# YOLO + SAM2 Video Processing Configuration input: video_path: "/path/to/input/video.mp4" output: directory: "/path/to/output/" filename: "processed_video.mp4" processing: # Duration of each video segment in seconds segment_duration: 5 # Scale factor for SAM2 inference (0.5 = half resolution) inference_scale: 0.5 # YOLO detection confidence threshold yolo_confidence: 0.6 # Which segments to run YOLO detection on # Options: "all", [0, 5, 10], or [] for default (all) detect_segments: "all" models: # YOLO model path - can be pretrained (yolov8n.pt) or custom path yolo_model: "yolov8n.pt" # SAM2 model configuration sam2_checkpoint: "../checkpoints/sam2.1_hiera_large.pt" sam2_config: "configs/sam2.1/sam2.1_hiera_l.yaml" video: # Use NVIDIA hardware encoding (requires NVENC-capable GPU) use_nvenc: true # Output video bitrate output_bitrate: "50M" # Preserve original audio track preserve_audio: true # Force keyframes for better segment boundaries force_keyframes: true advanced: # Green screen color (RGB values) green_color: [0, 255, 0] # Blue screen color for second object (RGB values) blue_color: [255, 0, 0] # YOLO human class ID (0 for COCO person class) human_class_id: 0 # GPU memory management cleanup_intermediate_files: true # Logging level (DEBUG, INFO, WARNING, ERROR) log_level: "INFO"