yolo26obbtensordec

Tensor decoder element for Yolo oriented bounding box detection. This supports YoloV10-obb, Yolo11-obb, Yolo12-obb and Yolo26-obb but only the one-to-one (end2end, NMS) heads.

Test image file, model file and labels file can be found here : https://gitlab.collabora.com/gstreamer/onnx-models

 gst-launch-1.0 v4l2src ! videorate max-rate=3 ! videoconvertscale \
  ! onnxinference  model-file=yolo26n-obb-e2e.onnx \
  ! yolo26obbtensordec score-threshold=0.8 label-file=labels/DOTAv1.txt \
  ! objectdetectionoverlay \
  ! glimagesink sink="gtkglsink processing-deadline=300000000"

This takes webcam input, performs oriented object bounding box detection via onnxinference on it, decodes the inferred tensors with yolo26obbtensordec and then overlays the detected objects on the frame via objectdetectionoverlay.

Hierarchy

GObject
    ╰──GInitiallyUnowned
        ╰──GstObject
            ╰──GstElement
                ╰──GstBaseTransform
                    ╰──GstYoloTensorDec
                        ╰──yolo26obbtensordec

Factory details

Authors: – Jan Schmidt

Classification: – Tensordecoder/Video

Rank – primary + 1

Plugin – rsanalytics

Package – gst-plugin-analytics

Pad Templates

sink

video/x-raw(ANY):
         format: { AYUV_F32, RGBA_F32LE, ARGB_F32, RGBA_F32BE, A444_16LE, A444_16BE, Y416_LE, AYUV64, RGBA64_LE, ARGB64, ARGB64_LE, BGRA64_LE, ABGR64_LE, Y416_BE, RGBA64_BE, ARGB64_BE, BGRA64_BE, ABGR64_BE, A422_16LE, A422_16BE, A420_16LE, A420_16BE, A444_12LE, GBRA_12LE, A444_12BE, GBRA_12BE, Y412_LE, Y412_BE, A422_12LE, A422_12BE, A420_12LE, A420_12BE, RGBA_F16LE, RGBA_F16BE, A444_10LE, GBRA_10LE, A444_10BE, GBRA_10BE, A422_10LE, A422_10BE, A420_10LE, A420_10BE, BGR10A2_LE, RGB10A2_LE, Y410, A444, GBRA, AYUV, VUYA, RGBA, RBGA, ARGB, BGRA, ABGR, A422, A420, AV12, RGBP_F32LE, RGBP_F32BE, RGB_F32LE, RGB_F32BE, Y444_16LE, GBR_16LE, Y444_16BE, GBR_16BE, Y216_LE, Y216_BE, v216, P016_LE, P016_BE, Y444_12LE, GBR_12LE, Y444_12BE, GBR_12BE, I422_12LE, I422_12BE, Y212_LE, Y212_BE, I420_12LE, I420_12BE, P012_LE, P012_BE, RGBP_F16LE, RGBP_F16BE, RGB_F16LE, RGB_F16BE, Y444_10LE, GBR_10LE, Y444_10BE, GBR_10BE, BGR10x2_LE, RGB10x2_LE, r210, I422_10LE, I422_10BE, NV16_10LE40, NV16_10LE32, Y210, UYVP, v210, I420_10LE, I420_10BE, P010_10LE, NV12_10LE40, NV12_10LE32, P010_10BE, MT2110R, MT2110T, NV12_10BE_8L128, NV12_10LE40_4L4, Y444, BGRP, GBR, RGBP, NV24, v308, IYU2, RGBx, xRGB, BGRx, xBGR, RGB, BGR, Y42B, NV16, NV61, YUY2, YVYU, UYVY, VYUY, I420, YV12, NV12, NV21, NV12_16L32S, NV12_32L32, NV12_4L4, NV12_64Z32, NV12_8L128, Y41B, IYU1, YUV9, YVU9, BGR16, RGB16, BGR15, RGB15, RGB8P, GRAY_F32LE, GRAY_F32BE, GRAY16_LE, GRAY16_BE, GRAY_F16LE, GRAY_F16BE, GRAY10_LE16, GRAY10_LE32, GRAY8 }
          width: [ 1, 2147483647 ]
         height: [ 1, 2147483647 ]
      framerate: [ 0/1, 2147483647/1 ]
        tensors: "tensorgroups\,\ yolo-26-obb-end2end-out\=\(/uniquelist\)\{\ \(caps\)\"tensor/strided\\\,\\\ tensor-id\\\=\\\(string\\\)yolo-26-obb-end2end-out\\\,\\\ dims\\\=\\\(int\\\)\\\<\\\ 1\\\,\\\ \\\[\\\ 1\\\,\\\ 2147483647\\\ \\\]\\\,\\\ 7\\\ \\\>\\\,\\\ dims-order\\\=\\\(string\\\)row-major\\\,\\\ type\\\=\\\(string\\\)float32\"\ \}\;"

Presence – always

Direction – sink

Object type – GstPad


src

video/x-raw(ANY):
         format: { AYUV_F32, RGBA_F32LE, ARGB_F32, RGBA_F32BE, A444_16LE, A444_16BE, Y416_LE, AYUV64, RGBA64_LE, ARGB64, ARGB64_LE, BGRA64_LE, ABGR64_LE, Y416_BE, RGBA64_BE, ARGB64_BE, BGRA64_BE, ABGR64_BE, A422_16LE, A422_16BE, A420_16LE, A420_16BE, A444_12LE, GBRA_12LE, A444_12BE, GBRA_12BE, Y412_LE, Y412_BE, A422_12LE, A422_12BE, A420_12LE, A420_12BE, RGBA_F16LE, RGBA_F16BE, A444_10LE, GBRA_10LE, A444_10BE, GBRA_10BE, A422_10LE, A422_10BE, A420_10LE, A420_10BE, BGR10A2_LE, RGB10A2_LE, Y410, A444, GBRA, AYUV, VUYA, RGBA, RBGA, ARGB, BGRA, ABGR, A422, A420, AV12, RGBP_F32LE, RGBP_F32BE, RGB_F32LE, RGB_F32BE, Y444_16LE, GBR_16LE, Y444_16BE, GBR_16BE, Y216_LE, Y216_BE, v216, P016_LE, P016_BE, Y444_12LE, GBR_12LE, Y444_12BE, GBR_12BE, I422_12LE, I422_12BE, Y212_LE, Y212_BE, I420_12LE, I420_12BE, P012_LE, P012_BE, RGBP_F16LE, RGBP_F16BE, RGB_F16LE, RGB_F16BE, Y444_10LE, GBR_10LE, Y444_10BE, GBR_10BE, BGR10x2_LE, RGB10x2_LE, r210, I422_10LE, I422_10BE, NV16_10LE40, NV16_10LE32, Y210, UYVP, v210, I420_10LE, I420_10BE, P010_10LE, NV12_10LE40, NV12_10LE32, P010_10BE, MT2110R, MT2110T, NV12_10BE_8L128, NV12_10LE40_4L4, Y444, BGRP, GBR, RGBP, NV24, v308, IYU2, RGBx, xRGB, BGRx, xBGR, RGB, BGR, Y42B, NV16, NV61, YUY2, YVYU, UYVY, VYUY, I420, YV12, NV12, NV21, NV12_16L32S, NV12_32L32, NV12_4L4, NV12_64Z32, NV12_8L128, Y41B, IYU1, YUV9, YVU9, BGR16, RGB16, BGR15, RGB15, RGB8P, GRAY_F32LE, GRAY_F32BE, GRAY16_LE, GRAY16_BE, GRAY_F16LE, GRAY_F16BE, GRAY10_LE16, GRAY10_LE32, GRAY8 }
          width: [ 1, 2147483647 ]
         height: [ 1, 2147483647 ]
      framerate: [ 0/1, 2147483647/1 ]

Presence – always

Direction – src

Object type – GstPad


Properties

score-threshold

“score-threshold” gfloat

Detections with a score inferior to this threshold will be excluded

Flags : Read / Write

Default value : 0.3


The results of the search are