Namespace VisioForge.Core.AI

CocoLabels: Default COCO-80 class label set used by the object detectors when no custom labels are supplied.
OnnxInferenceEngine: Wraps a Microsoft.ML.OnnxRuntime.InferenceSession and provides reusable RGBA-frame preprocessing (letterbox resize + NCHW conversion + optional normalization) and execution.
OnnxInferenceEventArgs: Provides the raw outputs produced by a generic ONNX inference run for a single video frame.
OnnxSessionFactory: Builds Microsoft.ML.OnnxRuntime.SessionOptions with the same execution-provider selection and bundled-native preload logic used by VisioForge.Core.AI.OnnxInferenceEngine, for engines that own their own Microsoft.ML.OnnxRuntime.InferenceSession instances rather than going through that class.
YoloDetector: Object detector built on top of VisioForge.Core.AI.OnnxInferenceEngine that supports multiple model families (YOLOv8/v11, YOLOX, RT-DETR / D-FINE) selected via VisioForge.Core.Types.X.AI.YoloDetectorSettings.Model.

CocoClass: COCO dataset class IDs for use with object detection and analytics. Enum values match the standard COCO-80 class index, so they can be cast directly to int for VisioForge.Core.Types.X.AI.DetectionFilterSettings.IncludedClassIds.