VvasInferDetection - VvasInferDetection - 6.3 English - XD056

Vitis Video Analytics SDK (VVAS) 6.3 User Guide (XD056)

Document_ID
XD056
Release_Date
2026-09-24
Version
6.3 English

VvasInferDetection holds the detection result for a single detected object. It is pointed to by VvasInferResult.data when infer_result_type == VVAS_INFER_RESULT_DETECTION.

Definition

typedef struct {
  VvasBoundingBox bbox;
  char *label;
  int class_id;
  double probability;
  char *obj_track_label;
} VvasInferDetection;

Members

bbox

Bounding box coordinates and display color for the detected object.

label

Human-readable class label string (for example, "car", "person"), or NULL if no label is available.

class_id

Numerical class index corresponding to label.

probability

Detection confidence score, typically in the range [0.0, 1.0].

obj_track_label

Tracker-assigned label for this object across frames. NULL when tracking is not in use.