Questions tagged [object-detection]

For questions related to object detection (where objects can be e.g. humans, dogs, houses, etc.), whose meaning or definition can vary depending on the context. OD can refer to the task of locating (i.e. finding the coordinates) an object in an image (so, in this case, it would be a synonym for object localization) or the task of locating the object and classifying it (i.e. object localization + object classification).

Filter by
Sorted by
Tagged with
-1 votes
0 answers
10 views

Converting TensorFlow Keras model API to model subclassing [closed]

For a simple TF2 Object detection CNN architecture defined using Keras's functional API as follows: ...
user avatar
  • 183
0 votes
0 answers
19 views

What object detection algorithm is the best for my particular problem?

I am trying to write a program to put a bounding box around dead fish, and not the live ones, in a video. I have minimal data (~5k frames and ~7k objects in total ) and it is VERY low quality (poor ...
user avatar
  • 11
1 vote
1 answer
30 views

How does YOLO detect the object when the object is in multiple grid cells?

I have been reading various articles and watching videos on YouTube, but I can't seem to understand one thing. How does YOLO make a bounding box for an object if it is in multiple grid cells? For ...
user avatar
1 vote
1 answer
17 views

Deep Learning for occlusion recognition is 2D or 3D space [closed]

Given a dataset of spatial 2D or 3D object map with their bounding box annotations, How feasible would it be to train a deep learning model to recognize (classify) "occluded" objects from a ...
user avatar
  • 11
0 votes
0 answers
27 views

At which step in faster R-CNN is non-maximum suppression performed?

At which step in faster R-CNN is non-maximum suppression performed? In some book, I have read that it is performed after passing the features through the last fully connected layers, which are located ...
user avatar
  • 1
-1 votes
1 answer
33 views

Extract person silhouette from photo or video

Are there any programming libraries or neural network design patterns designed for the task of finding persons in a photo/video and extracting their silhouettes (i.e. not only the rectangle containing ...
user avatar
  • 101
0 votes
1 answer
58 views

Is there way to segment an image without labeling/classification, as well as supervised learning?

Is there way to segment an image without labeling/classification, as well as supervised learning? For an illustrative example, if one considers an image with a dog and a cup (we don't particularly ...
user avatar
0 votes
0 answers
23 views

In traditional R-CNN, why do we use an SVM after training a ConvNet with a log loss?

I'm learning about development of object detection algorithms and came across this fact which seems strange to me - In the multi-stage pipeline of R-CNN, after using a region extractor to crop the ...
user avatar
0 votes
1 answer
28 views

Object Classification: How to decide which detected region is a RoI for classification?

I am working on a project where I am working on the Flickr-47 dataset to do logo detection and classification. My approach is to first finetune a YOLO v5 model with high recall to detect as many "...
user avatar
0 votes
1 answer
52 views

For an image (of any object), how to find its location in the other image(s) which contains it, given there are no labels or annotations for any image

Problem Statement: I am given 2 sets of images. All the images in both sets are without annotations and labels. First set : a set of images of the grocery store shelves (captured in the grocery stores)...
user avatar
0 votes
1 answer
24 views

Performance of augmented dataset with or without original images

I am training on yolo and I had a small dataset. I decided to increase it by augmenting it with rotation, shearing, etc to increase the size and increase accuracy. Now I have seen augmented datasets ...
user avatar
0 votes
0 answers
21 views

Best approach for object localization of small objects in 3D medical images

I'm working on a project where I try to detect aneurysms (widening of blood vessels) on brain MRI image data (TOF MRAs). I have a dataset of around 290 images. The images are all 128x128x80 px. I have ...
user avatar
0 votes
0 answers
17 views

3D object dimensions calculation from RGB camera

I happen to have one project which consists of a camera that should read barcode and calculate the parcel's dimensions. Barcode information is used for determining the parcel's designated address, etc,...
user avatar
0 votes
0 answers
19 views

Should we collect additional images if we use pre-trained dataset for specific classes?

At the moment, I'm working on one a project related to object detection. I'm going to use YOLO because it is a better option. I have collected images for traffic signs, but I also need to detect cars, ...
user avatar
0 votes
1 answer
60 views

Avoid unintentional "merging" in cluttered object detection

I have a problem that has bothered me quite some time. With modern methods object detectors can often be accurately trained, even with small to medium sized datasets. However, there is one thing where ...
user avatar
1 vote
1 answer
41 views

Why is it called "area of union" when calculating the Intersection over Union?

When calculating the Intersection Over Union the following explanation is widely used. (Source: A Survey on Performance Metrics for Object-Detection Algorithms, by Padilla et al. 2020) The image and ...
user avatar
  • 13
1 vote
0 answers
49 views

Question about true positive and false positive detections in object detection

I am computing true positives, false positives, and false negatives in order to calculate my model's precision and recall. I am using YOLOv5. According to this source and this one, an IoU overlap ...
user avatar
  • 119
1 vote
1 answer
56 views

Mask R-CNN: How are the computed masks projected back to the input image?

The computed masks by Mask R-CNN are of fixed size $m \times m$ each. How are they projected back to the image?
user avatar
  • 21
0 votes
2 answers
151 views

How to count overlapping objects with neural networks

Consider the following task to be solved by a neural network: Given a $N\times N$ pixel grid with up to $M$ objects drawn on it, either squares (9 pixels) or diamonds (5 pixels): square    diamond The ...
user avatar
1 vote
0 answers
23 views

Why are the learned offsets of anchor boxes in the RCNN object detection models scale invariant?

In the original RCNN paper (https://arxiv.org/pdf/1311.2524.pdf) and continued in later RCNN papers such as faster RCNN (https://arxiv.org/pdf/1506.01497.pdf) the learned offsets of the anchor boxes ...
user avatar
  • 143
2 votes
1 answer
58 views

How does a bounding box detection network "know" about absolute position?

I've always found bounding box regression a bit weird. There's no positional encoding like in vision transformers, so how does the network "know" the absolute position when producing ...
user avatar
-1 votes
1 answer
61 views

Equations for computing true positives and false positives when using object detection algorithms?

I am running some evaluation metrics using the YOLOv5 object detection algorithm, and wish to calculate my true positives and false positives. For instance, the evaluation metric outputs are as ...
user avatar
  • 119
0 votes
0 answers
76 views

How to use EfficientDet for semantic segmentation?

In the EfficientDet paper, section 5.2. 5.2. EfficientDet for Semantic Segmentation, the authors say we modify our EfficientDet model to keep feature level $\{P2, P3, ..., P7\}$ in BiFPN, but only ...
user avatar
  • 11
1 vote
1 answer
151 views

How does the classification head of EfficientDet work?

EfficientDet outputs classes and bounding boxes. My question is about both but specifically I am interested in the class prediction net part. In the paper's diagram it shows 2 conv layers. I don't ...
user avatar
  • 11
0 votes
0 answers
43 views

Object Center-point detection/tracking without bounding box

The dataset is of microscopic cells. The data format is that it comes with annotations of the center point location of each cell. Usually, the object detection/tracking dataset comes with a bounding ...
user avatar
2 votes
0 answers
40 views

What would be a reasonable option for clustering for unknown number of clusters and a lot of outliers?

I am implementing the CV detection pipeline with the use of SIFT and KNN Matcher. Image keypoints matched to the query keypoints produce the following image: The matched objects have a lot of key ...
user avatar
0 votes
0 answers
62 views

Object detection: when there's only 1 object in each image

Good day. I have a custom dataset for object detection, which has imbalance that each image has only one object annotation. I trained the object detection model(Efficientdet-dx) on TensorFlow object ...
user avatar
  • 1
0 votes
1 answer
35 views

Multiple labels for the same rectbox?

My goal is to identify the horse in a photo. I'm dealing with about 500 unique horses. My feeling is that the best way to distinguish one horse from another is by its face. So I trained Yolov5 ...
user avatar
2 votes
0 answers
20 views

Can a GIoU loss (generalized intersection over union) be used after an STN module (spatial transformer network)?

I have a model that uses an STN module for number detection and Mean Squared Error loss. But I would like to replace it for GIoU, because MSE doesn't take into account how much of the target area has ...
user avatar
  • 201
0 votes
1 answer
87 views

How do Tensorflow models and YOLO differ in terms of training steps?

Can anybody explain how the training steps work for the Tensorflow Object Detection algorithms available on the Tensorflow 2 Detection Model Zoo? For instance, YOLOv5 cycles through epochs. As I ...
user avatar
  • 119
1 vote
1 answer
28 views

When is an object detection approach over a CNN approach appropriate?

I understand that CNNs are for image classification while object detection is for localization + classification of the objects detected. However, in particular, AI for chest radiographs, why is object ...
user avatar
1 vote
1 answer
57 views

What kind of algorithm or approach can I use to find a specific type of object in an image?

What kind of algorithm or approach can I use to find a specific type of object in an image? In particular, I am interested in finding an object like a windmill in an image taken, for example, from ...
user avatar
  • 111
0 votes
0 answers
10 views

Why the two identical "IoU comparing procedures" are needed in Faster R-CNN(RPN & RCNN)?

As far as I know, there are two same 'IoU comparing procedures' in RPN and RCNN, but why is the same operation held twice? The paragraph right below is what I've comprehended about the Faster R-CNN. ...
user avatar
  • 1
2 votes
1 answer
136 views

How do I choose the hyper-parameters for a model to detect different guitar chords?

I need to build a hand detector that recognizes the chord played by a hand on a guitar. I read this article Static Hand Gesture Recognition using Convolutional Neural Network with Data Augmentation ...
user avatar
  • 73
2 votes
0 answers
42 views

Which method can accurately detect circular/angular shapes? (attached example)

Is there a method to detect shapes like these accurately and efficiently? I have tried the OpenCv Haar Casacade Classifier which does not work well. These shapes should all be the same class object ...
user avatar
1 vote
1 answer
89 views

Why do the object detection networks produce multiple anchor boxes per location?

In various neural network detection pipelines, the detection works as follows: One processes the input image through the pretrained backbone Some additional convolutional layers The detection head, ...
user avatar
0 votes
0 answers
13 views

Counting number of coaches in a train from real time video feed

I have a real time video feed of a train platform. I was able to detect coaches using CNN based model. But how can I calculate number of coaches in the train that passed the platform as well as the ...
user avatar
0 votes
0 answers
68 views

Data Augmentation for Object Detection - Polygon Region Shape

I'm looking to run a Mask RCNN code on my dataset of about 2700 images. The images are too large and I would like to resize them, and I would also like to add some shear, scale and zoom augmentations. ...
user avatar
1 vote
0 answers
24 views

In anchor based object detection, why don't the anchors share the same weights?

After reading about YOLO V3 and Faster R-CNN, I don't understand why the weights for the regression head aren't the same across all boxes of the same size. Given that the backbone of these systems is ...
user avatar
0 votes
0 answers
50 views

Which neural network architecture to use to detect very close and very small blobs in high resolution fluorescence images?

Context I am developing a pipeline to automate the detection of small, almost circular, bright blobs (4px) (see first image below) on high-resolution fluorescence images (2048px) and later to assign ...
user avatar
  • 101
1 vote
1 answer
423 views

Tensorflow object detection model total loss starts out good, but suddenly explodes up to high loss numbers

I'm training a Tensorflow object detection model with approx. 7500 images of two classes, which contains approx. 10,000 classes per class. I'm using Tensorflow 2.6.0, in case that is relavent. I am ...
user avatar
  • 119
0 votes
1 answer
76 views

How to handle an unbalanced dataset when training object detection algorithms?

I am training an object detection model, and I have some very highly unbalanced data annotations. I have almost 11,000 images, all with dimensions of 1024 $\times$ 1024. Within those images I have the ...
user avatar
  • 119
0 votes
0 answers
38 views

How big should the dataset for retraining ssd_mobilenet_v2 be?

I have retrained ssd_mobilenet_v2 using my own dataset with 2 classes (pen or pencil), using object detection API. For my project, I expect users to select specific pencils from all pencils and ...
user avatar
  • 1
1 vote
1 answer
38 views

Role of confidence or classification score in object detection mAP metrics

I know that mAP (mean Average Precision) is the common evaluation metric for the object detection tasks. It uses IoU (Intersection over Union) threshold such as mAP@0.5 to evaluate whether the ...
user avatar
0 votes
1 answer
42 views

What does a value of -1.000 mean in MS COCO Metrics for Object Detection

I am training some Object-Detection-Models from the TensorFlow Object Detection API and got from the evaluation with MS COCO metrics the following results for Average Precision: IoU = 0.5;0.9 maxDets =...
user avatar
0 votes
0 answers
334 views

How to get bounding box coordinates of all detected objects in yolov5 object detection?

While there is a similar question on stackoverflow, it pertains to yolov4 which, unlike yolov5, uses darknet. Yolov5 is far more intuitive to use than v4 and so a solution to this in v5 is desirable. ...
user avatar
0 votes
0 answers
26 views

How to improve detection of wide objects?

I am working on a project where part of it is to detect PV module arrays, I trained few object detection models through TensorFlow Object Detection API and the problem I got is that the trained models ...
user avatar
  • 1,039
0 votes
1 answer
249 views

Is it possible that the fine-tuned pre-trained model performs worse than the original pre-trained model?

I have downloaded a pre-trained EfficientDet D2 model (Tensorflow 2.0) and trained it on some data (about 20000 images with 20 classes). I set the number of steps to 25000 and batch size to 3 (...
user avatar
  • 103
0 votes
0 answers
14 views

How to scale Computer Vision? How to implement Emotion detection from live video feed of N different video simultaneously?

I have a pipeline based on Scaled Yolov4 detection algorithm for faces which extract faces of users and then uses a CNN to ...
user avatar
  • 233
0 votes
0 answers
37 views

How to work deeper with YOLO v4 scaled

I am pretty new in object detection. When I did some classification using TF with pretrained models I changed some last layers and choosed how many layers I want to train. I don't really get it with ...
user avatar
  • 1