5

There are various dataset available such as Pascal VOC dataset: You can perform all your task with these. size of the dataset is as follows ADE20K Semantic Segmentation Dataset: you can perform only segmentation here COCO dataset: This is rich dataset but a size larger then 5 GB so you can try downloading using google colab in your drive and then make ...


5

This is just an idea Given a set of pixels, the task is to decide: Which pixel is the center of an object? What is the size of the bounding boxes with the center is the pixel in part 1? Formula, consider this is a 2D image, call $(x,y)$ is the horizontal and vertical coordinate and $(w_i,h_i)$ is the size of bouding box of object $i$: $\text{For }m \in[x,x+...


4

If you want to get experience, you should probably start with some easier task. Object detection and localization are relatively hard and writing a neural network and image processing pipeline from scratch will take you a long time. If you want to build up an intuition about how NN's work, you might want to code some simple task from scratch. This is an ...


3

Is the image taken from a constant distance? If yes, you'd need to scale the images to the same dimensions first of all. For few images say 100-500 images (more the better) you'd need to label the dataset by proper scaling. Once labeled, use it to train a CNN (Although best would be training a ResNet). Once trained with decent accuracy, test it for the ...


2

Is this a good approach? Will I have a lot of trouble with different backgrounds? A lot will depend on the nature of the backgrounds you have, and how well they encode/decode by themselves without the object in frame. My gut feeling is that your system will have poor performance compared to a properly trained classifier, as the autoencoder will naturally ...


2

If you have stero pairs, and you can identify the objects in the scene, you do not need a neural network, you can just use triangulation. If you need to identify which objects in the scene are the same, you have an image segmentation problem. Depending on your problem and the amount of data you have access to, you may be able to use simple techniques like ...


2

You should use both classes together. Let's say you use the method you proposed. Then they will be contradicting each other as one teaches the network to recognize people, not objects and the other teaches the network to recognizes objects not person. There is no need for seperation of the two classes, unless you are making two seperate classifier. Hope I ...


2

I'm working on a similar problem. I'm using a 2D point cloud of an object, for example, X and Y coordinates for height, and with that more simple data set I will train a regression model (currently working on that). In my opinion, this approach with dissecting complex point cloud into cross sections that contain wanted dimension and feeding that to the model ...


2

Yes you can classify people bounding box with object detection. State of the art object detection model have people as one of the class in the object detection, as shown here: As you can see the image have both object bounding box and people bounding box.


2

This could be possible, providing you have the right dataset to train it on. The volume of a cup consist of width, height and depth. You can probably detect all three of those given the bounding box or the pixels of the cup. However detecting the dimensions of an object require a reference object, like a penny or your finger and you have to specify the ...


2

After a quick scan, it would seem that, in the history of object detection, machine learning has always been at the forefront. Before then, it would just be a heuristic approach. For a quick answer, here: https://towardsdatascience.com/real-time-object-detection-without-machine-learning-5139b399ee7d That goes over object detection without using machine ...


2

I guess that they need so little data because their models are already trained on huge datasets, and they are just transferring the learning (using those pre-trained models as starting point).


2

Precision is the number of true positives over the number of predicted positives(PP), and recall is the number of true positives(TP) over the number of actual positives(AP) you get. I used the initials just to make it easier ahead. A true positive is when you predict a car in a place and there is a car in that place. A predicted positive is every car you ...


2

You might want to look into building convolutional neural network (CNN) for object detection using Keras. With plain white squares, it should work pretty good.


2

I think you underestimate the size of YOLO. This is the size of one segment of yolo tiny according to the darknet .cfg file: Convolutional Neural Network structure: 416x416x3 Input image 416x416x16 Convolutional layer: 3x3x16, stride = 1, padding = 1 208x208x16 Max pooling layer: 2x2, stride = 2 208x208x32 ...


2

I think there is no absolute answer for this. Often its kind of trial and error. In general the CNN tries to generalize the problem, so using all logos with different augmentations and ground truths can maybe lead to some feature maps, which are so general that the CNN can find logos. But if your logos are so various, and embedded in colorful websites, the ...


2

If each photo is intended to show a photo of weed or crops you should give one label. If your task is different where you also try to localize weed or crops in the image, then you need to label accordingly. My understanding is you are trying to do the first case, therefore, there should be one label for each image.


2

This is really a semantic segmentation problem if OP wants to pinpoint the weeds. If OP wants to have such a segmentation he will need to hand segment every.single picture.


1

Maybe this is helpful: Recognising Traffic Signs With 98% Accuracy Using Deep Learning, by Eddie Forson. Greetings Mario


1

In fact, choosing smartly the values of the image augmentation can help the performance of your system. Where I work we developed an object detector for cars. We had the following image augmentation parameters: Apect ratio distorsion: it changed the cars dimensions Additive noise: it blurred the image Change colorspace: change the cars colors Saturation ...


1

If you want to evaluate on real thermal image dataset, you can use this one. Thermal Image dataset is mAP a relevant metric when I want to show result to a client ? (e.g a client doesn't understand if I tell him "my model has a mAP=0.7") Mean Average Precision is the relevant metric but it's more technical. You can start explaining with False Positives ...


1

NDDS is a UE4 plugin from NVIDIA to empower computer vision researchers to export high -quality synthetic images with metadata. NDDS supports images, segmentation, depth, object pose, bounding box, keypoints, and custom stencils. In addition to the expo rter, the plugin includes different components for generating highly randomized images. This randomization ...


1

Maybe try the COCO (common objects in context) dataset. It's often used for object detection, segmentation and localisation. They provide labels, and you can limit the size by downloading only a specific number of classes. http://cocodataset.org/#explore It's also quite a common one, so you can expect good documentation, and online answers to your ...


1

I might be able to help with the theory, but the coding... it is a non standard API such as Tensorflow or Pytorch (it might be custom code for what I can tell). The key element here is that the bouding boxes are removed only if they hold a prediciton for the same class that the box that is overlapping with (but with less confidence, that is why it gets ...


1

This looks like it could be a homework problem, so consider updating it with the homework tag if so. The second model has the same precision, but worse recall, than model 1. Therefore we would rather have model 1 than model 2. The third model has worse recall than model 1, and worse precision than model 1, therefore we would rather have model 1 than model ...


1

You can use the dataset test set as "frames" of video. Test the images with your model and calculate the images per second of the result and that is the same as frames per second. However you should set the batch size to 1 as in the real world scenario. You should also display each image with teh corresponding boxes after inference and remove the accuracy ...


1

I will consider that you need to extract(crop) the digram from the pdf research paper. You can use PyPDF2 or PyMuPDF to extract the images from the PDF file and then you can apply machine learning to do recognition and classification of the images. There are different types of machine learning solutions for image classification and you can start with ...


1

Not necessarily. Supposing your data is from the distribution of possible images containing an upright person close to the camera. Something like a neural network would perform poorly on the new data since it comes from a distribution other than on what it was trained. You could try augmenting the dataset to try to get some synthetic "far away upside down ...


1

You can use cv2.bitwise_and and pass rectangle as a mask. im = cv2.imread(filename) height,width,depth = im.shape cv2.rectangle(img,(384,0),(510,128),(0,255,0),3) cv2.rectangle(rectangle,(width/2,height/2),200,1,thickness=-1) masked_data = cv2.bitwise_and(im, im, mask=rectangle) cv2.imshow("masked_data", masked_data) cv2.waitKey(0)


1

Fisheye camera is always worst. Both convolutional networks object detectors and feature-based object detectors rely on the "isometry" of planar image - lack of strong distortions. Multiple camera have added benefit of several independent sources of information - ensembling. If each camera processed by separate network that may help in verification of ...


Only top voted, non community-wiki answers of a minimum length are eligible