Build an OpenCV YOLOX pipeline to benchmark KleidiCV preprocessing
Introduction
Understand YOLOX and KleidiCV in the detection pipeline
Build OpenCV with and without KleidiCV
Prepare the YOLOX model and test image
Compile and run YOLOX static-image detection
Evaluate KleidiCV preprocessing and pipeline performance
Next Steps
Build an OpenCV YOLOX pipeline to benchmark KleidiCV preprocessing
Who is this for?
This is an advanced topic for C++ developers who want to deploy ONNX computer vision models and measure image-processing performance on arm64 Linux boards.
What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Build matching baseline and default KleidiCV versions of OpenCV.
- Deploy a YOLOX ONNX model and label objects in a static image.
- Compare image-operation, full preprocessing, and pipeline latency to distinguish local optimization from application-level improvement.
Prerequisites
Before starting, you'll need the following prerequisites:
- An arm64 development board running 64-bit Debian or Ubuntu
- At least 12 GB of free storage for two OpenCV builds
- GCC 10 or later, or Clang 12 or later
- Familiarity with C++, CMake, and the Linux command line
- Time for source downloads and two OpenCV compilations in addition to the 90-minute hands-on estimate
Summary
This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
You’ll build a YOLOX static-image detection pipeline on an arm64 Linux board and compare preprocessing with and without KleidiCV. First, you’ll identify the pipeline stages, then build matching OpenCV installations and prepare the model, labels, and image. You’ll compile and run the C++ application against both builds. Finally, you’ll check its detections, and benchmark image operations, full preprocessing, and in-memory pipeline latency under consistent conditions.