Questions tagged [faster-rcnn]
The faster-rcnn tag has no usage guidance.
42
questions
0
votes
0answers
7 views
What is the difference between a bounding box and ROI (Region of Interest)
I was reading about the Fast RCNN for object detection. From what I understand, it uses pre-computed ROI's (using selective search) and uses these to predict the bounding box offsets and uses smooth ...
0
votes
1answer
26 views
How to interpret fast-rcnn metrics?
I'm following this tutorial to fine tune Faster RCNN model, during training process a lot of statistics are produced however I don't know how to interpret them.
what are major characteristics to look ...
0
votes
0answers
11 views
Faster RCNN is not able to recognize composed elements
I tried to fine tune Faster RCNN to realize object detection task with bounding boxes where I shall recognize face, eyes and mouth on image. However Faster RCNN seems to fail to recognize objects when ...
1
vote
0answers
102 views
Region Proposal Network - How to subsampling 256 fg/bg anchors
I am trying to understand training process of RPN. I have problem with creating mini batches of 256 anchors. If features map has shape 18x25=450 and every position has 9 anchors it is 4050 potential ...
1
vote
0answers
72 views
Preprocess problem Faster RCNN in tensorflow object detection API
I've wrapped meta-architecture with the code below:
...
1
vote
1answer
40 views
Training Object Detection model on just 10 images
I am trying to train an object detection model using Mask-RCNN with Resnet50 as backbone. I am using the pre-trained models from PyTorch's Torchvision library. I have only 10 images that I can use to ...
2
votes
0answers
449 views
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 ...
1
vote
0answers
24 views
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 ...
0
votes
0answers
115 views
Visualizing Faster R-CNN Result
I'm a newbie in computer vision and trying to learn object detection, and the first task my supervisor gave me was to create object detection model using Faster R-CNN. After days and nights of ...
0
votes
0answers
20 views
Applying instance segmentation without using COCO format
I need to apply instance segmentation, (AKA pixel wise prediction) on some satellite imagery. Almost every guide on the internet, uses the COCO format and dataset. But my dataset is in the form of two ...
1
vote
0answers
302 views
How can I calculate the F1 score using Mask RCNN?
I customized the "https://github.com/matterport/Mask_RCNN.git" repository to train with my own data set, for object detection, ignoring the mask segmentation part. Now I am evaluating my results, I ...
1
vote
0answers
48 views
Detect the presence/absense of simple components from a circuit board using object detection
In this case I have a challenge of inspecting a recently mounted product, using computer vision, to detect the absence of any component that I have to check.
For this task, I tried the concept of ...
0
votes
0answers
21 views
The features from CNN and R-CNN for a region
I have a dataset of images with bounding boxes around the regions in the image. I do not need R-CNN to detect the regions as they are given in the dataset, but I need to extract the features of the ...
0
votes
1answer
225 views
How to create a feature vector given final set of feature maps?
I've got a faster-rcnn (resnet-101 backbone) for object detection, and am extracting feature tensors for each detected object, which is a 7x7x2048 tensor (basically 2048 feature maps, each 7x7). For ...
1
vote
0answers
15 views
Efficient implementation of seperable convolution in tensorflow
It seems like the native implementation of separable convolution in tensorflow is not efficient.
https://github.com/tensorflow/tensorflow/issues/12940
Is anyone aware how can we get an efficient ...
1
vote
0answers
19 views
How many augmentated data points for each training image?
What are some useful rules of thumb for picking the number of augmenters per training image?
I realize this is a hyperparameter I can vary and test: I'm just trying to get a sense for reasonable ...
1
vote
0answers
103 views
Image masking tool to implement mask RCNN using python
I am trying to understand Mask RCNN. For that I have to input image with mask in png format while building the model.
I try to follow the article present in this blog.
The blogger used Pixel ...
1
vote
0answers
64 views
How does a Faster R-CNN gets trained and how does the Region Proposal Network fits into that?
so a Faster R-CNN consists of 3 parts:
-the Base CNN
-the Region Proposal Network with RoIpooling
-and the classification CNN at the end
So I asked myself if all these three Networks are trained ...
1
vote
1answer
959 views
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 ...
2
votes
1answer
190 views
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 ...
1
vote
1answer
20 views
Saving images in a non-retraceable way, but still able to train R-CNN's on them
For a computer vision project I am working with images that the company only allows me to have on my computer for a maximum of 24 hours due to regulations. Every day a few hundred images come in via ...
0
votes
1answer
391 views
Object detection model using images which have single instance of class per image-can it detect multiple instances in a single image?
I tried to train Faster R-CNN to detect multiple instances of a single class (eg. pomegranate on a pomegranate tree) but the training data consisted of 200 images where each image had only one object ...
1
vote
1answer
66 views
Extract segment from document scan
I need to extract some "valuable" information from document scan. For example, document's number, incoming date, organizations, persons, etc.
Example document:
I'm trying to extract highlighted ...
6
votes
2answers
4k views
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 ...
1
vote
1answer
358 views
Tensorflow F-RCNN first stage input and output strides
Trying to optimize performances on Tensorflow's faster_rcnn_resnet50 (from the model zoo), I'm currently working on understanding the full .config file they provide, and I'm having a hard time with ...
1
vote
0answers
431 views
matterport mask-r-cnn transfer learning on own dataset using VGG annotator ver.1
The code I used was taken from shapes.py, balloon.py, inspect_balloon_data.ipynb but mostly ...
5
votes
2answers
459 views
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 ...
1
vote
0answers
96 views
Understanding Faster R-CNN
I'm having some trouble understanding the way the Faster R-CNN algorithm works. Specifically, the way the authors describe the concept of anchors.
In their paper from here they describe anchors in ...
2
votes
0answers
715 views
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 ...
0
votes
1answer
44 views
Building Image Dataset In a Studio
I'm currently working in a problem of Object Detection, more specifically we want to count and differentiate similar species of moths.
We are already testing some ...
1
vote
2answers
276 views
2
votes
1answer
145 views
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 ...
1
vote
0answers
118 views
Mask RCNN detecting object but mask is inaccurate
I am trying to detect the inner region of a object. Currently I am using the mask rcnn implementation provided by tensorflow in the models zoo.
The object is similar to a hula hoop that is square in ...
0
votes
1answer
310 views
Mask RCNN: Random predictions during inference for the same image
I recently trained the Mask RCNN (matterport's implementation) on some satellite images, but during inference mode, I'm getting random predictions for the same set of weights for the same image.
That ...
1
vote
0answers
297 views
with tf.device(DEVICE): model = modellib.MaskRCNN(mode = “inference”, model_dir = LOGS_DIR, config = config) [closed]
ValueError Traceback (most recent call last)
/miniconda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
509 as_ref=...
3
votes
1answer
169 views
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 ...
1
vote
0answers
79 views
Query about Landmark pooling layer in Fashionnet paper
I have gone through Deepfashion paper.I have query regarding Landmark pooling layer.
1) Image has 4,6 or 8 landmark points depending on cloth type. So how do you decide size of last FC layer in ...
1
vote
1answer
77 views
Faster R-CNN wrapper for the number of RPNs in the layer dimensions?
When I intialize Faster R-CNN in the deployment phase, the number of samples per image (parameter from config file: TEST.RPN_POST_NMS_TOP_N) is set to 300, that's the number of predicted bounding ...
9
votes
2answers
13k views
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 ...
4
votes
1answer
366 views
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 ...
1
vote
0answers
1k views
How to perform Instance Segmentation using Tensorflow?
I used Tensorflow Object Detection API for a custom dataset based on the instructions at this help document.As required , collected the dataset,annotated it in PASCAL VOC XML format,split into ...
8
votes
4answers
4k views
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 ...
