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

The example given based on the yolov1 paper: The last layer has a tensor of the dimension 7x7x30. but the dimension of the last tensor is not in every case 7x7x30. let be: S: the number of grid cells in X and Y direction C: the number classes to train B: the number of bounding boxes in every grid cell The dimension of the output tensor is calculated with ...


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

No. YOLO and SSD are based on Nvidia's proprietary CUDA technology which is not available on Raspberry simply because of the GPU vendor is not Nvidia. Even more, there seems to be no implementation of even OpenCL for the Raspberry's GPU. What you can do is to try port YOLO's of SSD's CNN core from CUDA to Raspberry GPU's assembler, in the way described in, ...


3

It depends on what is your ultimate goal. If your goal is to simply classify the object in the image, having more complex output won't help. Simpler output representation yields better result. If your goal is to detect the bounding box, output the bounding box. There is no need for a more complex output feature. If you use a segmentation method for bounding ...


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 ...


3

You can introduce another class to your network - "not a book". After that, you will need to add new data to your dataset, random images that do not contain books to classify and train your network on that data. So when your network won't see a book it will output high probability for "not a book" class, if an image with a book will be shown to the network ...


3

Cartesian Bias and Pipeline Efficiency You are experiencing a techno-cultural artifact of Cartesian-centric imaging running all the way back to the dawn of coordinate systems. It is the momentum of practice as a consequence of applying Cartesian 2D coordinates to rasterize images appearing at the focal planes of lenses from the dawn of television and the ...


3

Yes, it is not specified because the region proposal algorithm did not change from R-CNN (the previous version from Fast R-CNN, however, in the next verion, Faster R-CNN, this algorithm is replaced by a CNN). The region proposal algorithm you are looking for is called selective search. You can find in the R-CNN paper that the algorithm is described in "...


2

Here's a recent paper that does what you're looking for. It looks like they achieve this simply by adding a couple rotated prior boxes and regressing the angles in between. This is similar to what standard object detectors do in terms of creating a bunch of prior box shapes and regressing the actual sizes.


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

A bounding box is a rectangle superimposed over an image within which all important features of a particular object is expected to reside. It's purpose is to reduce the range of search for those object features and thereby conserve computing resources: Allocation of memory, processors, cores, processing time, some other resource, or a combination of them. ...


2

It should not be much more difficult to predict a rotated rectangle compared to a bounding box. A bounding box can be parameterized with 4 floats: $x_c$, $y_c$, width, height. A rotated rectangle can be parameterized with 5 floats: $x_c$, $y_c$, width, height, angle. However, to avoid the wrap-around issue with predicting the angle with one value (0° is same ...


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

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.


2

As per your requirements, I would suggest that you start with any simple CNN network. CNNs take advantage of the hierarchical pattern in data and assemble more complex patterns using smaller and simpler patterns. Therefore, on the scale of connectedness and complexity, CNNs are on the lower extreme. Here is a Keras example: model = models.Sequential() ...


2

There are different questions and even different lines of thought here. Let's go through them On resizing Why do we need to resize? To fit the network input which is fixed when nets are no Fully Convolutional Networks (FCN) What if my net is FCN? Still makes sense to resize to bound the dimension of the input features you want to detect (a person on a small ...


2

To verify the accuracy of the classification stage, you will need labeled images with a single car. To train and verify accuracy of the detection stage and full system, you can: in the datasets with images with multiple cars, manually, mark the image rectangles that contains one car. from previous, split the image in one or more ones, each one containing a ...


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