Perceive the world by predicting!
基于StreamYOLO的实时通用检测模型,支持8类交通目标检测。StreamYOLO基于YOLOX模型,使用Dual-Flow Perception特征融合模块,learns 特征层面的时序关系,提高环境感知预测的能力。与此同时,StreamYOLO设计了一个Trend-Aware Loss 去感知物体运动变化强度,用以加权物体预测的回归,使运动剧烈变化物体获得更高的回归权重,从而获得更好的预测结果。
开始你的模型探索之旅!
Play the model with a few line codes !
import cv2
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys
model_id = 'damo/cv_cspnet_video-object-detection_streamyolo'
test_video = 'https://modelscope.oss-cn-beijing.aliyuncs.com/test/videos/test_realtime_vod.mp4'
# 初始化实时检测pipeline
realtime_video_object_detection = pipeline(
Tasks.video_object_detection, model=model_id)
# 进行实时检测
result = realtime_video_object_detection(test_video)
if result:
bboxes_list = result[OutputKeys.BOXES]
print(bboxes_list)
else:
raise ValueError('process error')
Argoverse-HD 数据集是最近提出的自动驾驶数据集,该数据集与其他的自动驾驶相比,数据规模中等,复杂程度较高,是一个较有代表性的数据集。更重要的是,Argoverse-HD 是第一个提出流感知任务的数据集,并且设计了Stream AP评测标准。该标准将感知时延充分考虑,实现对模型的性能-速度的全面、有效评价。
本模型暂时不支持finetune, 具体离线训练细节如下:
Model | size | velocity | sAP 0.5:0.95 |
sAP50 | sAP75 | weights | COCO pretrained weights |
---|---|---|---|---|---|---|---|
StreamYOLO-l | 600×960 | 1x | 36.9 | 58.1 | 37.5 | official | official |
@inproceedings{streamyolo,
title={Real-time Object Detection for Streaming Perception},
author={Yang, Jinrong and Liu, Songtao and Li, Zeming and Li, Xiaoping and Sun, Jian},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={5385--5395},
year={2022}
}
@article{yang2022streamyolo,
title={StreamYOLO: Real-time Object Detection for Streaming Perception},
author={Yang, Jinrong and Liu, Songtao and Li, Zeming and Li, Xiaoping and Sun, Jian},
journal={arXiv preprint arXiv:2207.10433},
year={2022}
}