dnn_softNMSBoxes

Deep neural networksfunctionOpenCV 5.0.0

import { dnn_softNMSBoxes } from '@banou/opencv-wasm'

Use after await initOpenCV(). See the initialization and named imports guide.

Explore visually: Non-maximum suppression →

Reduce overlapping detector proposals by retaining the most useful scored boxes.

VISUAL WALKTHROUGHDetection

REFERENCE INPUTOverlapping detections

Three boxes cover one object; another box covers a separate object.

→

RESULTTwo detections remain

Greedy hard NMS keeps the strongest overlapping box and the separate object. Soft-NMS instead adjusts competing scores.

Illustrative example. The stages explain the method; they are not a live OpenCV execution.

Performs soft non maximum suppression given boxes and corresponding scores. Reference: https://arxiv.org/abs/1704.04503

See: SoftNMSMethod

dnn_softNMSBoxes(bboxes: RectVector, scores: FloatVector, updated_scores: FloatVector, score_threshold: number, nms_threshold: number, indices: IntVector, top_k: number, sigma: number, method: number): void;

4 available overloads

dnn_softNMSBoxes(bboxes: RectVector, scores: FloatVector, updated_scores: FloatVector, score_threshold: number, nms_threshold: number, indices: IntVector): void;

dnn_softNMSBoxes(bboxes: RectVector, scores: FloatVector, updated_scores: FloatVector, score_threshold: number, nms_threshold: number, indices: IntVector, top_k: number): void;

dnn_softNMSBoxes(bboxes: RectVector, scores: FloatVector, updated_scores: FloatVector, score_threshold: number, nms_threshold: number, indices: IntVector, top_k: number, sigma: number): void;

dnn_softNMSBoxes(bboxes: RectVector, scores: FloatVector, updated_scores: FloatVector, score_threshold: number, nms_threshold: number, indices: IntVector, top_k: number, sigma: number, method: number): void;

bboxes

a set of bounding boxes to apply Soft NMS.

scores

a set of corresponding confidences.

updated_scores

Output destination, filled by the native operation. a set of corresponding updated confidences.

score_threshold

a threshold used to filter boxes by score.

nms_threshold

a threshold used in non maximum suppression.

indices

Output destination, filled by the native operation. the kept indices of bboxes after NMS.

top_k

keep at most top_k picked indices.

sigma

parameter of Gaussian weighting.

method

Gaussian or linear.

Upstream declaration ↗

These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.