Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [object-detection]

Object detection deals with recognizing the presence of objects of a certain semantic class (e.g., “humans”, “buildings”, “cars”, etc.) in digital image and video data.

1
vote
2answers
26 views

What is sigma function in the YOLO object detector? [closed]

I have gone through the YOLO9000 paper, in that they have mentioned that network predicts 5 coordinates of the bounding box, and from that we find the exact centre coordinates and the width and height....
0
votes
0answers
6 views

What is scale-invariance and log-space translations of a bounding box?

In slow R-CNN paper, the bounding box regression's goal is to learn a transformation that maps a proposed bounding box P to a ground-truth box G and we parameterize the transformation in terms of four ...
0
votes
0answers
12 views

I have question about normalization of human pose estimation

I have a question about normalization of object joint detection here is the description about the normalization method Further, since the joint coordinates are in absolute image coordinates, it ...
0
votes
1answer
24 views

Combining custom YOLO network for face detection with another CNN

I am looking for a way to build and train an end-to-end CNN that contains two steps: 1) a CNN for finding a face and hands in the image and 2) CNN that works on the crops of the face and hands. To ...
2
votes
2answers
66 views

Which layer in a CNN able to detect spinned and translated objects

Conv layer or max pooling layer or anything else does the job? In my opinion, Conv layer or max pooling layer are able to do the job only when the rotations or translations are not too big.
0
votes
0answers
14 views

What is the best DL face detection trained model?

I want to test a pretrained face detection model. Which one is the best out there? I am using pytorch but I guess, the model can be adapted from any other framework. Thanks.
0
votes
0answers
24 views

How do convolutional predictors work in SSD Object Detection?

I'm trying to understand this paper SSD: Single Shot MultiBox Detector by Liu et al, there they mention "Convolutional predictors for detection: Each added feature layer (or optionally an ex- ...
0
votes
0answers
25 views

Detecting the bounding box of an object in an image?

I have a dataset of images . Each image has an object in it. In a seperate csv file , I have been provided with the coordinates of the bounding box for the object in the training images. How do I ...
8
votes
3answers
97 views

Is it possible to give variable sized images as input to convolutioal neural network

Can we give images with variable size as input to convolutional neural network for object detection? If possible, How can we do that? But if we try to crop the image, we will be loosing some portion ...
0
votes
1answer
53 views

Faster R-CNN - why do we need a classifier after the region proposal network?

It is my understanding that the region proposal network performs both classification, to find out if a certain box contains foreground or background, and regression, to fine tune the locations of the ...
0
votes
0answers
14 views

Cannot seem to converge beyond a loss of 3 on an object detector being trained on YOLO

Data The you only look once YOLO algorithm is used for object detection. I have scoured the internet for resources on how to tackle this problem, but there seems to be a lot of resources that point ...
0
votes
0answers
15 views

meanAveragePrecision(mAP) score calculated for the object detection with class imbalance

How is the meanAveragePrecision(mAP) score calculated for the object detection? How can I modify it to take class imbalance into account? Should I make it weighted meanAveragePrecision(mAP) where I ...
2
votes
1answer
132 views

Tensorflow batch normalization for images - padding issue

I'm trying to train anomaly/defect detection network on custom images. Let say I have to detect scratches on special steel boxes and I have two views: side view with dimension 2300 x 550 (width x ...
0
votes
0answers
17 views

what will “Faster RCNN”(or any other object detection algorithm that uses anchors) do in this situation?

Can anyone please tell me what will "Faster RCNN"(or any other object detection algorithm that uses anchors) do in this situation? If there are 2 object and both are inside 2 different anchors and ...
0
votes
1answer
41 views

Object detection training: will mirroring images help or hinder?

Will Tensorflow training benefit from doubling the images by mirroring images (flipping horizontally)? In other words, if the original image contains text that says: "this is a test", the mirrored ...
0
votes
1answer
287 views

what purpose do the grid cells serve in YOLO object detection algorithm?

so I was looking at YOLO and I read several blogs online, but one concept I'm having trouble understanding is why do we want to divide the image into different grids, and then predict the bounding box ...
1
vote
0answers
34 views

clustering objects in point cloud

I am currently working on point cloud data analysis, trying to label objects which are not ground or vegetation e.t.c. So far I tried many clustering algorithms, with moderate success. In my best ...
1
vote
1answer
60 views

Question about bounding boxes to handle false positives

I have trained a model to detect vehicle number plates. The issue is that it returns matches of partial plates, with high confidence. To eliminate partials I want to add two new boxes to the images ...
0
votes
1answer
170 views

What does anchors' scales actually refer to in Faster RCNN?

I am trying to understand the faster RCNN but I can't understand the meaning of anchors' scales? Especially in this article Faster RCNN. The author considers 3 scales $(128^2, 256^2, 512^2)$ ...
0
votes
0answers
19 views

Loss decreases but mAP is dropping

I'm using the RetinaNet model for object detection in images. When I train the model, I all ways see the same behavior: For the first three - four epochs the mAP increases and then it decreases again. ...
0
votes
0answers
41 views

Recognizing an object in multiple images

Suppose I am doing an object detection task from images. However, unlike usual image detection tasks, there is a difference - the images comes in groups of threes and we know that only one of the ...
3
votes
0answers
33 views

Sequential Prediction: Data Modeling and Classical Algorithms

I have data that can be called demographic data. Raw data Person 0001 \begin{array}{|c|c|} \hline Feb\,1981- Apr\,85 & engaged\,\,in\,\,\underline{activity}\,\,\textit{A}\,\,of \,\,\underline{...
2
votes
0answers
49 views

Can you compute errors bars from Precision and Recall?

I am performing an object detection task for counting cars in an image. I have the confusion matrix (TP, FP, FP, TN) of the model. I guess TN is just zero in this case, as we aren't detecting where a ...
0
votes
1answer
159 views

What are the ways to calculate the error rate of a deep Convolutional Neural Network, when the network produces different results using the same data?

I am new to the object recognition community. Here I am asking about the broadly accepted ways to calculate the error rate of a deep CNN when the network produces different results using the same data....
1
vote
0answers
14 views

Seeking the terminology of a particular type of object localization

Much like this paper on cell detection, I have a vision task in which I'd like to output the pixel coordinates of object centers. The number of objects can vary. Effectively I'd like to learn a ...
1
vote
0answers
138 views

Finding objects in an image given a single instance of the object from the same image - Deep Learning approach

I have an aerial image containing planes like this: I want to detect planes in the image (find bounding boxes around planes). For this user draws a bounding box on one of the planes and the algorithm ...
1
vote
0answers
30 views

Active learning for object detection- Batch Selection

I have a small dataset of about 220 images for three classes. I am using YOLO (you only look once) network for an object detection. I am trying to use Active learning in order to reduce the number of ...
1
vote
0answers
196 views

Computing average precision metric and cost fucntion for object detection task using scikitLearn and Tensorflow

I have a Data set that contains 5 thousand pictures of my object of interest and 5 thousand pictures with out it. I trained a Convolutional Neural Network using Tensor Flow to detect the position of ...
1
vote
0answers
28 views

Is it a good idea to train a Neural Network on continiously randomly generated training data? [duplicate]

Hello everyone I'm building a license plate detection model in Tensorflow. I built a function that chooses a license plate at random from a collection of ~5000 plates and puts it in a random place in ...
0
votes
4answers
967 views

Object localization with CNN [closed]

I am interested in locating the center of a playing card on the surface of a table: I have written a script so that I can generate images like this, where the card is moved around and rotated. My ...
2
votes
0answers
66 views

Avoiding OCR performance coupling to upstream Bounding Box model

I have a model pipeline where I first use an object detection deep learning model to locate text regions in images of natural scenery (i.e. outdoor images), and then send the cropped region to a deep ...
0
votes
1answer
19 views

Detecting whether image contains object or not

I've been able to train a CNN for binary classification. It detects whether an image is more likely to contain object A or object B (it returns 0 or 1). How would I go about building a network that ...
0
votes
0answers
41 views

Very Noisy Images

I will train YOLO to recognize drones, I found 70-80 images and I will use Augmentation Libraries to get more images but for my task I also need images which drones are overlapped each other. Can I ...
0
votes
1answer
204 views

mAP calculation in object detection

I'm quite confused as to how I can calculate the AP (average precision) or mAP (mean average precision) to evaluate an object detection model. I specifically want to know if the True Positives (TP) ...
0
votes
1answer
1k views

What is a good loss function for object localisation and classification using a cnn?

Context: Using a CNN to localise a object in an image. There are two kinds of objects present represented by classes C1 and C2. The output of the CNN is 6 nodes i.e. C1, C2, x, y, w, h. Where [C1,C2] =...
1
vote
0answers
25 views

object detection with neural networks: merge classes or not?

When using methods such as Faster R-CNN or Yolo for object detection, does it make sense to cluster visually dissimilar objects to reduce the number of classes? Let's make up an artificial example: ...
4
votes
0answers
786 views

What are the best methods for reducing false positives using tensorflow's object detection framework?

I am training a single object detector with mask rcnn and I have tried several methods for reducing false positives. I started with a few thousand examples of images of the object with bounding boxes ...
0
votes
1answer
287 views

Handling data without ground truth bounding boxes in SSD / RetinaNet?

In the paper SSD: Single Shot MultiBox Detector by Liu et al., 2015, the Matching strategy section reads: During training we need to determine which default ...
2
votes
1answer
72 views

Detect visual attention area in an image [closed]

I'm trying to detect the visual attention area in a given image and crop the image into that area. For instance, given an image of any size and a rectangle of say LxW dimension as an input, I would ...
3
votes
1answer
381 views

Are there networks specialised on object detection for a single class of object?

I want to detect the location of a single class of object, which might occur multiple times in an image. Specifically, this relates to research on detecting brake lights for autonomous vehicles. I ...
7
votes
2answers
1k views

Do more object classes increase or decrease the accuracy of object detection

Assume you have an object detection dataset (e.g, MS COCO or Pascal VOC) with N images where k object classes have been labeled. You train a neural network (e.g., Faster-RCNN or YOLO) and measure the ...
2
votes
1answer
328 views

Coordinate prediction parameterization in object detection networks

State of the art object detection networks, such as RetinaNet, Faster R-CNN, and YOLO, use a coordinate encoding where the bounding box regression is given relative to the anchor box: Centers: $t_x = ...
1
vote
1answer
983 views

Fine Tuning vs. Transferlearning vs. Learning from scratch

In my master thesis, I am researching on transfer learning on a specific use Case, a traffic sign detector implemented as a Single Shot Detector with a VGG16 base network for classification. The ...
0
votes
0answers
812 views

SSD MobileNet v1 loss not converging bounding boxes all over the place

I've trained SSD MobileNet v2 model using Tensorflow API on my own dataset of ~4k dog pictures and it displays bounding boxes all over the place. I've trained with batch size 1. The same dataset ...
1
vote
0answers
34 views

OverFeat paper questions

Can anybody please explain some details of "Overfeat multi-scale classification"? I was reading the overfeat paper1 and came through its section "3.3 Multi-Scale classification". I am unable to ...
1
vote
1answer
341 views

What is the need of multiple Bounding Boxes per grid cell in YOLO v1?

This question is regarding YOLO v1 architecture as in here. I am confused as to why authors have used 2 bounding boxes per grid cell for training. Assuming there can be only one object per grid cell. ...
0
votes
1answer
1k views

why Tensorflow object detection API predicting one class for all object? [closed]

I used Tensorflow object deteciton API following this tutorial and trained it to predict custom images of three category. After 49K steps and with most loss < 0.05 I stopped and froze the model. ...
0
votes
1answer
78 views

In weakly supervised learning for object detection and localization, how does the neural network associate a particular object with its label?

I understand how an object detection algorithm (in particular neural nets) can localize one object. The question is how they can associate a particular object with a particular label when there are ...
6
votes
1answer
934 views

One-shot object detection with Deep Learning

In the recent years, the field of object detection has experienced a major breakthrough after the popularization of the Deep Learning paradigm. Approaches such as YOLO, SSD or FasterRCNN hold the ...
-1
votes
1answer
437 views

Multiple digits MNIST and transfer learning [closed]

I have a sample of 50,000 images, some of which are shown below: $\qquad$ $\qquad$ $\qquad$ $\qquad$ Associated to these images are labels for the digit with the largest pixel size. My goal is ...