Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [faster-rcnn]

49 questions
10
votes
2 answers

How does the bounding box regressor work in Fast R-CNN?

In the fast R-CNN paper (https://arxiv.org/abs/1504.08083) by Ross Girshick, the bounding box parameters are continuous variables. These values are predicted using regression method. Unlike other neural network outputs, these values do not represent…
Saptarshi Roy
  • 427
  • 2
  • 4
  • 11
9
votes
2 answers

Is Faster RCNN the same thing as VGG-16, RESNET-50, etc... or not?

My understanding is that Faster RCNN is an architecture for performing object detection. It finds objects in an image and classifies them. My understanding is also that VGG-16, RESNET-50, etc... also find objects in images and classify them. Are…
b19wh33l5
  • 91
  • 1
  • 2
8
votes
4 answers

Faster-RCNN how anchor work with slider in RPN layer?

I am trying to understand the whole Faster-RCNN, From https://www.quora.com/How-does-the-region-proposal-network-RPN-in-Faster-R-CNN-work Then a sliding window is run spatially on these feature maps. The size of sliding window is n×n (here 3×3).…
Mithril
  • 373
  • 6
  • 15
5
votes
2 answers

Feeding 3 consecutive video frames to a CNN to track a tennis ball

I want to use CNN transfer learning to track a tennis ball from TV broadcasts of tennis matches. I used VGG annotating tool annotation tool link (use version 1 of the tool for compatibility with matterport code) and have about 200 frames annotated…
mLstudent33
  • 574
  • 1
  • 4
  • 17
4
votes
2 answers

Backpropagation in Faster R-CNN

I understand how the convolution layers are applied after selective search finds the regions of interest in vanilla R-CNN and so the back-propagation or any weight updating is done in the individual convolution networks. But in Faster R-CNN a…
deadcode
  • 153
  • 1
  • 7
3
votes
1 answer

Faster RCNN-RPN NETWORK

I already asked this question in stack overflow, but got response from experts, to post this question here, please help me to understand this concept... I am trying to understand RPN network in Faster RCNN. I understand the concept of RPN…
abdlp Komp
  • 31
  • 1
3
votes
0 answers

Bounding box regression in R-CNN

In R-CNN paper, they give the definition of the target values for bounding box regression Given that $(P, G)$ is a (prediction box, ground-truth box) pair of the form $(x, y, w, h)$ where $x, y$ is the center coordinate of the box, $w, h$ are width…
HOANG GIANG
  • 159
  • 9
3
votes
1 answer

Get bounding boxes for adjacent instances of a single class in image

I have a dataset with thousands of music score pages and manually annotated bounding boxes for the individual bars: My objective is now to train a DNN that should ultimately be able to get these bounding boxes on its own. First idea was to use…
sonovice
  • 131
  • 2
2
votes
1 answer

Why does Faster R-CNN use SGD optimizer instead of Adam?

I just start learning Faster R-CNN and I have some doubts about the optimizer of this network. In my understanding, Adam optimizer performs much better than SGD in a lot of networks. However, the paper of Faster R-CNN choose SGD optimizer instead of…
icebear
  • 21
  • 1
  • 1
  • 6
2
votes
2 answers

Pre trained dataset for Car damage detection

I'm making a Car Damage Detection model which would have 2 classes to detect upon. My dataset has a total of 300 images (out of which I'd be using some for testing), which are totally insufficient to train the model from scratch. Can I use a…
Preetkaran Singh
  • 123
  • 4
2
votes
1 answer

How does R-CNN and AlexNet compare?

I know AlexNet does object classification in images [categories] and R-CNN does object localization [category and bounding box]. How does R-CNN and AlexNet compare? Are they used for the same purpose or R-CNN does more? Does R-CNN use Alexnet as a…
Fakrudeen
  • 123
  • 4
2
votes
1 answer

what is the best approach to detect small objects with similar shape?

I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks with different brands are stacked, placed on the…
Hoang Dang Tuan
  • 75
  • 1
  • 7
2
votes
0 answers

Which model is used for document extraction (CamScanner, Microsoft Lens etc)

I want to start a small project where I'd create a model(s) that would extract document from a picture and rescale it, something like CamScanner or Microsoft Lens apps do. I've gathered a small dataset just to prototype the concept, but I'm not sure…
apantovic
  • 21
  • 1
1
vote
0 answers

Understanding how anchors are created in a regional proposal network

I understand that in Faster R-CNN, the image is fed into a pre-trained CNN (such as VG16). So say I have a 37x50x512 feature map. Firstly, I assume that each feature map (37x50x1) is fed into the RPN? or does each of the 512 feature maps get fed in…
user218030
  • 15
  • 3
1
vote
0 answers

Best way to train yolov5 on a custom dataset

I have a dataset with about 100 images that look like this. My goal is get yolov5 to detect buildings in similar images. In order to do this I would like yolov5 to get to close to 1 in precision on the training dataset The images are of size 10000…
Ariel Baron
  • 111
  • 1
1
2 3 4