feat: initial HSAP platform

Huaxu Sentinel Active Safety Platform with embedded algorithm code,
Docker Compose setup, and vendored dataset scaffolds for clone-and-run.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-05-25 16:59:59 +08:00
commit 7c43b44c57
1619 changed files with 373355 additions and 0 deletions

View File

@@ -0,0 +1,14 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
[package]
name = "YOLO-ONNXRuntime-Rust"
version = "0.1.0"
edition = "2021"
authors = ["Jamjamjon <xxyydzml@outlook.com>"]
[dependencies]
anyhow = "1.0.92"
clap = "4.5.20"
tracing = "0.1.40"
tracing-subscriber = "0.3.18"
usls = { version = "0.0.19", features = ["auto"] }

View File

@@ -0,0 +1,100 @@
# YOLO-Series ONNXRuntime Rust Demo for Core YOLO Tasks
This repository provides a [Rust](https://rust-lang.org/) demo showcasing key [Ultralytics YOLO](https://docs.ultralytics.com/) series tasks such as [Classification](https://docs.ultralytics.com/tasks/classify/), [Segmentation](https://docs.ultralytics.com/tasks/segment/), [Detection](https://docs.ultralytics.com/tasks/detect/), [Pose Estimation](https://docs.ultralytics.com/tasks/pose/), and Oriented Bounding Box ([OBB](https://docs.ultralytics.com/tasks/obb/)) detection using the [ONNXRuntime](https://github.com/microsoft/onnxruntime). It supports various YOLO models (YOLOv5 through YOLO11) across multiple computer vision tasks.
## ✨ Introduction
- This example leverages the latest versions of both the [ONNX Runtime](https://onnxruntime.ai/) and popular YOLO models.
- We utilize the [usls crate](https://github.com/jamjamjon/usls/tree/main) to streamline YOLO model inference in Rust, providing efficient data loading, visualization, and optimized inference performance. This allows developers to easily integrate state-of-the-art object detection into their Rust applications.
## 🚀 Features
- **Extensive Model Compatibility**: Supports a wide range of YOLO versions including [YOLOv5](https://docs.ultralytics.com/models/yolov5/), [YOLOv6](https://docs.ultralytics.com/models/yolov6/), [YOLOv7](https://docs.ultralytics.com/models/yolov7/), [YOLOv8](https://docs.ultralytics.com/models/yolov8/), [YOLOv9](https://docs.ultralytics.com/models/yolov9/), [YOLOv10](https://docs.ultralytics.com/models/yolov10/), [YOLO11](https://docs.ultralytics.com/models/yolo11/), [YOLO-World](https://docs.ultralytics.com/models/yolo-world/), [RT-DETR](https://docs.ultralytics.com/models/rtdetr/), and others.
- **Versatile Task Coverage**: Includes examples for `Classification`, `Segmentation`, `Detection`, `Pose`, and `OBB`.
- **Precision Flexibility**: Works seamlessly with `FP16` and `FP32` precision [ONNX models](https://docs.ultralytics.com/integrations/onnx/).
- **Execution Providers**: Accelerated support for `CPU`, [CUDA](https://developer.nvidia.com/cuda-toolkit), [CoreML](https://developer.apple.com/documentation/coreml), and [TensorRT](https://docs.ultralytics.com/integrations/tensorrt/).
- **Dynamic Input Shapes**: Dynamically adjusts to variable `batch`, `width`, and `height` dimensions for flexible model input.
- **Flexible Data Loading**: The `DataLoader` component handles images, folders, videos, and real-time video streams.
- **Real-Time Display and Video Export**: The `Viewer` provides real-time frame visualization and video export functions, similar to OpenCVs `imshow()` and `imwrite()`.
- **Enhanced Annotation and Visualization**: The `Annotator` facilitates comprehensive result rendering, supporting bounding boxes (HBB), oriented bounding boxes (OBB), polygons, masks, keypoints, and text labels.
## 🛠️ Setup Instructions
### 1. ONNXRuntime Linking
<details>
<summary>You have two options to link the ONNXRuntime library:</summary>
- **Option 1: Manual Linking**
- For detailed setup instructions, consult the [ONNX Runtime linking documentation](https://ort.pyke.io/setup/linking).
- **Linux or macOS**:
1. Download the appropriate ONNX Runtime package from the official [Releases page](https://github.com/microsoft/onnxruntime/releases).
2. Set up the library path by exporting the `ORT_DYLIB_PATH` environment variable, pointing to the downloaded library file:
```bash
# Example path, replace with your actual path
export ORT_DYLIB_PATH=/path/to/onnxruntime/lib/libonnxruntime.so.1.19.0
```
- **Option 2: Automatic Download**
- Use the `--features auto` flag with Cargo to let the build script handle downloading the library automatically:
```bash
cargo run -r --example yolo --features auto
```
</details>
### 2. [Optional] Install CUDA, CuDNN, and TensorRT
- The CUDA execution provider requires [NVIDIA CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit) version `12.x`.
- The TensorRT execution provider requires both CUDA `12.x` and [NVIDIA TensorRT](https://developer.nvidia.com/tensorrt) `10.x`. Ensure [cuDNN](https://developer.nvidia.com/cudnn) is also correctly installed.
### 3. [Optional] Install ffmpeg
To enable viewing video frames and saving video inferences, install the `rust-ffmpeg` crate's dependencies. Follow the instructions provided here:
[https://github.com/zmwangx/rust-ffmpeg/wiki/Notes-on-building#dependencies](https://github.com/zmwangx/rust-ffmpeg/wiki/Notes-on-building#dependencies)
## ▶️ Get Started
Run the examples using Cargo. The `--` separates Cargo arguments from the example's arguments.
```bash
# Run a custom model (e.g., YOLOv8 detection)
cargo run -r -- --task detect --ver v8 --nc 6 --model path/to/your/model.onnx
# Classify examples
cargo run -r -- --task classify --ver v5 --scale s --width 224 --height 224 --nc 1000 # YOLOv5 Classification
cargo run -r -- --task classify --ver v8 --scale n --width 224 --height 224 --nc 1000 # YOLOv8 Classification
cargo run -r -- --task classify --ver v11 --scale n --width 224 --height 224 --nc 1000 # YOLO11 Classification
# Detect examples
cargo run -r -- --task detect --ver v5 --scale n # YOLOv5 Detection
cargo run -r -- --task detect --ver v6 --scale n # YOLOv6 Detection
cargo run -r -- --task detect --ver v7 --scale t # YOLOv7 Detection
cargo run -r -- --task detect --ver v8 --scale n # YOLOv8 Detection
cargo run -r -- --task detect --ver v9 --scale t # YOLOv9 Detection
cargo run -r -- --task detect --ver v10 --scale n # YOLOv10 Detection
cargo run -r -- --task detect --ver v11 --scale n # YOLO11 Detection
cargo run -r -- --task detect --ver rtdetr --scale l # RT-DETR Detection
# Pose examples
cargo run -r -- --task pose --ver v8 --scale n # YOLOv8-Pose Estimation
cargo run -r -- --task pose --ver v11 --scale n # YOLO11-Pose Estimation
# Segment examples
cargo run -r -- --task segment --ver v5 --scale n # YOLOv5-Segment
cargo run -r -- --task segment --ver v8 --scale n # YOLOv8-Segment
cargo run -r -- --task segment --ver v11 --scale n # YOLO11-Segment
cargo run -r -- --task segment --ver v8 --model path/to/FastSAM-s-dyn-f16.onnx # FastSAM Segmentation
# OBB (Oriented Bounding Box) examples
cargo run -r -- --ver v8 --task obb --scale n --width 1024 --height 1024 --source images/dota.png # YOLOv8-OBB
cargo run -r -- --ver v11 --task obb --scale n --width 1024 --height 1024 --source images/dota.png # YOLO11-OBB
```
**Use `cargo run -- --help` to see all available options.**
For more detailed information and advanced usage, please refer to the [usls-yolo example documentation](https://github.com/jamjamjon/usls/tree/main/examples/yolo).
## 🤝 Contributing
Contributions are welcome! If you'd like to improve this demo or add new features, please feel free to submit issues or pull requests on the repository. Your input helps make the Ultralytics ecosystem better for everyone. Check out the [Ultralytics Contribution Guide](https://docs.ultralytics.com/help/contributing/) for more details.

View File

@@ -0,0 +1,238 @@
// Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
use anyhow::Result;
use clap::Parser;
use usls::{
models::YOLO, Annotator, DataLoader, Device, Options, Viewer, Vision, YOLOScale, YOLOTask,
YOLOVersion, COCO_SKELETONS_16,
};
#[derive(Parser, Clone)]
#[command(author, version, about, long_about = None)]
pub struct Args {
/// Path to the ONNX model
#[arg(long)]
pub model: Option<String>,
/// Input source path
#[arg(long, default_value_t = String::from("../../ultralytics/assets/bus.jpg"))]
pub source: String,
/// YOLO Task
#[arg(long, value_enum, default_value_t = YOLOTask::Detect)]
pub task: YOLOTask,
/// YOLO Version
#[arg(long, value_enum, default_value_t = YOLOVersion::V8)]
pub ver: YOLOVersion,
/// YOLO Scale
#[arg(long, value_enum, default_value_t = YOLOScale::N)]
pub scale: YOLOScale,
/// Batch size
#[arg(long, default_value_t = 1)]
pub batch_size: usize,
/// Minimum input width
#[arg(long, default_value_t = 224)]
pub width_min: isize,
/// Input width
#[arg(long, default_value_t = 640)]
pub width: isize,
/// Maximum input width
#[arg(long, default_value_t = 1024)]
pub width_max: isize,
/// Minimum input height
#[arg(long, default_value_t = 224)]
pub height_min: isize,
/// Input height
#[arg(long, default_value_t = 640)]
pub height: isize,
/// Maximum input height
#[arg(long, default_value_t = 1024)]
pub height_max: isize,
/// Number of classes
#[arg(long, default_value_t = 80)]
pub nc: usize,
/// Class confidence
#[arg(long)]
pub confs: Vec<f32>,
/// Enable TensorRT support
#[arg(long)]
pub trt: bool,
/// Enable CUDA support
#[arg(long)]
pub cuda: bool,
/// Enable CoreML support
#[arg(long)]
pub coreml: bool,
/// Use TensorRT half precision
#[arg(long)]
pub half: bool,
/// Device ID to use
#[arg(long, default_value_t = 0)]
pub device_id: usize,
/// Enable performance profiling
#[arg(long)]
pub profile: bool,
/// Disable contour drawing, for saving time
#[arg(long)]
pub no_contours: bool,
/// Show result
#[arg(long)]
pub view: bool,
/// Do not save output
#[arg(long)]
pub nosave: bool,
}
fn main() -> Result<()> {
let args = Args::parse();
// logger
if args.profile {
tracing_subscriber::fmt()
.with_max_level(tracing::Level::INFO)
.init();
}
// model path
let path = match &args.model {
None => format!(
"yolo/{}-{}-{}.onnx",
args.ver.name(),
args.scale.name(),
args.task.name()
),
Some(x) => x.to_string(),
};
// saveout
let saveout = match &args.model {
None => format!(
"{}-{}-{}",
args.ver.name(),
args.scale.name(),
args.task.name()
),
Some(x) => {
let p = std::path::PathBuf::from(&x);
p.file_stem().unwrap().to_str().unwrap().to_string()
}
};
// device
let device = if args.cuda {
Device::Cuda(args.device_id)
} else if args.trt {
Device::Trt(args.device_id)
} else if args.coreml {
Device::CoreML(args.device_id)
} else {
Device::Cpu(args.device_id)
};
// build options
let options = Options::new()
.with_model(&path)?
.with_yolo_version(args.ver)
.with_yolo_task(args.task)
.with_device(device)
.with_trt_fp16(args.half)
.with_ixx(0, 0, (1, args.batch_size as _, 4).into())
.with_ixx(0, 2, (args.height_min, args.height, args.height_max).into())
.with_ixx(0, 3, (args.width_min, args.width, args.width_max).into())
.with_confs(if args.confs.is_empty() {
&[0.2, 0.15]
} else {
&args.confs
})
.with_nc(args.nc)
.with_find_contours(!args.no_contours) // find contours or not
// .with_names(&COCO_CLASS_NAMES_80) // detection class names
// .with_names2(&COCO_KEYPOINTS_17) // keypoints class names
// .exclude_classes(&[0])
// .retain_classes(&[0, 5])
.with_profile(args.profile);
// build model
let mut model = YOLO::new(options)?;
// build dataloader
let dl = DataLoader::new(&args.source)?
.with_batch(model.batch() as _)
.build()?;
// build annotator
let annotator = Annotator::default()
.with_skeletons(&COCO_SKELETONS_16)
.without_masks(true) // no masks plotting when doing segment task
.with_bboxes_thickness(3)
.with_keypoints_name(false) // enable keypoints names
.with_saveout_subs(&["YOLO"])
.with_saveout(&saveout);
// build viewer
let mut viewer = if args.view {
Some(Viewer::new().with_delay(5).with_scale(1.).resizable(true))
} else {
None
};
// run & annotate
for (xs, _paths) in dl {
let ys = model.forward(&xs, args.profile)?;
let images_plotted = annotator.plot(&xs, &ys, !args.nosave)?;
// show image
match &mut viewer {
Some(viewer) => viewer.imshow(&images_plotted)?,
None => continue,
}
// check out window and key event
match &mut viewer {
Some(viewer) => {
if !viewer.is_open() || viewer.is_key_pressed(usls::Key::Escape) {
break;
}
}
None => continue,
}
// write video
if !args.nosave {
match &mut viewer {
Some(viewer) => viewer.write_batch(&images_plotted)?,
None => continue,
}
}
}
// finish video write
if !args.nosave {
if let Some(viewer) = &mut viewer {
viewer.finish_write()?;
}
}
Ok(())
}