Questions tagged [object-detection]

Object detection is a computer-vision and image-processing technique for locating instances of objects in images or videos. Common applications include face detection and object tracking. Object detection algorithms typically leverage machine learning or deep learning to produce meaningful results.

Filter by
Sorted by
Tagged with
1
vote
1answer
175 views

YOLO Dense Prediction

I have two questions about dense prediction in YOLOv4 paper What does it mean by the (hard negative, online hard) example mining method is not applicable to one-stage object detector, because this ...
0
votes
0answers
6 views

Reduce Training steps for SSD-300

I am new to deep learning and I am trying to train my SSD-300 (single shot detector) model which is taking too long. For example even though I ran 50 epochs, it is training for 108370+ global steps. I ...
0
votes
1answer
30 views

Is an image with 5 labels equivalent to 5 images with 1 label?

I am collecting data to train an object detection model using and was wondering if 5 labels in the same image and 5 images with 1 label each provided the same quality of input training data. Example: ...
0
votes
0answers
5 views

Soft-NMS during Inference

I have read the paper about the soft-NMS and the problem that tries to solve. Does it make sense to use this algorithm during inference apart from training? It smooths the predictions on the bounding ...
2
votes
0answers
8 views

Heterogenous data between classes in object detector

I have created a synthetic dataset for object detection with about a dozen classes by placing models of the classes in front of random images (from the MIT Place2 dataset) in Blender. This is working ...
0
votes
0answers
26 views

Does having two different models improve performance for underrepresented classes?

I am currently working on a dataset that has approximately 7000 annotations, but suffers from severe class imbalance (there are 1331 annotations for the most represented class, and 77 for the least ...
0
votes
1answer
29 views

Train a point rather than a bounding box for object detection

In the graph below, object detection is done through a point that points to the right place rather than a bounding box (e.g., using faster RCNN). What method enables to train such a point?
1
vote
1answer
105 views

Is there any paper of object detection that detect not trained class or object?

After reading some object detection papers (kinds of R-CNN, YOLO,...) I'm wondering if there is a detector that detects objects ...
0
votes
0answers
33 views

Fine-tuning a pre-trained Tensorflow model

I have two questions regarding fine-tuning a pre-trained Tensorflow model on a mix of high-quality and low-quality images.In other words, ' Does the large contrast in image quality confuses the model ...
0
votes
0answers
13 views

How can I detect symbols/icons on a label?

Given this label: How can I identify that the CE mark is there? I've tried template matching with OpenCV but results are quite inconsistent because of symbol-template size differences (scaling & ...
3
votes
2answers
94 views

How can we create an label, value detector?

I am trying to implement an text detector using MaskRCNN such that the model detects the label and value as shown in the image below. Detecting the same is easier for fields like page date and order ...
2
votes
1answer
42 views

Detect Objects on a table

is it possible to train a model which detects and draws bounding boxes for objects on a table, when I use a dataset where objects on a table are labeled with boundingboxes?
0
votes
1answer
20 views

Activation Maps using Tensorflow Object Detection API

I am trying to create visual explanations such as GradCAM from a trained object detection model. In order to implement the algorithm I need to access intermediate tensors and calculate gradients to ...
2
votes
1answer
86 views

Why yolo4 pytorch re-training loss seems high as like first time training?

I had a setup a yolo4 pytorch framework in google colab by cloning git clone https://github.com/roboflow-ai/pytorch-YOLOv4.git. I generated checkpoints by giving ...
0
votes
2answers
39 views

Logic behind pre-trained weights and transfer learning

I am not sure about the logic behind, how pre-trained weights actually make sense and translate into a new problem. To be more specific; for example in a object detection network, how would a model's ...
0
votes
1answer
174 views

How to obtain and load a good initial data set for object localization?

I'm looking for a good data set for training a CNN based network to do object localization (i.e. a data set with class labels and bounding box data). What is a good initial data set to use? How can ...
2
votes
1answer
333 views

Curve of MAPs to evaluate training progress of Mask RCNN on synthetic data

Is MAP (Mean Average Precision) a good substitute for measuring training and validation accuracy at different stages of training a machine learning model for object detection? I am retraining a Mask ...
1
vote
0answers
440 views

Calculating the F score of Object Detection of Mask RCNN

I am using Detectron2 Mask RCNN for an object detection problem. The images consist of cells that are very close to each other. I can not use mAP as a performance measure since the annotations are a ...
0
votes
0answers
9 views

What kinds of changes can I attempt on my object detector .config file to improve the detection accuracy?

I have trained an object detection model with 2 classes, around 7500 images, and approx. 10,000 annotations per class. I was able to fine-tune Faster R-CNN with ResNet (V1) from the Tensorflow Object ...
1
vote
1answer
63 views

Average Precision if Target Class is Not in Evaluation

Suppose I have 5 classes, denoted by 1, 2, 3, 4, and 5, and this is used in object detection. When evaluating an object detection performance, suppose I have classes 1, 2, and 3 present, but classes 4 ...
2
votes
0answers
26 views

Few shot learning and object detector

I have a dataset with a lot of classes (~10000+) but few examples by classes (~15-). I want to classify these classes, but there are some specificities. My examples provide from a video stream. ...
2
votes
1answer
212 views

YOLOv3 Predicting bounding boxes for grid containing multiple centers

I recently started learning about YOLO and object detection, and I am kind of stuck on something. I was wondering if someone could explain to me what happens when a grid cell contains the centers of ...
1
vote
2answers
131 views

What is Image Annotation?

Why do we need to use Labelimg tool for object detection? After labeling the bunch of training images using labelimg tool which will give CSV file How that CSV file works with TensorFlow object ...
1
vote
1answer
246 views

Understanding 'scale_boxes' in YOLO Algorithm of CNN

I'm studying Andrew NG's Convolutional Neural Networks and am in Week 3 of the course which deals with object detection using YOLO algorithm . I don't understand one section in the programming ...
0
votes
0answers
6 views

Why do CNN regression models fail to localise an object when the scale, aspect & image type has significant variance?

Background I'm wanting to understand how to build an object detection algorithm from scratch. My initial thoughts were that architectures like YOLO and Faster-RCNN would find any object given enough ...
0
votes
0answers
19 views

Why is VGG16 better for object localisation than MobileNet?

Prologue I have been trying to perform object localization to provide the [x1,y1,x2,y2] coordinates of objects in an image using Keras. I was stuck for ever because I was using MobileNetV2 as my ...
0
votes
0answers
30 views

Extract features using Bounding Box

I have a ground truth bounding box for a 3d object. I would like to extract useful features for the object. My goal is to concatenate these visual object features with language features (from the ...
0
votes
0answers
22 views

COVID-19 Rapid Test Result Image Detection

I fine-tuned an Inception V3 model provided in AWS SageMaker to detect COVID-19 Rapid Test Results (see the image below for an example). I provided about 20 pictures of negative and about 20 pictures ...
2
votes
1answer
318 views

What am I supposed to see on tensorboard images tab?

I'm training an object detection model with Tensorflow and monitor the training task with tensorboard. I was expecting in the Images tab of tensorboard that displayed images would show a bounding box (...
1
vote
1answer
823 views

Tuning SSD Mobilenet for better performance

I'm using Tensorflow's SSD Mobilenet V2 object detection code and am so far disappointed by the results I've gotten. I'm hoping that somebody can take a look at what I've done so far and suggest how I ...
1
vote
1answer
588 views

SSD based on ResNet-101 doesn't improve over SSD-VGGNet

I am training a SSD model for detecting mobile cranes. The training dataset contains 1,000 images and test set over 400 images. About 200 epochs gave mAP 83%, but my target is 90%. So I trained SSD-...
0
votes
1answer
925 views
0
votes
1answer
38 views

Feature extraction in machine learning

I am a bit confused by reading A survey on object detection in remote sensing. They state that machine learning-based object detection consists of three essential parts - feature extraction, feature ...
0
votes
0answers
25 views

Minibatch SGD performs better than Adam for Region proposal network training

I am using both minibatch SGD (with momentum) and Adam for training a region proposal network. The library used is KERAS. The batch size in both cases is 5 and initial learning rate is 0.01. The ...
1
vote
0answers
15 views

Forward height/width information into classification model?

Please forgive me if it's not the right StackExchange, but I didn't find any related to computer vision questions. Problem: I have a pipeline for object detection and classification where I first ...
2
votes
1answer
78 views

Difference between text-based image retrieval and natural language object retrieval

I am working on creating a model that locates an object in the scene (2D image or 3D scene) using a natural language query. I came across this paper on natural language object retrieval that mentions ...
1
vote
1answer
75 views

How to resize image along with their mask?

I have original images of the size 1935x1481. I am using labelme to annotate the images. I am creating polygons on the original image. Is there a way to resize the image along with their mask? I am ...
1
vote
1answer
360 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 ...
0
votes
0answers
4 views

How to create COCO format data out of list of boxes

I have $N$ images. I have a script that extracts boundary boxes of an object that I am interested in. For each image, I may get $m$ boxes. There is only one item that I am interested in which is cat. ...
1
vote
1answer
9 views

'Collision' resolution for precision in object detection

For object detection we often use metrics based on precision/recall. My question is what is generally the process of matching the prediction and ground truth bound boxes, when there are multiple ...
0
votes
0answers
10 views

What does the Region Proposal Network output in Faster-RCNNs?

Does it output corrections and offsets to the anchor boxes(that were generated by using some specific aspect ratios and scales)? Also if this the answer is YES, Suppose I have 3 scales - [8,16,32] and ...
0
votes
0answers
13 views

Evaluating the performance of tracking multiple objects detected with object detection

I have a ground truth dataset where the objects have been manually annotated and each object have been provided an ID that is consistent through time. There are no false positives or false negatives ...
0
votes
2answers
88 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 ...
1
vote
0answers
25 views

Why YOLO algorithm predicts B boxes for each grid cell S?

In yolo each grid cell predicts multiple bounding boxes lets say in YOLOv1 it predicts B=2, what is the advantage as it only predicts class probabilities only once for each grid cell. If that so why ...
2
votes
1answer
57 views

Where can I find free multi-instance single-label datasets for object detection?

I'm trying to find free multi-instance single-label datasets for object detection online. By "multi-instance and single-label" I mean that each image contains only object belonging to one ...
0
votes
0answers
17 views

how to make image classification model to detect object and track object in a video

i have built a disaster classification model . now i want to use this classification model to detect ex- cyclone in a video to draw bounding box around it and track the cyclone if possible.is it ...
0
votes
0answers
13 views

can i do object detection on pretrained classification model...?

so i built a natural disaster classification model using transfer learning Renet50(tensor flow) got 98% accuracy and now instead of just classifying natural disaster lets say a cyclone appeared in ...
1
vote
1answer
63 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 ...
0
votes
0answers
10 views

Compute IoU for each class in Mask R-cnn

I'm trying to compute the IoU, with the matterport Mask R-cnn implementation, for each class (13 in total) that i have in my dataset. For now i managed to compute the average IoU for all the classes ...

1
2 3 4 5
7