Questions tagged [object-detection]

The tag has no usage guidance.

0
votes
0answers
25 views

How to choose our data set wisely?

I have a couple of questions and I was wondering if you could answer them. I have a bunch of images of the cars (side view only). I would like to train a model with those images. My objects of ...
0
votes
0answers
3 views

What is the initial size of anchor in Faster R-CNN?

So we generate anchors for input images which will be later used for classification and then regression for bounding box. If we have image size of 224*224*3 and our feature map is of size 7*7*512. ...
0
votes
0answers
6 views

Object Detection using Faster R-CNN conundrum

So we have our image right? We use some pre-trained model like VGG or Inception which will predict the feature_map. Suppose to a shape of (7,7,512) from the original of (224,224,3). We use this ...
0
votes
0answers
5 views

Should detection times get longer for dlib.train_simple_object_detector when I add more images?

I've played around some with dlib.train_simple_object_detector and have found that as I add more images the detection time grows longer when I later perform detections. Why is this happening? To my ...
0
votes
0answers
11 views

How to detect hand or head using opencv in python (Without bounding box)

Can anyone help me how we can detect hand or head using opencv. I want to detect hand or head in any lighting condition. right now I have developed using bounding box and contour comparison algorithms ...
0
votes
0answers
11 views

How to find the False Positives per Image when using the Tensorflow Object Detection API

I have trained a Faster-RCNN Model using the Tensorflow Object Detection API on a custom dataset consisting of 10 classes. I have evaluated its performance and obtained the mAP and AP for each class. ...
0
votes
0answers
12 views

Image-Level Detection

I am not sure if this is the correct term to use, but I'm looking into Image-Level Detection models. By image-level, I mean models that get an image as an input and then determine whether it belongs ...
1
vote
0answers
11 views

Creating an Object Detection model with images and coordinates of bounding boxes

I am trying to build a custom Object Detection model which can detect guns from a given image. The dataset is from here. The dataset has a good number of images and each image has 4 coordinates of ...
2
votes
1answer
19 views

What's the difference between Haar-like Features and Haar Cascades?

Are they the same in terms of their algorithm? Or do they differ in their respective detection methods?
2
votes
1answer
25 views

Creating a Object Detection model from scratch using Keras

I have a dataset containing 330 images which contain guns. Along with the images, I have a text file associated with each image file which contains, The number of objects ( guns ) in the image. ...
0
votes
1answer
21 views

Extracting structure and content from invoices

I have been lately hugely inspired https://rossum.ai/, which is able to extract text from invoice documents. Do you have any ideas how this could be implemented? Well, it's clear that they did a lot ...
1
vote
1answer
25 views

Does the score output of a classification model has a global meaning?

The scores-output layer contains the class scores that the model generated for the current sample and it is passed thru the softmax layer to get the final output in the form of a probabilities vector. ...
2
votes
1answer
33 views

What is the difference between semantic segmentation, object detection and instance segmentation?

I'm fairly new at computer vision and I've read an explanation at a medium post, however it still isn't clear for me how they truly differ.
0
votes
0answers
8 views

number of images vs num of annotations per image

I am training a fasterRCNN with ResNet-50 as backbone feature extractor, for 2 classes(OBJECT OF INTEREST & background). Below is the information about my data: Big and medium sized objects of ...
2
votes
0answers
15 views

Is it possible to modify the layers of the models present in the Tensorflow Object Detection API

I would like to know if there is any way in which we can change the base layers of the models offered by the Tensorflow Object Detection API and if so, is it possible to change things like pooling/...
0
votes
0answers
31 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 ...
0
votes
0answers
25 views

I can not find a pre-trained neural network model for object detection

A simple model is needed, but with good accuracy, mAP for detecting objects is preferably trained on COCO, preferably on ipynb (to run or train on google colab). The models from the Tensorflow (...
0
votes
0answers
14 views

How to change the neural network model to improve the accuracy of mAP without learning from 0, but retraining already trained model

how you can change the Faster R-CNN Resnet 101 or Faster R-CNN Inception Resnet V2 model to improve the accuracy of mAP detection without learning the model with 0, but retraining already trained ...
0
votes
0answers
18 views

How do I change the IOU while running the eval.py script using the Tensorflow object detection API

I have trained a FasterRCNN_Inception_Resnet_v2 model using the TensorFlow object detection API on my own custom dataset. I am successfully able to evaluate the performance and get the AP of each ...
0
votes
0answers
14 views

State of the art in accurate object tracking & detection

Im working with an offline video file which has vehicles in it. I tried using YOLOv3, but it is not very accurate. Moreover, it kind of fails in occlusion. I am concerned more about accuracy than ...
1
vote
1answer
28 views

What is a basic object detection/localization ML algorithm that can be used for my relatively simple image set?

I have a relatively simple object localization task. I have an image set that are either uniform or contain an 'object' consisting of a black circular shape at some position in the image. The labels ...
1
vote
0answers
37 views

Is there a metric for counting AND classification simultaneously?

I'm working on a project that mixes object detection and crowd counting. The metric for object detection is mAP, which combines the regression of the bounding boxes with the precision of the ...
0
votes
0answers
61 views

Bead detection in a necklace using TensorFlow Object detection

I want to detect and show the count of beads in a necklace. For this purpose, I am using a TensorFlow object detection API. I have the images dataset similar to this image, I want to know what kind ...
1
vote
1answer
58 views

People detection methods

In my problem I want to distinguish people from other shapes in images e.g I want to accurately know how many people are in specific region of image (at least for small number of people, for crowded ...
1
vote
0answers
29 views

How to calculate Average Precision for Image Segmentation?

If I've understood things correctly, when calculating AP for Object Detection (e.g. VOC, COCO etc) the procedure is: collect up all the detected objects in your dataset sort the detections by their ...
0
votes
0answers
32 views

Bouding box regression in R-CNN (and similar methods)

Here is the bounding-box regression technique used in R-CNN What I don't understand is why $t_w$ needs to be $\log (G_w / P_w)$ instead of just $G_w / P_w$ (i.e. using normalized coordinates just ...
0
votes
0answers
156 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 ...
1
vote
0answers
24 views

What is wrong with my Precision-Recall curve?

Hi, I found this: https://github.com/rafaelpadilla/Object-Detection-Metrics I prepared my data: ground-truth and prediction files with bounding boxes. but I got a very strange plot. What do you thing?
1
vote
2answers
30 views

Detection model - Training with class-instance limit-awareness

Is there a way to make a detection model aware of the maximal number of possible objects of a given class within a single image? For example in a toy case with 2 classes. If I know that in every ...
0
votes
0answers
17 views

Should images with multiple objects of the same class be used as training sample for multi-classes object detection models?

Let's say the model try to detect all the grapes on a branch of grapes. Can I use images of a grape branch with all the grapes labeled as a training sample? Will it affect the quality of the RPN ? Is ...
1
vote
0answers
148 views

YOLO v3 complete architecture

I am attempting to implement YOLO v3 in Tensorflow-Keras from scratch, with the aim of training my own model on a custom dataset. By that, I mean without using pretrained weights. I have gone through ...
0
votes
1answer
19 views

Action Recognition for multiple objects and localization

I want to ask question regarding the action detection on the video with proposed frames. I've used Temporal 3D ConvNet for the action recognition on video. Successfully trained it and can recognize ...
1
vote
1answer
64 views

Detecting address labels using Tensorflow Object Detection API

I am experimenting with the Tensorflow Object Detection API on a Windows 7 machine. I am trying to detect US address labels (and similar blocks of text) as they appear on a piece of mail or an ...
2
votes
1answer
39 views

How to detect different brands of milk

I'm trying to create a object detection model to detect different type of milk. What is the best approach to achieve the result in the picture below? As you can see in the picture, this model did ...
2
votes
0answers
127 views

mAP using Tensorflow object detection API

After I train my object detector using the Tensorflow object detection API(to detect only cars), I get an mAP value around 0.32 while running the eval.py script. However, in the Tensorflow Detection ...
2
votes
1answer
64 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 ...
0
votes
0answers
15 views

What (and how) should I use for object detection in this case?

I have read a few papers on object detection and analyzed several implementations of object detection applied to car number plates. In my case, the task is a bit more difficult in that I need to ...
0
votes
0answers
18 views

ChainerCV training data processing

I have an imageset of 250 images of shape (3, 320, 240) and 250 annotation files and a ImageSet/Main folder containing train, val, test text files which has lists of images for train, test and ...
1
vote
1answer
169 views

Issues with training SSD on own dataset

I'm new to ML and trying to train a SSD300, with some Keras-Code github.com/pierluigiferrari/ssd_keras I found on github. For training I'm using an own (very small) dataset of objects that are not in ...
1
vote
1answer
72 views

Extracting the feature map in Tensorflow Object Detection API

I would like to know how can I extract the feature map of a mobilenet trained on tensorflow object detection API. I want to take that feature map in order to feed another classifier. Thanks!
1
vote
0answers
15 views

Is it beneficial to train 1 object detector for N classes vs N object detectors each for a different class?

I always wondered if training an object detector to recognize (let's say), dogs and cats performs better or worse than training 2 object detectors, one for cats only and one for dogs only. Would this ...
0
votes
0answers
170 views

Odd Loss Curves for Object Detection Task

I'm re-training a Single Shot Detector (specifically the ssdlite_mobilenet_v2_coco from the TensorFlow model zoo) to detect some new images. I have about 15k images in the training set and about 4k in ...
0
votes
0answers
101 views

openCV tracking algorith & Haar Cascades

(long question sorry) This script below will utilize my windows 10 laptop webcam detect faces with haar cascades and calculate the centroid of what ever is captured. Besides OpenCV I also use the ...
0
votes
0answers
9 views

How to count objects in ChainerCV

I want to know how to count objects in object detection using ChainerCV. I want to clarify if we need to work with vis_bbox for counting and if yes how to use it to count. Do I have to write count ...
0
votes
1answer
105 views

mean average precision - pseudo code

There are many blog posts and threads concerning the computation of mAP, both for PASCAL and for COCO. Still, they do not answer some fundamental questions. I am listing here the flow as I understand ...
0
votes
1answer
102 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
23 views

Keras - How to using Cnn trained model on video image.?

I have trained Cat and dog image using CNN with Python ( total 10K, 8K for training and 2K for testing ). I want to make prediction in a video. Video Contain both cat and dog at a single moment. How ...
0
votes
0answers
55 views

How is Stochastic Gradient Descent done in Faster RCNN?

In Tenosrflow Object Detection API, you can choose different pretrained models such as Faster RCNN, SSD. Then you can specify the batch size during training. I know that for Stochastic Gradient ...