visdrone / dronevehicle Goto Github PK
View Code? Open in Web Editor NEWDrone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning
Hi,
how can I download the dataset? Baidu forces me to install some tool with registration. I do not speak Chinese, so I cannot follow what to do. Thank you
I'm Trying to download the dataset through baidu link but it seems that baidu website is not working outside china, so if you could provide alternative link, Please
白天、夜晚、无光夜晚的场景类型标注对图片的可靠性有参考性,很需要,但找不到标签。我在论文中看到对三种场景的个数有统计,应该有标注,不知道为啥下载的数据集里没有。
13个月啦
Where is data?
请问什么时候公布数据集
请问啥时候能公布数据集?鸽子王都没你能鸽
1.你们的热成像图拍的时候选择的白热还是黑热?
2.热成像图与rgb图是怎么处理对齐问题的? 有开源处理对齐问题的代码吗?
Thank you for your contribution to the previous datasets, and look forward to the release of this dataset as soon as possible!
Thank you very much for your great work.
I am wondering why SMO and MA can be applied to the IR modality in Table V, since Winf = 1 and there is no misalignment weight for the IR modality.
Besides, it would be very much appreciated if you can tell me what instances are used for calculating mAP? Is it all instances from RGB and IR annotations, filtered with NMS?
感谢您的精彩工作。
我很好奇论文中表V里,为什么SMO和MA可以用在IR波段上,因为Winf是1,也就是SMO不对IR中没有标注的目标加上权重,而且IR波段好像也没有不配准的权重。
另外,能否告知哪些目标用于计算mAP?是RGB和IR标注中所有的目标整合在一起,用NMS过滤一下吗?非常感谢!
Hello, I think this is a good work!
It is May now. When can I download it?
When uploading the dataset?I want to use your dataset for research.
2020/9/20
数据出现两种不同的格式,四点式和八点式
Hi thank you for your work! Are we still getting a Google drive link for the dataset?
What camera(RGB&IR) do you use in this datasets?
GoogleDrive:
googledrive link will be released soon.
Can anyone load dataset to the google drive?
how to convert the annotations to train with yolov5?
Thank you again for this great dataset.
When I work on DroneVehicle, I find it hard to distinguish between truck, van, and freight-car by myself as a human. In the bottom right corner of image 08966.jpg in the test set, there is a line of freight-cars. However, they seem a bit more like vans to me. For trucks and freight-cars, it seems that a freight-car always has a container on its back, while a truck does not. Am I correct?
Therefore, I would like to ask -- what is the definition of truck, van, and freight-car?
Thank you very much!
再次感谢这个数据集。
我做实验的时候,发现肉眼很难辨别truck, van和freight-car这三个类别。比如在测试集里08966.jpg图像的右下角有一排freight-car,但是看起来有一点点像van。对truck和freight-car来说,是不是freight-car背后一定有一个集装箱,而truck没有?
所以我想问一下,truck,van和freight-car具体是怎么定义的?
非常感谢!
请问这是什么原因造成的
数据集Train 和test部分的百度网盘提取码好像是错的,用不了了,麻烦改下,谢谢。
我觉得这个数据集很有意义,非常感谢你们的工作。请问什么时候可以下载?
请问,RGBT数据集中两个模态是怎样配准的
请问这个有HBB格式下算法的基线吗
It's already December 8th.
@VisDrone
训练集和验证集图片为什么要存在白边,直接采用带白边的图片训练是否会在实际航拍图片识别中存在问题
Still no dataset of images even after 4 months.
In paper, author claims the dataset has 28,439 image pairs with 840x712 resolution.
In github, it only has 19,459 image pairs with 740x612 resolution due to white border in 100 pixels.
19,459/28,439*(740612)/(840712) = 51.8%
so the actual published dataset is only half size of the clamed dataset in paper....
To get the paper more in cited and impact more, please publish more to make your work reproducible.
You have provided a very good benchmark for detection and counting. I am very interested in your work and would like to communicate and communicate with you in detail. My email address is [email protected] and I look forward to your reply.
希望有大佬可以帮忙解答,是因为数据预处理的问题吗
I wonder which infrared camera the infrared images are captured by? NIR or TIR. They have different characteristics.
Could you please provide some parameters of the optical and infrared cameras capturing which are not mentioned in the paper but may be very important in real-world applications?
where is the download link for the dataset?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.