I want to carry couple of tests to evaluate the accuracy of a pose estimation algorithm that I am working on. I have a 3D model of some objects and would like to generate synthetic images of this object at various known poses.
For someone being new to computer vision, which method/tool i can use to generate synthetic images.
Related
I am currently testing out custom object detection using the Tensorflow API. But I don't quite seem to understand the theory behind it.
So if I for example download a version of MobileNet and use it to train on, lets say, red and green apples. Does it forget all the things that is has already been trained on? And if so, why does it then benefit to use MobileNet over building a CNN from scratch.
Thanks for any answers!
Does it forget all the things that is has already been trained on?
Yes, if you re-train a CNN previously trained on a large database with a new database containing fewer classes it will "forget" the old classes. However, the old pre-training can help learning the new classes, this is a training strategy called "transfert learning" of "fine tuning" depending on the exact approach.
As a rule of thumb it is generally not a good idea to create a new network architecture from scratch as better networks probably already exist. You may want to implement your custom architecture if:
You are learning CNN's and deep learning
You have a specific need and you proved that other architectures won't fit or will perform poorly
Usually, one take an existing pre-trained network and specialize it for their specific task using transfert learning.
A lot of scientific literature is available for free online if you want to learn. you can start with the Yolo series and R-CNN, Fast-RCNN and Faster-RCNN for detection networks.
The main concept behind object detection is that it divides the input image in a grid of N patches, and then for each patch, it generates a set of sub-patches with different aspect ratios, let's say it generates M rectangular sub-patches. In total you need to classify MxN images.
In general the idea is then analyze each sub-patch within each patch . You pass the sub-patch to the classifier in your model and depending on the model training, it will classify it as containing a green apple/red apple/nothing. If it is classified as a red apple, then this sub-patch is the bounding box of the object detected.
So actually, there are two parts you are interested in:
Generating as many sub-patches as possible to cover as many portions of the image as possible (Of course, the more sub-patches, the slower your model will be) and,
The classifier. The classifier is normally an already exisiting network (MobileNeet, VGG, ResNet...). This part is commonly used as the "backbone" and it will extract the features of the input image. With the classifier you can either choose to training it "from zero", therefore your weights will be adjusted to your specific problem, OR, you can load the weigths from other known problem and use them in your problem so you won't need to spend time training them. In this case, they will also classify the objects for which the classifier was training for.
Take a look at the Mask-RCNN implementation. I find very interesting how they explain the process. In this architecture, you will not only generate a bounding box but also segment the object of interest.
For my next TF2-based computer vision project I need to classify images to a pre-defined set of classes. However, multiple objects of different classes can occur on one such image. That sounds like an object detection task, so I guess I could go for that.
But: I don't need to know where on an image each of these objects are, I just need to know which classes of objects are visible on an image.
Now I am thinking which route I should take. I am in particular interested in a high accuracy/quality of the solution. So I would prefer the approach that leads to better results. Thus from your experience, should I still go for an object detector, even though I don't need to know the location of the detected objects on the image, or should I rather build an image classifier, which could output all the classes that are located on an image? Is this even an option, can a "normal" classifier output multiple classes?
Since you don't need the object localization, stick to classification only.
Although you will be tempted to use the standard off-the-shelf network of multi-class multi-label object detection because of its re-usability, but realize that you are asking the model to do more things. If you have tons of data - not a problem. Or if your objects are similar to the ones used in ImageNet/COCO etc, you can simply use standard off-the-shelf object detection architecture and fine-tune on your dataset.
However, if you have less data and you need to train from scratch (e.g. medical images, weird objects), then object detection will be an overkill and will give you inferior results.
Remember, most of the object detection networks re-cycle the classification architectures with modifications added to last layers to incorporate additional outputs for object detection coordinates. There is a loss function associated with those additional outputs. During training in order to get best loss value, some of the classification accuracy is compromised for the sake of getting better object localization coordinates. You don't need that compromise. So, you can modify the last layer of object detection network and remove the outputs for coordinates.
Again, all this hassle is worth only if you have less data and you really need to train from scratch.
I'm trying to build a detection + classification model that will recognize an object in an image and classify it. Every image will contain at most 1 object among my 10 classes (i.e. same image cannot contains 2 classes). An image can, however, contain none of my classes/objects. I'm struggling with the general approach to this problem, especially due to the nature of my problem; my objects have different sizes. This is what I have tried:
Trained a classifier with images that only contains my objects/classes, i.e. every image is the object itself with background pre-removed. Now, since the objects/images have different shapes (aspect ratios) I had to reshape the images to the same size (destroying the aspect ratios). This would work just fine if my purpose was to only build a classifier, but since I also need to detect the objects, this didn't work so good.
The second approach was similar to (1), except that I didn't reshape the objects naively, but kept the aspect ratios by padding the image with 0 (black). This completely destroyed my classifiers ability to perform well (accuracy < 5%).
Mask RCNN - I followed this blogpost to try build a detector + classifier in the same model. The approach took forever and I wasn't sure it was the right approach. I even used external tools (RectLabel) to generate annotated image files containing information about the bounding boxes.
Question:
How should I approach this problem, on a general level:
Should I build 2 separate models? (One for detection/localization and one for classification?)
Should I be annotating my images using annotations file as in approach (3)?
Do I have to reshape my images at any stage?
Thanks,
PS. In all of my approaches, I augmented the images to generate ~500-1000 images per class.
To answer your questions:
No, you don't have to build two separate models. What you are describing is called Object detection, which is classification along with localization. There are many models which do this: Mask_RCNN, Yolo, Detectron, SSD, etc..
Yes, you do need to annotate your images for training a model for your custom classes. Each of the models mentioned above has needs a different way of annotation.
No, you don't need to do any image resizing. Most of the time it is done when the model loads the data for training or inference.
You are on the right track with trying MaskRCNN.
Other than MaskRCNN, you could also try Yolo. There is also an accompanying easy-to-use annotating tool Yolo-Mark.
If you go through this tutorial, you would understand what you care about.
How to train your own Object Detector with TensorFlow’s Object Detector API
The SSD model is small so that it would not take so much time for training.
There are some object detection models.
On RectLabel, you can save bounding boxes in the PASCAL VOC format.
You can export TFRecord for Tensorflow.
https://rectlabel.com/help#tf_record
I obtain depth & reflectance maps from Lidar (2D images) and I have also camera images (2D images). Image have the same size.
I want to use CNN to perform object detection using both images. It is a sort of "fusion CNN"
How am I suppose to do it? Did I am suppose to use a pre-train model? But the is no pre-train model using lidar images..
Which is the best CNN algorithm to do it? ie for performing fusion of modalities for object detection
Thanks you in advance
Did I am suppose to use a pre-train model?
Yes you should, unless you are super confident that you can find a working model directly by urself.
But the is no pre-train model using lidar image
First I`m pretty sure there are LIDAR based network .e.g
L Caltagirone , LIDAR-Camera Fusion for Road Detection Using Fully
Convolutional ... arxiv, 2018
Second, even if there is no open source implementation for direct LIDAR-based, You can always convert the LIDAR to the depth image. For Depth image based CNN, there are hundreds of implementation for segmentation and detection.
How am I suppose to do it?
First, you can place them side by side parallel, for RGB and depth/LIDAR 3d pointcloud. Feed them separately
Second, you can also combine them by merging the input to 4D tensor and transfer the initial weight to the single model. At last perform transfer learning in your given dataset.
best CNN algorithm?
Totally depends on your task and hardware. Do you need best in processing speed or best in accuracy? Define your "best", please.
ALso Are you using it for autonomous car or for in-house nurse care system? different CNN system customizes the weight for different purposes.
Generally, for real-time multiple object detection using a cheap PC e.g DJI manifold, I would suggest Yolo-tiny
I'm using cnn built by keras(tensorflow) to do visual recognition.
I wonder if there is a way to know what my own tensorflow model "see".
Google had a news showing the cat face in the AI brain.
https://www.smithsonianmag.com/innovation/one-step-closer-to-a-brain-79159265/
Can anybody tell me how to take out the image in my own cnn networks.
For example, what my own cnn model recognize a car?
We have to distinguish between what Tensorflow actually see:
As we go deeper into the network, the feature maps look less like the
original image and more like an abstract representation of it. As you
can see in block3_conv1 the cat is somewhat visible, but after that it
becomes unrecognizable. The reason is that deeper feature maps encode
high level concepts like “cat nose” or “dog ear” while lower level
feature maps detect simple edges and shapes. That’s why deeper feature
maps contain less information about the image and more about the class
of the image. They still encode useful features, but they are less
visually interpretable by us.
and what we can reconstruct from it as a result of some kind of reverse deconvolution (which is not a real math deconvolution in fact) process.
To answer to your real question, there is a lot of good example solution out there, one you can study it with success: Visualizing output of convolutional layer in tensorflow.
When you are building a model to perform visual recognition, you actually give it similar kinds of labelled data or pictures in this case to it to recognize so that it can modify its weights according to the training data. If you wish to build a model that can recognize a car, you have to perform training on a large train data containing labelled pictures. This type of recognition is basically a categorical recognition.
You can experiment with the MNIST dataset which provides with a dataset of pictures of digits for image recognition.