I want to train my YOLOV3 with Stanford Drone Dataset but IDK how can do it. Someone has any idea?
Stanford Drone Dataset: http://cvgl.stanford.edu/projects/uav_data/
You can use AlexeyAB repository to annotate your data accordingly. There is a tool called YOLO_mark there which you can use to draw bounding boxes around objects. In the dataset you mentioned, seems like the data is already annotated. If so, you can use matlab or any other tool to convert the annotation formats to the format of YOLO, which is relative values of each box coordinates:
<object-class> <x_center> <y_center> <width> <height>
Related
I am working on a pytorch project, where I’m using a webcam video stream. An object detector is used to find objects within the frame and each box is given an id by a tracker. Then, I want to analyse each bounding box with a CNN-LSTM and classify it (binary classification) based on the previous frame sequence of that box (for the last 5 frames). I want the program to run a close to real-time as possible.
Currently I am stuck with the CNN-LSTM part of my problem - the detector and tracker are working quite well already.
I am a little bit clueless on how to approach this task. Here are the questions I have:
1) How does inferencing work in this case? Do I have to save np arrays for each bounding box containing the last 5 frames, then add the current frame and delete the oldest one? Then use the model for each bounding box that is in the current frame. This way sounds very slow and inefficient. Is there a faster or easier way?
2) Do you have any tipps for creating the dataset? I have a couple of videos with bounding boxes and labels. Should I loop through the videos and save save each frame sequence for each bounding box in a new folder, together with a csv that contains the label? I have never worked with an CNN-LSTM, so I don’t know how to load the data for training.
3) Would it be possible to use the extracted features of the CNN in parallel? As mentioned above, The extracted features should be used by the LSTM for a binary classification problem. The classification is only needed for the current frame. I would like to use an additional classifier (8 classes) based on the extracted CNN features, also only for the current frame. For this classifier, the LSTM is not needed.
Since my explaining propably is very confusing, the following image hopefully helps with understanding what I want to build:
Architecture
This is the architecture I want to use. Is this possible using Pytorch? So far, I only worked with CNNs and LSTM seperately. Any help is apprechiated :)
Is it possible to use GCP Machine Learning products to train a model to draw bounding boxes on certain objects in an image? I'd like to be able to feed labeled images and have it predict where that label would belong.
I think you are looking for something like this, where the Tensorflow machine learning library is used:
https://cloud.google.com/solutions/creating-object-detection-application-tensorflow
A note:
When you say that you want to be able to feed labeled images and have it predict where that label would belong, i assume you mean where that object is present in the image in terms of the bounding box coordinates. If so then the library should take care of that for you, your job is just to train the network with your labeled images.
I have written an object classification program using BoW clustering and SVM classification algorithms. The program runs successfully. Now that I can classify the objects, I want to track them in real time by drawing a bounding rectangle/circle around them. I have researched and came with the following ideas.
1) Use homography by using the train set images from the train data directory. But the problem with this approach is, the train image should be exactly same as the test image. Since I'm not detecting specific objects, the test images are closely related to the train images but not essentially an exact match. In homography we find a known object in a test scene. Please correct me if I am wrong about homography.
2) Use feature tracking. Im planning to extract the features computed by SIFT in the test images which are similar to the train images and then track them by drawing a bounding rectangle/circle. But the issue here is how do I know which features are from the object and which features are from the environment? Is there any member function in SVM class which can return the key points or region of interest used to classify the object?
Thank you
I have been tasked to use OpenCV and C++
Read a set of videos for creating a set of images/learning.
Classify objects seen in the videos
Label the images
test against series of test videos to check objects were identified as expected. draw a rectangle around them and label.
I am new to OpenCV however happy to program in C++ as soon as approach is formed. I am also planning to write my own functions at a later stage.
I need your help in formning right way of solution approach as I have to identify household objects [cup, soft toy, phone, camera, keyboard) from a stream of video and then test on another stream of video. The original video has depth information as well but not sure how to use it to my benefit.
Read about Support vector machine (SVM) , Feature extraction (e.g. SIFT/SURF) , SVM training and SVM testing. And, for drawing Rectangle, read about findContour(), drawContour() in openCV.
Approach:
Detect objects (e.g. car/plane etc.). Store the points of its contours
Extract some features of that object using SIFT/SURF
Based upon the extracted features, classify the object using SVM (the input for SVM will be the extracted features)
And if the SVM says -Yes! it is a car. Then, draw a rectangle around it using the points of its contour which you had stored in first step.
I am working on a project to stitch together around 400 high resolution aerial images around 36000x2600 to create a map. I am currently using OpenCV and so far I have obtained the match points between the images. Now I am at a lost in figuring out how to get the matrix transformation of the images so I can begin the stitching process. I have absolutely no background in working with images nor graphics so this is a first time for me. Can I get some advice on how I would approach this?
The images that I received also came with a data sheet showing longitude, latitude, airplane wing angle, altitude, etc. of each image. I am unsure how accurate these data are, but I am wondering if I can use these information to perform the proper matrix transformation that I need.
Thanks
Do you want to understand the math behind the process or just have an superficial idea of whats going on and just use it?
The regular term for "image snitching" is image alignment. Feed google with it and you'll find tons of sources.
For example, here.
Best regards,
zhengtonic
In recent opencv 2.3 release...they implemented a whole process of image stitching. Maybe it is worth looking at.