--- title: Effortless GStreamer Analytics Cross-Platform Support... description: Collabora redesigned GStreamer's ONNX plugin to support a broader range of AI analytics workflows. The refactor splits responsibilities across three new... canonical: https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Effortless GStreamer Analytics Cross-Platform Support via ONNX Runtime | daily.dev og:description: Collabora redesigned GStreamer's ONNX plugin to support a broader range of AI analytics workflows. The refactor splits responsibilities across three new... og:url: https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm og:image: https://api.daily.dev/og/posts/O0GIwXotM.png og:image:alt: Effortless GStreamer Analytics Cross-Platform Support via ONNX Runtime og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Effortless GStreamer Analytics Cross-Platform Support via ONNX Runtime **[Collabora Blog](https://daily.dev/sources/collabora)** · 3 min read · 0 upvotes · 0 comments ## Summary Collabora redesigned GStreamer's ONNX plugin to support a broader range of AI analytics workflows. The refactor splits responsibilities across three new elements: `onnxinference` handles generic ONNX model inference and attaches tensor outputs via the new `GstTensorMeta` metadata object; `ssdobjectdetector` acts as a simpler tensor decoder for SSD object detection; and `objectdetectionoverlay` renders bounding boxes and labels. This architecture makes it straightforward to add new tensor decoders for different AI models and to plug in alternative inference engines like TensorFlow Lite or PyTorch. ONNX Runtime supports inference across x86/ARM CPUs, NVIDIA/AMD/Intel GPUs, and AMD FPGAs via its execution providers. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I run ONNX model inference in a GStreamer pipeline? Use the `onnxinference` element, specifying an execution provider and model file. It runs inference and attaches tensor outputs to outgoing buffers via `GstTensorMeta`. A downstream `ssdobjectdetector` element decodes the tensors, and `objectdetectionoverlay` renders bounding boxes. For example: `gst-launch-1.0 multifilesrc location=image.jpg ! jpegdec ! videoconvert ! onnxinference execution-provider=cpu model-file=model.onnx ! ssdobjectdetector label-file=labels.txt ! objectdetectionoverlay ! videoconvert ! autovideosink`. _Engineers building GStreamer ML pipelines track plugin architecture changes like this on daily.dev._ ### What hardware does ONNX Runtime support for inference execution providers? ONNX Runtime supports inference across x86 and ARM CPUs, NVIDIA, AMD, and Intel GPUs, and AMD FPGAs through its execution providers. Additional providers are available from vendor repositories beyond the upstream list. This broad hardware coverage makes it suitable as a cross-platform inference backend inside frameworks like GStreamer. _Teams choosing an inference backend for embedded or GPU hardware weigh options like these on daily.dev._ ## Similar posts on daily.dev - [AMD Contributes ONNX Runtime Backend To FFmpeg DNN Filter](https://daily.dev/posts/amd-contributes-onnx-runtime-backend-to-ffmpeg-dnn-filter-zrjcdjg7v) · Phoronix · 5 upvotes · 0 comments - [Build Portable ML Models with ONNX](https://daily.dev/posts/build-portable-ml-models-with-onnx-vy4ol05iy) · Daily Dose of Data Science \| Avi Chawla \| Substack · 7 upvotes · 0 comments - [Build Local AI Apps with C\+\+ and NVIDIA TensorRT RTX Samples](https://daily.dev/posts/build-local-ai-apps-with-c-and-nvidia-tensorrt-rtx-samples-aufd3cqlp) · NVIDIA Developer · 1 upvotes · 0 comments - [New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations](https://daily.dev/posts/new-dnn-engine-with-enhanced-onnx-and-llm-vlm-support-intel-arm-and-risc-v-hardware-optimizations-5jrhxdsuq) · CNX Software · 0 upvotes · 0 comments --- Tags: [#object-detection](https://daily.dev/tags/object-detection) [View this post on daily.dev](https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Effortless GStreamer Analytics Cross-Platform Support via ONNX Runtime","url":"https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm"},"datePublished":"2026-08-11T08:52:36.825Z","dateModified":"2026-08-11T09:08:01.145Z","description":"Collabora redesigned GStreamer's ONNX plugin to support a broader range of AI analytics workflows. The refactor splits responsibilities across three new...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ac23ce571f0b35d836dbe9ec90966c8a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ac23ce571f0b35d836dbe9ec90966c8a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collabora Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collabora Blog","logo":"https://media.daily.dev/image/upload/s--ZGZ0FjqS--/f_auto,q_auto/v1786438306/logos/collabora?_a=BAMAMicg0","url":"https://daily.dev/sources/collabora"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"object-detection","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collabora Blog","item":"https://daily.dev/sources/collabora"},{"@type":"ListItem","position":3,"name":"Effortless GStreamer Analytics Cross-Platform Support via ONNX Runtime"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/effortless-gstreamer-analytics-cross-platform-support-via-onnx-runtime-o0giwxotm#faq","mainEntity":[{"@type":"Question","name":"How do I run ONNX model inference in a GStreamer pipeline?","acceptedAnswer":{"@type":"Answer","text":"Use the `onnxinference` element, specifying an execution provider and model file. It runs inference and attaches tensor outputs to outgoing buffers via `GstTensorMeta`. A downstream `ssdobjectdetector` element decodes the tensors, and `objectdetectionoverlay` renders bounding boxes. For example: `gst-launch-1.0 multifilesrc location=image.jpg ! jpegdec ! videoconvert ! onnxinference execution-provider=cpu model-file=model.onnx ! ssdobjectdetector label-file=labels.txt ! objectdetectionoverlay ! videoconvert ! autovideosink`. Engineers building GStreamer ML pipelines track plugin architecture changes like this on daily.dev."}},{"@type":"Question","name":"What hardware does ONNX Runtime support for inference execution providers?","acceptedAnswer":{"@type":"Answer","text":"ONNX Runtime supports inference across x86 and ARM CPUs, NVIDIA, AMD, and Intel GPUs, and AMD FPGAs through its execution providers. Additional providers are available from vendor repositories beyond the upstream list. This broad hardware coverage makes it suitable as a cross-platform inference backend inside frameworks like GStreamer. Teams choosing an inference backend for embedded or GPU hardware weigh options like these on daily.dev."}}]} ```