Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
chihy ff6f9b2381 | 2 years ago | |
---|---|---|
.idea | 2 years ago | |
net | 2 years ago | |
0251.jpg | 2 years ago | |
dehaze_api_test.py | 2 years ago | |
readme.md | 2 years ago | |
requirements.txt | 2 years ago | |
test_CID.png | 2 years ago |
PCID-Net:Peng Cheng Image Dehazing Network
1.0
针对雾天采集的交通场景图片及视频,引入自动去雾能力,对图片及视频进行增强。
请参考 requirements.txt
主要面向受大雾影响的交通场景图片,其他带雾日常图片亦可。
输出图像可提高检测算法在大雾场景下的检测准确率。对于带雾图片,先经本算法的去雾,后再经过检测算法,检测结果会有提升。
一般正常的带雾图像也可输入进行去雾操作,但是本算法不以视觉质量提升为目标,输出图像可能会有亮度对比度风格等调整。
from net.api import DehazingNet
dehaze_net = DehazingNet()
dehaze_img = dehaze_net.dehaze(haze_img)
参数 | 类型 | 是否必填 | 说明 |
---|---|---|---|
haze_img | PIL.Image.Image 或 ndarray | 是 | 维度为(H,W,C)的图片,通道类型为RGB, 图片长宽应大于50*50 |
参数 | 类型 | 说明 |
---|---|---|
dehaze_img | Tensor(torch.float32) | 维度为(c,h,w)的tensor,通道类型为RGB |
from PIL import Image
from net.api import DehazingNet
import torchvision.utils as vutils
haze_img = Image.open('0251.jpg')
dehaze_net = DehazingNet()
dehaze_img = dehaze_net.dehaze(haze_img)
vutils.save_image(dehaze_img, 'test_CID.png')
针对交通道路雾天采集的交通场景图片及视频,引入自动去雾能力,对图片及视频进行增强
Python MATLAB Shell Text Markdown
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》