficientDet
Need instance segmentation? → Detectron2 or YOLOv8-seg
Need custom objects? → Fine-tune YOLOv8

# ❌ No preprocessing - poor results
import cv2
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
video = cv2.VideoCapture('drone_footage.mp4')

while True:
    ret, frame = video.read()
    if not ret:
        break

    # Raw frame detection - no normalization, no resizing
    results = model(frame)
    # Poor accuracy, slow inference

# ✅ Proper preprocessing pipeline
import cv2
import numpy as np
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
video = cv2.VideoCapture('drone_footage.mp4')

# Model expects 640x640 input
TARGET_SIZE = 640

def preprocess_frame(frame):
    # Resize while maintaining aspect ratio
    h, w = frame.shape[:2]
    scale = TARGET_SIZE / max(h, w)
    new_w, new_h = int(w * scale), int(h * scale)

    resized = cv2.resize(frame, (new_w, new_h), interpolation=cv2.INTER_LINEAR)

    # Pad to square
    pad_w = (TARGET_SIZE - new_w) // 2
    pad_h = (TARGET_SIZE - new_h) // 2

    padded = cv2.copyMakeBorder(
        resized,
        pad_h, TARGET_SIZE - new_h - pad_h,
        pad_w, TARGET_SIZE - new_w - pad_w,
        cv2.BORDER_CONSTANT,
        value=(114, 114, 114)  # Gray padding
    )

    # Normalize to 0-1 (if model expects it)
    # normalized = padded.astype(np.float32) / 255.0

    return padded, scale

while True:
    ret, frame = video.read()
    if not ret:
        break

    preprocessed, scale = preprocess_frame(frame)
    results = model(preprocessed)

    # Scale bounding boxes back to original coordinates
    for box in results[0].boxes:
        x1, y1, x2, y2 = box.xyxy[0]
        x1, y1, x2, y2 = x1/scale, y1/scale, x2/scale, y2/scale

# ❌ Process every frame (30 FPS video = 1800 frames/min)
import cv2
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
video = cv2.VideoCapture('drone_footage.mp4')

detections = []

while True:
    ret, frame = video.read()
    if not ret:
        break

    # Run detection on EVERY frame
    results = model(frame)
    detections.append(results)

# 10-minute video = 18,000 inferences (15 minutes on GPU)

# ✅ Sample every Nth frame
import cv2
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
video = cv2.VideoCapture('drone_footage.mp4')

SAMPLE_RATE = 30  # Process 1 frame per second (if 30 FPS video)

frame_count = 0
detections = []

while True:
    ret, frame = video.read()
    if not ret:
        break

    frame_count += 1

    # Only process every 30th frame
    if frame_count % SAMPLE_RATE == 0:
        results = model(frame)
        detections.append({
            'frame': frame_count,
            'timestamp': frame_count / 30.0,
            'results': results
        })

# 10-minute video = 600 inferences (30 seconds on GPU)

# ✅ Only process when scene changes significantly
import cv2
import numpy as np
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
video = cv2.VideoCapture('drone_footage.mp4')

def scene_changed(prev_frame, curr_frame, threshold=0.3):
    """Detect scene change using histogram comparison"""
    if prev_frame is None:
        return True

    # Convert to grayscale
    prev_gray = cv2.cvtColor(prev_frame, cv2.COLOR_BGR2GRAY)
    curr_gray = cv2.cvtColor(curr_frame, cv2.COLOR_BGR2GRAY)

    # Calculate histograms
    prev_hist = cv2.calcHist([prev_gray], [0], None, [256], [0, 256])
    curr_hist = cv2.calcHist([curr_gray], [0], None, [256], [0, 256])

    # Compare histograms
    correlation = cv2.compareHist(prev_hist, curr_hist, cv2.HISTCMP_CORREL)

    return correlation < (1 - threshold)

prev_frame = None
detections = []

while True:
    ret, frame = video.read()
    if not ret:
        break

    # Only run detection if scene changed
    if scene_changed(prev_frame, frame):
        results = model(frame)
        detections.append(results)

    prev_frame = frame.copy()

# Adapts to video content - static shots skip frames, action scenes process more

# ❌ Sequential processing - GPU underutilized
import cv2
from ultralytics import YOLO
import time

model = YOLO('yolov8n.pt')

# 100 images to process
image_paths = [f'frame_{i:04d}.jpg' for i in range(100)]

start = time.time()

for path in image_paths:
    frame = cv2.imread(path)
    results = model(frame)  # Process one at a time
    # GPU utilization: ~20%

elapsed = time.time() - start
print(f"Processed {len(image_paths)} images in {elapsed:.2f}s")
# Output: 45 seconds

# ✅ Batch inference - GPU fully utilized
import cv2
from ultralytics import YOLO
import time

model = YOLO('yolov8n.pt')

image_paths = [f'frame_{i:04d}.jpg' for i in range(100)]

BATCH_SIZE = 16  # Process 16 images at once

start = time.time()

for i in range(0, len(image_paths), BATCH_SIZE):
    batch_paths = image_paths[i:i+BATCH_SIZE]

    # Load batch
    frames = [cv2.imread(path) for path in batch_paths]

    # Batch inference (single GPU call)
    results = model(frames)  # Pass list of images
    # GPU utilization: ~85%

elapsed = time.time() - start
print(f"Processed {len(image_paths)} images in {elapsed:.2f}s")
# Output: 8 seconds (5.6x faster!)

# Find optimal batch size for your GPU
import torch

def find_optimal_batch_size(model, image_size=(640, 640)):
    for batch_size in [1, 2, 4, 8, 16, 32, 64]:
        try:
            dummy_input = torch.randn(batch_size, 3, *image_size).cuda()

            start = time.time()
            with torch.no_grad():
                _ = model(dummy_input)
            elapsed = time.time() - start

            throughput = batch_size / elapsed
            print(f"Batch {batch_size}: {throughput:.1f} img/s")
        except RuntimeError as e:
            print(f"Batch {batch_size}: OOM (out of memory)")
            break

# Find optimal batch size before production
find_optimal_batch_size(model)