운전자 이상행동 감지를 위한 Video Swin Transformer 기반 모델입니다.
1import torch
2from model import DriverBehaviorModel
3
4model = DriverBehaviorModel(num_classes=5, pretrained=False)
5checkpoint = torch.load("pytorch_model.bin", map_location="cpu")
6model.load_state_dict(checkpoint["model"])
7model.eval()
1// build.gradle
2implementation 'com.microsoft.onnxruntime:onnxruntime-android:1.16.0'
3
4// Kotlin
5val session = OrtEnvironment.getEnvironment()
6 .createSession(assetManager.open("model.onnx").readBytes())
7
8val output = session.run(mapOf("video_input" to inputTensor))
Input Shape: [1, 3, 30, 224, 224] (batch, channels, frames, height, width)
Channel Order: RGB
Normalization: (pixel / 255.0 - mean) / std
- mean = [0.485, 0.456, 0.406]
- std = [0.229, 0.224, 0.225]
Resize: 224x224 (BILINEAR)
Frames: 30 frames uniformly sampled
This model is for research purposes only.
@misc{driver-behavior-detection-2026,
title={Driver Behavior Detection using Video Swin Transformer},
author={C-Team},
year={2026}
}
