I have been trying to tackle a problem where I need to track multiple people through multiple camera viewpoints on a real-time basis.
I found a solution DeepCC (https://github.com/daiwc/DeepCC) on DukeMTMC dataset but unfortunately, this solution has been taken down because of data confidentiality issues. They were using Fast R-CNN for object detection, triplet loss for Re-identification and DeepSort for real-time multiple object tracking.
Questions:
1. Can someone share some other resources regarding the same problem?
2. Is there a way to download and still use the DukeMTMC database for multiple tracking problem?
3. Is anyone aware when the official website (http://vision.cs.duke.edu/DukeMTMC/) will be available again?
Please feel free to provide different variations of the question :)
Intel OpenVINO framewors has all part of this task:
Objects detection with pretrained Faster RCNN, SSD or YOLO.
Reidentification models.
And complete demo application.
And you can use another models. Or if you want to use detection on GPU then take opencv_dnn_cuda for detection and OpenVINO for reidentification.
A good deep learning library that I have used in the past for my work is called Mask R-CNN, or Mask Regions-Convolutional Neural-Network. Although I have only used this algorithm on images and not on videos, the same principles apply, and it's very easy to make the transition to detection objects in a video. The algorithm uses Tensorflow and Keras, where you can split your input data, i.e images of people, into two sets, training, and validation.
For training, use a third party software like via, to annotate the people in the images. After the annotations have been drawn, you will export a JSON file with all annotations drawn, which will be used for the training process. Do the same thing for the validation phase, BUT make sure the images in the validation have not been seen before by the algorithm.
Once you have annotated both groups and generated JSON files, you then can start training the algorithm. Mask R-CNN makes it very easy to train, with all you need to do is pass one line full of commands to start it. If you want to train data on your GPU instead of your CPU, then install Nvidia's CUDA, which works very well with supported GPUs, and requires no coding after the installation.
During the training stage, you will be generating weights files, which are stored in the .h5 format. Depending on the number of epochs you choose, there will be a weights file generated per epoch. Once the training has finished, you then will just have to reference that weights file anytime you want to detect relevant objects, i.e. in your video feed.
Some important info:
Mask R-CNN is somewhat of an older algorithm, but it still works flawlessly today. Although some people have updated the algorithm to Tenserflow 2.0+, to get the best use out of it, use the following.
Tensorflow-gpu 1.13.2+
Keras 2.0.0+
CUDA 9.0 to 10.0
Honestly, the hardest part for me in the past was not using the algorithm, but finding the right versions of Tensorflow, Keras, and CUDA, that all play well with each other, and don't error out. Although the above-mentioned versions will work, try and see if you can upgrade or downgrade certain libraries to see if you can get better results.
Article about Mask R-CNN with video, I find it to be very useful and resourceful.
https://www.pyimagesearch.com/2018/11/19/mask-r-cnn-with-opencv/
The GitHub repo can be found below.
https://github.com/matterport/Mask_RCNN
EDIT
You can use this method across multiple cameras, just set up multiple video captures within a computer vision library like OpenCV. I assume this would be done with Python, which both Mask R-CNN and OpenCV are primarly based in.
Related
In the previous reality capture system users could set a parameter which would determine the resolution of the output models. I want to wind up with models about 100-150K vertices. Is there a setting that allows me to request the modeler to keep the number of generated vertices within some bounds, somewhere in the forge API?
The vertex/triangle decimation is usually, what can be called "subjective" task, which can also explain why there are so many optimization algorithms in the wild.
One type of optimization you would need and expect for "organic" models, and totally different one for an architectural building.
The Reality Capture API provides you only with raw Hi-Res results, avoiding "opionated" optimizations. This should be considered just as a step in automation pipeline.
Another step, would be, upon receiving, to automatically optimize the resulted mesh based on set of settings you need.
One of these steps could be Design Automation for 3ds Max, where you feed a model and using the ProOptimizer Modifier within 3ds Max, you output the mesh with needed detail. A sample of this step, can be found here: https://forge-showroom.autodesk.io/post/prooptimizer.
There are also numerous opensource solutions which should help you cover this post-processing step.
I have a few questions regarding the fine-tuning process.
I'm building an app that is able to recognize data from the following documents:
ID Card
Driving license
Passport
Receipts
All of them have different fonts (especially receipts) and it is hard to match exactly the same font and I will have to train the model on a lot of similar fonts.
So my questions are:
Should I train a separate model for each of the document types for better performance and accuracy or it is fine to train a single eng model on a bunch of fonts that are similar to the fonts that are being used on this type of documents?
How many pages of training data should I generate per font? By default, I think tesstrain.sh generates around 4k pages.
Maybe any suggestions on how I can generate training data that is closest to real input data
How many iterations should be used?
For example, if I'm using some font that has a high error rate and I want to target 98% - 99% accuracy rate.
As well maybe some of you had experience working with this type of documents and maybe you know some common fonts that are being used for these documents?
I know that MRZ in passport and id cards is using OCR-B font, but what about the rest of the document?
Thanks in advance!
Ans 1
you can train a single model to achieve the same but if you want to detect different languages then I think you will need different models.
Ans 2
If you are looking for some datasets then have a look at this Mnist Png Dataset which has digits as well as alphabets from various computer-based fonts. Here is a link to some starter code to use the data set implemented in Pytorch.
Ans 3
You can use optuna to find the best set of params for your model, but you will need some of the
using-optuna-to-optimize-pytorch-hyperparameters
Have a look at these
PAN-Card-OCR
document-details-parsing-using-ocr
They are trying to achieve similar task.
Hope it answers your Question...!
I would train a classifier on the 4 different types to classify an ID, license, passport, receipts. Basically so you know that a passport is a passport vs a drivers license ect. Then I would have 4 more models that are used for translating each specific type (passport, drivers license, ID, and receipts). It should be noted that if you are working with multiple languages this will likely mean making 4 models based each specific language meaning that if you have L languages you make need 4*L number of models for translating those.
Likely a lot. I don’t think that font is really an issue. Maybe what you should do is try and define some templates for things like drivers license and then generate based on that template?
This is the least of your problems, just test for this.
Assuming you are referring to a ML data model that might be used to perform ocr using computer vision I'd recommend to:
Setup your taxonomy as required by your application requirements.
This means to categorize the expected font sets per type of scanned document (png,jpg tiff etc.) to include inside the appropriate dataset. Select the fonts closest to the ones being used as well as the type of information you need to gather (Digits only, Alphabetic characters).
Perform data cleanup on your dataset and make sure you have homogenous data for the OCR functionality. For example, all document images should be of png type, with max dimensions of 46x46 to have an appropriate training model. Note that higher resolution images and smaller scale means higher accuracy.
Cater for handwritting as well, if you have damaged or non-visible font images. This might improve character conversion options in cases that fonts on paper are not clearly visible/worn out.
In case you are using keras module with TF on mnist provided datasets, setup a cancellation rule for ML model training when you reach 98%-99% accuracy for more control in case you expect your fonts in images to be error-prone (as stated above). This helps avoid higher margin of errors when you have bad images in your training dataset. For a dataset of 1000+ images, a good setting would be using TF Dense of 256 and 5 epochs.
A sample training dataset can be found here.
If you just need to do some automation with your application or do data entry that requires OCR conversion from images, a good open source solution would be to use information gathering automatically via PSImaging module (Powershell) use the degrees of confidence retrieved (from png) and run them against your current datasets to improve your character match accuracy.
You can find the relevant link here
I need to visually recognise some flat pictures showed to camera. There are not many of them (maybe 30) but discrimination may depend on details. The input may be partly obscured or shadowed and is suspect to lighting changes.
The samples need to be updatable.
There are many existing frameworks for object detection, with the most reliable ones depending on deep learning methods (mostly convolutional networks). However, the pretrained models are not well optimised to discern flat imagery of course, and even if I start training from scratch, updating the system for new samples would take a cumbersome training process, if I am right about how this works.
Is it possible to use deep learning while still keeping the sample pool flexible?
Is there any other well known reliable method to detect images from a small sample set?
One can use well trained networks for visual classification like Inception or SqueezeNet, slice of the last layer(s) and add a simple statistical algorithm (for example k-nearest neighbour) that can be directly teached by the samples in a non-iterative fashion.
Most classification-related calculations like lighting and orientation insensitivity are already handled by the pre-trained network then, while the network's output keep enough information to allow statistical algorithms decide the image class.
An implementation using k-nearest neighbour is shown here: https://teachablemachine.withgoogle.com/ , the source is hosted here: https://github.com/googlecreativelab/teachable-machine .
Use transfer learning; you’ll still need to build a training set, but you’ll get better results than starting with random weights. Try to find a model trained on images similar to yours. You might also do some black box testing of the selected model with your curated images to baseline it’s response curve to your images.
Is there a simple way (e.g. without modifying caffe code) to load wights from multiple pretrained networks into one network? The network contains some layers with same dimensions and names as both pretrained networks.
I am trying to achieve this using NVidia DIGITS and Caffe.
EDIT: I thought it wouldn't be possible to do it directly from DIGITS, as confirmed by answers. Can anyone suggest a simple way to modify the DIGITS code to be able to select multiple pretrained networks? I checked the code a bit, and thought the training script would be a good place to start, but I don't have in-depth knowledge of Caffe, so I'm not sure what the best/quickest way to achieve this would be.
As Shai suggested, there was no way of doing this, so I decided to clone the official repository and make the appropriate changes. I changed the code so that multiple pretrained networks can be loaded by using a colon as separator.
I created a pull request on the official repository and my changes were then merged with the main branch of DIGITS, meaning it is now possible to use this functionality in DIGITS.
AFAIK there is no straight forward way of doing so.
However, you can use net surgery to load the pretrained models and manually assign their weights to the target net. Once you have a single net with all the weights initialized according to the various pretrained models, you can save it and use it as a single pretrained model for the rest of your work.
I'm using joint positions from a Kinect camera as my state space but I think it's going to be too large (25 joints x 30 per second) to just feed into SARSA or Qlearning.
Right now I'm using the Kinect Gesture Builder program which uses Supervised Learning to associate user movement to specific gestures. But that requires supervised training which I'd like to move away from. I figure the algorithm might pick up certain associations between joints that I would when I classify the data myself (hands up, step left, step right, for example).
I think feeding that data into a deep neural network and then pass that into a reinforcement learning algorithm might give me a better result.
There was a paper on this recently. https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
I know Accord.net has both deep neural networks and RL but has anyone combined them together? Any insights?
If I understand correctly from your question + comment, what you want is to have an agent that performs discrete actions using a visual input (raw pixels from a camera). This looks exactly like what DeepMind guys recently did, extending the paper you mentioned. Have a look at this. It is the newer (and better) version of playing Atari games. They also provide an official implementation, which you can download here.
There is even an implementation in Neon which works pretty well.
Finally, if you want to use continuous actions, you might be interested in this very recent paper.
To recap: yes, somebody combined DNN + RL, it works and if you want to use raw camera data to train an agent with RL, this is definitely one way to go :)